WO2020260735A1 - Method and system for classifying banknotes based on neuroanalysis - Google Patents

Method and system for classifying banknotes based on neuroanalysis Download PDF

Info

Publication number
WO2020260735A1
WO2020260735A1 PCT/ES2020/070383 ES2020070383W WO2020260735A1 WO 2020260735 A1 WO2020260735 A1 WO 2020260735A1 ES 2020070383 W ES2020070383 W ES 2020070383W WO 2020260735 A1 WO2020260735 A1 WO 2020260735A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
biometric
ticket
neurometric
banknote
Prior art date
Application number
PCT/ES2020/070383
Other languages
Spanish (es)
French (fr)
Inventor
María Carmen TORRECILLA MORENO
Mariano Luis ALCAÑIZ RAYA
Jaime Guixeres Provinciale
Javier MARÍN MORALES
Diego ÁLVAREZ RODRÍGUEZ
Fernando LEÓN MARTÍNEZ
José María SÁNCHEZ ECHAVE
Miguel Vicente LÓPEZ SOBLECHERO
Rubén ORTUÑO MOLINERO
Original Assignee
Banco De España
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Banco De España filed Critical Banco De España
Publication of WO2020260735A1 publication Critical patent/WO2020260735A1/en

Links

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q90/00—Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/003—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency using security elements

Definitions

  • the present invention relates to the technical field of neuroanalysis of objects through the processing of biometric signals of users exposed to said objects and, more specifically, to the characterization of banknotes and communication material thereof based on quantifiable information extracted from biometric signals, which makes it possible to classify banknotes and their communication material according to an objective perception of users of certain parameters on the design and security elements.
  • banknotes must respond to aesthetic and functional criteria that allow their easy recognition, detect their authenticity or simplify their handling while complying with a multitude of technical requirements both from the public and from manufacturers and issuing bodies.
  • the banknote is a means of communication in itself with which it is intended to communicate the message expressed in its design
  • the public's requirements should take into account the public's intellectual and emotional processes on how they perceive these aesthetic and functional aspects. to ensure that the message embedded in the banknote design is received by the public in a manner true to the communication purpose of the design.
  • the communication materials must also be prepared taking into account the intellectual and emotional processes of the public in order to generate the greatest possible communicative impact on it, in order to maximize the guarantee that the public has received the training message and, moreover, he has understood it as he was expected to. For this, it is so important to evaluate the content incorporated in the Communication materials, such as the materials themselves (brochures, images, videos, advertisements, etc.), such as the distribution of said materials in the different communication channels (web, radio, TV, written press, etc.).
  • Implicit measures refer to methods and techniques capable of capturing or tracking implicit mental processes or their results, including brain imaging, behavioral monitoring, and psychosomatic outcomes. Neuroscience has shown that in most of the brain processes that regulate our emotions, attitudes, behaviors and decisions, our conscience does not intervene. That is, these implicit processes are brain functions that occur automatically and without conscious control or awareness, which is in contrast to explicit processes that occur through conscious executive control.
  • the present invention describes, in a first aspect, a method for classifying banknotes, based on neuroanalysis, comprising the steps of: providing a user with visual information on a banknote ; acquiring, by means of a sensor of an input module at least one biometric signal from the user, in response to the visual information of the ticket; segmenting, in a processing module, the biometric signals acquired in predetermined periods of time; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with the pre-established patterns; obtain at least one biometric variable based on the identified events; analyze, in the process module, the biometric variables, according to previously known results stored in a database; establish, in the process module, a neurometric indicator based on the previous analysis; and classifying, in an output module, the bill according to the established neurometric indicator.
  • the visual information of the banknote is provided physically, virtually or through a combination of the two in a tangible interface on which virtual elements added to a physical ticket using augmented reality technology.
  • the biometric signal comprises information from at least one implicit process of the user, to be selected from: analysis of gestures in the interaction of the ticket with the hands, eye tracking and analysis of facial expression.
  • the biometric signal comprises information on a physiological response of the user to be selected from: a cerebral response, a variation of the heart rate and the conductance of the skin.
  • the present invention contemplates the possibility of obtaining a biometric variable of the user's eye tracking, where the identified events result from the comparison of the eye tracking signal with a pattern that establishes a first threshold of movement speed of the user's eye that determines the presence of a fixation event or a saccadic event. Additionally, the possibility of, once a saccadic movement has been detected, is contemplated, determining whether it corresponds to an environmental saccadic movement or a focal saccadic movement, according to a second pre-established threshold of angular deviation of the user's eye during said event.
  • biometric variables obtained by the present invention are contemplated to comprise quantifiable information on said identified events, to be selected from: number of identified events, average duration of identified events, frequency of each identified event in a preset time, sequence of events identified and number of visits to the same predefined area.
  • the area of interest is greater than or equal to the area of the bill occupied by the security element and where the area of interest includes the area of the bill occupied by said security element.
  • analyzing the biometric variables according to previously known results comprises training a supervised learning system of the process module according to the following steps:
  • the possibility of analyzing the biometric variables through the supervised learning module of the process module is contemplated, following the steps of: providing the initial value of the neurometric indicator, assigned to each ticket, in an input of the learning system; apply a predictive model, by the supervised learning system, on the biometric variables obtained by the process module and the assigned initial value; and validate, through a cross-validation process, with a previously determined number of iterations, the predictive model.
  • the partial metrics of the present invention represent one or more of the following user's brain cognitive processes: visual interest, attention, evoked emotions, motivation, mental load, stress, and arousal level.
  • the user is provided with tactile and audible information about the bill.
  • a second aspect of the invention refers to a system for classifying banknotes, based on neuroanalysis, comprising the following elements: - an input module comprising at least one sensor, configured to acquire a biometric signal from the user, in response to visual information of the ticket provided to said user;
  • a processing module configured to segment the biometric signal in predetermined periods of time; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with the pre-established patterns; obtain at least one biometric variable based on the identified events; analyze biometric variables according to previously known results stored in a database; and establish a neurometric indicator based on the analysis; and
  • an output module configured to classify the bill, according to the neurometric indicator.
  • the output module has display means, configured to visually represent the neurometric indicators of the banknote and a final classification metric, based on the neurometric indicators, associated with the visual information of each banknote.
  • the present invention therefore implies a series of advantages over the state of the art. It is very advantageous for the design and incorporation of security elements in the banknotes, the neuroanalysis carried out by the present invention, where unlike the studies known in the state of the art, it contemplates the integration of metrics that quantify the gestural behavior of interaction of the public with the banknote, integrates eye-tracking techniques to map fixations on the banknote, brain measurement equipment synchronized with the valuation of each banknote, integrates the heart rate variability signal as an indicator of the impact at the valence and excitation level of the banknote design and ultimately, it produces a banknote classification based on a precise objective characterization of human perception.
  • the banknote classification carried out by the method and system of the present invention follows a process that ensures their replicability and comparison between studies carried out, with the same equipment, anywhere in the world.
  • the present invention contemplates the generation of a classifier with neurobehavioral impact, which takes into account metrics from the analysis system ocular, physiological and voluntary responses, to provide indicators of design impact that help to compare different design parameters in order to determine the design and security elements that will make up a banknote.
  • FIG. 1 shows a block diagram that collects the complete methodology followed in an embodiment of the invention.
  • FIG. 2 schematically shows the process of identification and quantification of the information extracted from a biometric eye-tracking signal acquired in one of the embodiments of the invention.
  • FIG. 3 shows a block diagram that collects the classifier generation and training process used by the present invention.
  • FIG. 4 graphically associates several examples of the signals measured to each user for the calculation of different neurometric indicators. Five different indicators are concretely represented.
  • FIG. 5 shows one of the possible displays provided at the exit of a particular embodiment of the invention, where various areas of interest have been defined on the bill associated with both security elements and design elements.
  • FIG. 6 schematizes the possibilities of presenting objects for the neuro-evaluation of the present invention, preferably banknotes, both in real and virtual format, with or without context.
  • the present invention discloses a method and system for sorting banknotes, based on neuroanalysis techniques. Thus, it makes it possible to determine which design and security elements should be integrated in the manufacture of a new banknote and its optimal configuration, based on the monitoring of certain conscious and unconscious processes of the public exposed to such elements.
  • the present invention can also be applied to banknote communication material, which makes it possible to efficiently produce communication materials that emphasize the main characteristics of banknotes in information brochures, both printed and on web pages, of the issuing entities (accessible for example through the website of the Bank of Spain),
  • each of the security elements of a banknote such as reliefs, watermarks, security threads, portrait windows, holograms, colors, infrared properties, micro-texts or response to standard or special ultraviolet light
  • the application of the present invention on said communication material allows determine, in the same way that in the case of evaluating a banknote, its effectiveness in communicating to the public l
  • the design and security elements integrated in a banknote based on the monitoring of certain conscious and unconscious processes of the public exposed to such communication materials.
  • the neurodesign of banknotes according to the present invention can be applied to only one or to all the elements that are currently integrated in a banknote or communication material.
  • it is applicable to security elements, since the security of any of the elements that are implemented on a banknote to ensure its authenticity does not come solely from the technical characteristics of said elements, which prevent or hinder their imitation, It is also influenced by the level of security perceived by the public.
  • the present invention therefore, increases the effectiveness of the elements that make up the ticket and the communication materials providing an evaluation of the same based on various implicit measurements of the user, which are obtained as a result of a quantification of detected events, by comparing with certain pre-established patterns of the biometric signals of the user captured by the corresponding sensors arranged in the system.
  • the quantification of the conscious and unconscious responses is carried out using techniques from neuroscience and the measurement of behavior, which are used to infer, from the events detected in the biometric signals, various biometric variables that characterize these signals during the exposure time of a user to a visual stimulus. From these biometric variables, the existence of patterns in the unconscious responses and their correlations with the evaluation of the elements of the banknote under study is verified, obtaining neurometric indicators that classify these elements based on cognitive responses, such as visual interest or Workload.
  • the classification of the set of biometric variables into neurometric indicators is carried out using supervised learning techniques such as neural networks. Subsequently, each of these neurometrics is weighted and merged into a single final metric, based on weights defined by a group of experts, which will allow a general characterization of the design or security element or complete bill or communication material that is used. it is analyzing, thus allowing to determine if said element is suitable to be integrated into the banknote or, to be put into circulation if a complete banknote is being analyzed, or to disclose to the public if it is communication material.
  • Figure 1 shows a block diagram that collects the methodology followed in a complete embodiment of the invention.
  • a configurable neuro-evaluation module 2 with a configuration that defines the context 21 to be extracted, (context 211 may not be provided, a real context 212 provided or a virtual context 213 provided), the ticket presentation mode 22 (it may be a physical presentation mode 221 or a presentation mode virtual 222), users 23 to which the samples are to be exposed and the modes 24 of obtaining the responses (the response by human behavior 241, the physiological response 242 and the voluntary responses 243 are contemplated).
  • x ° A x l , where A e M mxn (M) is the neurometric matrix of the banknotes fl, l fl, n
  • the metrics obtained at the output of the process module depend entirely on the selected techniques and ways of obtaining user responses.
  • the following responses are contemplated:
  • facial expression analysis 2412 a front camera is available to detect gestures on the user's face, which will be subsequently analyzed by applying facial expression analysis algorithms;
  • monitoring of user behavior when faced with ticket 2413 it comprises a compilation of the interactions that the user performs with the ticket, which are obtained through a set of cameras that record their gestures. To do this, several RGB-D cameras are available which, together with specific artificial vision algorithms, allow the detection and quantification of the habitual gestures of users when interacting with the banknote.
  • - Physiological response 242 it comprises a compilation of the interactions that the user performs with the ticket, which are obtained through a set of cameras that record their gestures. To do this, several RGB-D cameras are available which, together with specific artificial vision algorithms, allow the detection and quantification of the habitual gestures of users when interacting with the banknote.
  • - Physiological response 242 it comprises a compilation of the interactions that the user performs with the ticket, which are obtained through a set of cameras that record their gestures. To do this, several RGB-D cameras are available which, together with specific artificial vision algorithms, allow the detection and quantification of the habitual gestures of users when interacting with the banknote.
  • a wireless helmet is placed on the user's head, in communication with the rest of the system, for brain measurement of electroencephalograms;
  • 2422 heart rate variability which can be measured for example by placing electrodes on the thoracic area or by means of a photoelectric sensor on the index finger;
  • skin conductance 2423 can optionally be measured by applying electrodes to the wrist, palm of the hand, or middle phalanges of the index and ring fingers to measure skin conductance.
  • biometric signals are obtained for each of the users at the input 31 of the neurometric processing module 3. Therefore, the input of the neurometric processing module groups the synchronized signals obtained for each user by the corresponding sensors, those related to human behavior, those related to its physiological response and those related to its voluntary response.
  • a conditioning process 32 may include techniques to eliminate the noises that may have been generated during the measurement process (especially relevant in physiological signals), techniques to rule out possible outliers and techniques for signal normalization if necessary.
  • Conditioning is a necessary process, except for voluntary responses, prior to extracting relevant metrics from signals.
  • Each of the signs used receives a specific conditioning such as those detailed below.
  • the conditioning comprises four sub-processes consisting mainly of face detection, feature identification, action identification, and emotion identification.
  • all the different frames that make up the video obtained are analyzed to identify the user's face by applying artificial vision techniques, such as the "Viola Jones Cascaded Classifier” algorithm.
  • a detection of the characteristics of the face is carried out using facial coding algorithms, for example the FACS system ("Facial Action Coding System"), which can identify characteristics such as vectors of the eyelids, corners of the mouth, tip of the nose, etc. This creates a mesh of points that represents the user's face.
  • the facial expression signal is finally composed of six independent signals, individually corrected with a baseline, where each one of them represents the probability that the subject is experiencing each of the basic emotions in an instant of time.
  • the conditioning is mainly concentrated in the detection of gestures of the user in the video signal, where their hands are observed and interaction with the bill, or communication material.
  • the video is segmented for each of the tickets, or communication materials, presented to each user.
  • each video segment is analyzed to detect one or several events, for example: “the user turns the ticket”, “the user touches the ticket looking for a distinctive texture”, “the user turns the ticket”, “the user looks at the ticket against the light ”,“ the user manipulates the ticket looking for a distinctive sound ”,“ the user folds the ticket ”.
  • the detection of these gestures is preferably carried out through a semi-manual process that, supported by open source libraries, such as "OpenPose", to characterize the position of the hands, their phalanges and perform an initial identification of the gestures described above, adds a manual review to confirm the correct identification of the gestures detected and processed by the algorithms.
  • open source libraries such as "OpenPose”
  • the signals and measures related to the brain response 2421 of the user are based on a signal of electroencephalogram (EEG) composed of a power signal for each of the electrodes that make up the data acquisition hardware.
  • EEG electroencephalogram
  • the data from each channel is analyzed to identify damaged channels, using the standardized fourth moment (kurtosis) of the signal from each electrode. Additionally, the channel is also considered damaged if the signal is flatter than 10% of its total duration. If a channel is considered to be damaged, it can be interpolated from its neighboring electrodes
  • the baseline of the EEG signal is removed by subtracting the mean and setting a band pass filter between 0.5 and 40 Hz. The resulting signal is then segmented into periods of one second duration.
  • ICA Independent Component Analysis
  • signal conditioning comprises analyzing an electrocardiogram (ECG) signal, for example via the Pan-Tompkins algorithm, for detection of the QRS interval. This detection allows obtaining a new time series that characterizes the electrocardiogram with the time that passes between beats. To have a good quality signal, the detection carried out by the Pan-Tompkins algorithm is reviewed to detect ectopic beats and artifacts and, finally, a series of RR beats is obtained that collect the time difference between two consecutive beats and allows the analysis to be carried out. heart rate variability.
  • ECG electrocardiogram
  • conditioning consists of a visual inspection for diagnosis and correction of artifacts that the signal may incorporate. These artifacts are corrected by first or second degree linear interpolations. Next, the phasic component of the signal is extracted to the clean signal, which is affected by unconscious changes derived from specific stimuli, and is not affected by other changes such as temperature. Finally, this signal with the phasic component is standardized using the Venables and Christie formulas to eliminate inter-subject differences.
  • the neurometric processing module 3 applies, signal by signal, algorithms for the extraction of numerical biometric variables of interest 33 in each of the conditioned signals. The individual biometric variables of each user are obtained and synchronized with the phases of the neuro-evaluation of the stimuli proposed.
  • the process follows the scheme in figure 2.
  • the basic parameters of eye tracking 70 are extracted.
  • they are extracted the main parameters of eye tracking, which are differences between fixations and saccades.
  • fixations we mean the instants in which the eye is focusing on the visual scene to convey visual information to the brain.
  • saccades is meant the displacement of the eye in order to refocus another point of visual interest.
  • each raw data of the present embodiment is classified into one of the following two states:
  • Corrections are calculated across the groups of samples defined by the fixture, as long as the duration reaches a minimum, set for example to 100 ms.
  • the position of the fixation is defined by the average position of the samples associated with that fixation.
  • the lengths of the saccades are defined by the distance between continuous fixings.
  • a division of saccades is contemplated, applicable to the vision of the bill or communication material, which divides these eye movements between environmental saccades (those that sweep the bill completely) or focal saccades (those that move around a specific area of the note of interest).
  • environmental saccades such as that sweep the bill completely
  • focal saccades such as that move around a specific area of the note of interest.
  • Said procedure applies algorithms for segmentation and identification of objects by image analysis to identify the banknote under study in space, so that the position of the banknote in the 3D coordinate system is known at all times.
  • the position of the user's eye is monitored in the same 3D coordinate system, with which a pairing of both values can be made on a 2D two-dimensional space, in which the banknote is represented as an image in both faces on which to project the fixations and saccades obtained.
  • the visual interest of the user is considered relevant in certain areas of the ticket or communication material, it must be segmented in all the areas of interest that are desired.
  • a stage of predefinition of the areas of interest of the note 72 is contemplated.
  • Each of these areas can include design elements, security elements or communication elements of the note about which it is interesting to know the perception of the users. It will only be necessary to mark with a software tool, on each of the faces, the coordinates of the vertices of the areas of interest.
  • the procedure for extracting metrics from the eye-tracking signal contemplates an extraction 73 of metrics related to the user's visual attention on the entire bill or communication material in general. These metrics will take into account one or more of the following events: “fixations on the entire bill (on both sides)”, “saccades on the bill”, “flashes of vision on the bill (measure usually provided by the team eye tracking) ”,“ pupil size (measurement usually provided by eye tracking equipment) ”.
  • the identification of events in the eye-tracking signal encourages the application of a series of mathematical operations to translate those events into quantifiable information, including, for example: counting the number of events (fixations, saccades, blinks) that happen within of the entire bill (on both sides); count the time each average event lasts; count the frequency of these events in a defined period of time; or get the sequence of these events.
  • the procedure for extracting metrics from the eye tracking signal includes an extraction 74 of metrics related to the visual attention of the user on said predefined areas of interest.
  • an additional basic parameter is previously calculated, associated with the areas of interest, which is the term “visit.”
  • visit we mean a type of event in which more than one continuous fixation occurs and that the time between fixings does not exceed a time threshold preset, for example one second.
  • the extraction of numerical biometric variables of interest 33 comprises characterizing the response of each user, to each of the banknotes displayed, from several independent identified and processed emotions. For this, the signals are segmented according to the presentation time of the stimuli, extracting several independent signals that characterize each bill.
  • the first are general metrics, computing the mean of the signal in the stimulus (eg: average probability of "joy")
  • the second are metrics based on thresholds, where each signal is applies a function that analyzes whether the probability of being in a particular emotion is higher than X, to later calculate the percentage of time that the subject has been above said threshold, where said threshold can be defined in two levels, for example 0 , 5 to detect the percentage of time that the subject has been experiencing that emotion, regardless of intensity, and 0.8 to calculate the percentage of time that the subject has been experiencing that emotion intensely
  • the third type of metrics are ratio metrics, such as the ratio between positive and negative emotions.
  • biometric variables for monitoring human behavior 2413 from the conditioned signal, the number of times that a gesture is executed while viewing a ticket is counted, and the percentage it represents compared to the total number of gestures.
  • the extraction of numerical biometric variables of interest comprises, from the signals conditioned after the conditioning process 32, a spectral analysis of the encephalogram signal to estimate the spectral power in each second, within the classical frequency band: Q (4-8 Hz), a (8-12 Hz), b (13-25 Hz), and (25-40 Hz).
  • Q 4-8 Hz
  • b 13-25 Hz
  • a-40 Hz the classical frequency band
  • it is carried out using the Welch method with 50% overlap, from which metrics that characterize the power of each of the bands are derived in each second and, from them, other metrics are derived.
  • frontal asymmetry which It can be interpreted as the amount of motivation (approach) or rejection in the face of a stimulus. It is defined as:
  • those that characterize the cognitive states are also calculated. These variables use pre-trained classifiers that, based on initial tasks that the user must perform to calibrate the classifier, allow predicting the level of “hook” and “workload.”
  • the “hook” reflects the general level of hook , commitment, attention and concentration during the visual scanning of the user's information collection, while by "workload” is understood any cognitive process that implies an executive process, such as analytical reasoning, problem solving or memory of work.
  • the extraction of numerical biometric variables of interest 33 comprises three types of variables: those derived from the time domain, those derived from the frequency domain and those that quantify non-dynamics. linear.
  • the time domain analysis includes the following characteristics: mean and standard deviation of the RR intervals, the square root of the mean of the sum of squares of the differences between the adjacent RR intervals (RMSSD), the number of successive differences of intervals that differ by more than 50 ms (pNN50), the triangular interpolation of the heart rate variability histogram (HRV) and the reference width of the RR histogram evaluated by triangular interpolation (TINN).
  • the characteristics in the frequency domain are calculated using the power spectrum density (PSD), applying the Fast Fourier Transform.
  • PSD power spectrum density
  • the analysis is performed in three bands: VLF (very low frequency, ⁇ 0.04 Hz), LF (low frequency, 0.04-0.15 Hz) and HF (high frequency, 0.12-0.4 Hz) .
  • VLF very low frequency
  • LF low frequency
  • HF high frequency, 0.12-0.4 Hz
  • the maximum value which corresponds to the frequency with the maximum magnitude
  • the power of each frequency band are calculated in absolute and percentage terms.
  • the normalized power (nu) for the LF and HF bands and the percentage of total power are calculated, previously subtracting the VLF power from the total power.
  • the LF / HF ratio is calculated to quantify sympathovagal balance and to reflect sympathetic modulations. Also, the total power is calculated.
  • a Poincaré analysis is applied, which is a visual and quantitative technique, in which the shape of a frame is classified into functional classes, providing summary information on the behavior of the heart.
  • a transverse axis (SD1) is associated with rapid beat-to-beat variability and a longitudinal axis (SD2) analyzes the long-term variability of R-R.
  • An entropy analysis is also included, using existing methods in the state of the art such as “Sample entropy” (SampEn), “Approximate entropy” (ApEn) and DFA correlations.
  • the conductivity of the skin 2423 from the clean signal that represents the phasic component of the EDA (electrodermal activity), two types of biometric variables will be generated that characterize the level of activation of the user when viewing a ticket or communication material.
  • the first type is composed of the average of the signal in the segment of each stimulus, while the second type of variable analyzes the peaks experienced by the user while viewing the bill. These peaks will be characterized by the number of peaks per minute and their average amplitude.
  • biometric variables from the user's voluntary responses 243
  • these responses are quantified with the percentage of hits and misses.
  • the average response time is calculated for each of the tasks.
  • Examples of interviews and questionnaires carried out are the following: after viewing each banknote (front and back) on the monitor by the user, questions are asked about certain semantic axes such as aesthetics, quality, design, durability, pleasure or emotional aspects, in addition to an evaluation and unconscious association of open attributes for each of the banknotes; After viewing all the tickets by the user, a questionnaire consisting of questions is completed to find out which tickets, what security elements are remembered, where on the ticket is a certain security element located or what content the communication material incorporates, and recognition questions showing banknote images that ask the user whether or not they were shown during the test; after physical interaction with each banknote By the user, a questionnaire is completed to evaluate the physical support of the banknote (paper, plastic or their variants) or of the communication material and attributes similar to the previous phase, but adding attributes related to the handling of the banknote such as geometry, texture, sound and / or relief.
  • certain semantic axes such as aesthetics, quality, design, durability, pleasure or emotional aspects, in addition to an evaluation and unconscious association of open attributes for each of the bank
  • the neurometric processing module 3 of the present invention applies a classification algorithm in a predictive module 34, to obtain at the output a set of neurometric indicators 4 of the user's neuro-evaluation.
  • Figure 3 comprises a block diagram that represents the two parts into which the calibration is divided: first, the generation of a true reference set 300 (“ground truth” in English) and second, the creation of the predictive model 310.
  • a true reference set 300 (“ground truth” in English)
  • the creation of the predictive model 310 For the generation of the true reference set, the biometric variables 33 obtained for a set of banknotes, for example one hundred banknotes, will be used.
  • the banknote set covers the widest possible range of responses on a cognitive, emotional and behavioral level.
  • This set is preferably chosen by a multidisciplinary team of experts selected from different fields / sectors (such as banking, psychology or neuroscience) and contains both real banknotes and ad-hoc designs that guarantee a great disparity of answers.
  • the group of experts selects 301 only the biometric variables related to the neurometric indicator, from the set of neurometric indicators 4, which is being generated at each moment (some examples are included below of the relationship between the selected biometric variables and the different indicators of neuroevaluation).
  • an unsupervised machine learning algorithm of the grouping type k-means
  • the hundred bills are divided into different groups according to their response to the different metrics that make up the indicators. Subsequently, the mean of each group is calculated, which represents the average response in each group. He A team of experts validates 308 the groups and analyzes in depth 303 the responses of each group based on their mean and assigns a value 304 of the indicator to this group of banknotes, for example following a Likert scale from 1 to 5.
  • the classification model 310 is created. For this, a data set is created where the inputs are the selected biometric variables 301 and the output is the value already assigned 304 to the corresponding neurometric indicator. With this data set the predictive model 306 based on artificial neural networks is designed. The training 305 of the neural network, which is fed with the selected metrics 301 and the assigned values 304, is validated 307 applying a cross-validation algorithm of k-iterations with a k of 10 and, subsequently, the model is tested with the 15% of the sample, which has been extracted prior to the validation process. Once the predictive model 306 has been validated and tested, it can be applied to the biometric variables of any banknote, giving an assessment on each of the neurometric indicators.
  • the output of the predictive module 34 comprises the indicators generated according to the predictive models obtained, which are applied to the numerical biometric variables of interest 33 and produce as a result a value for each of the indicators of the neuro-evaluation of each banknote for each user.
  • Figure 4 shows a diagram with the measured signals of each user to be taken into account for the calculation of certain indicators.
  • the human behavior responses 241 represented by the eye-tracking signals are considered relevant.
  • physiological responses 242 represented by brain response 2421 and voluntary responses in the form of task response 2431 and reaction time 2432;
  • a fourth emotional indicator 44 BEII
  • the human behavioral responses 241 represented by the facial expression analysis 2412, the physiological responses 242 represented by the heart rate variability 2422 and the skin conductance 2423 are considered relevant, and voluntary responses in the form of interviews 2433 and questionnaires 2434;
  • a fifth safety indicator 45 BSCI
  • the indicator of visual interest 41 BVIS (Banknote Visual Interest Score), is a metric related to the interest at a visual level that the banknote design arouses. This high-level metric focuses on a non-linear model that establishes a score of interest at the visual level that the perception of the banknote design generates and that allows its comparison between different types of design.
  • the indicator is calculated through supervised learning techniques applied to the biometric variables of interest 33, extracted from the selected conditioned signals, which contain quantifiable information and which in this embodiment specifically comprise:
  • some values related to the voluntary response are considered as a global assessment of the design of the evaluated banknotes; the memory of the tickets and areas of interest of the ticket; and the times allocated to carry out the banknote evaluation tasks.
  • the 42 BEI down payment indicator (Banknote Engagement Index ”), refers to the level of sustained functional attention that the person is applying to the perception of the banknote or communication material. This indicator is of great interest because it reflects whether the bill or communication material arouses enough interest to focus on it. In addition, it allows to discern if the subject is focused on the task and therefore the rest of the metrics obtained at that moment are of value.
  • the workload indicator 43 BWI Banknote Workload Index
  • the cognitive load indicator 43 BWI refers to the cognitive load or mental effort that the process entails for the subject. of perception and assessment of certain attributes of the ticket or communication material. It is very important because a high cognitive load can mean that there is an information saturation, which leads to rejection, but at the same time a low value can indicate boredom of the subject, which is also negative.
  • a cognitive indicator that combines the previous two, engagement indicator 42 BEI and workload indicator 43 BWI, is contemplated.
  • the 44 BEII emotional indicator (Banknote Emotional Induction Indetf ') used In one of the embodiments of the invention, it is a metric relative to the emotional induction capacity of the bill or communication material.
  • the BEI indicator is based on the calculation and representation of a point on a two-dimensional spatial axis from which the capacity for emotional arousal (Arousal) and the capacity to generate a positive or negative emotion (Valencia) are extracted.
  • the processing of the signal from behavioral measures for example, micro facial expressions during the viewing of the banknote
  • the physiological response asymmetry of the cerebral hemispheres, cardiac variability is used and skin conductance.
  • the security indicator BSCI (English "Banknote Security Capacity Index") used in one of the embodiments of the invention, is a metric related to the security of the banknote. Specifically, this indicator reflects the capacity of the banknote's design and security elements to be authenticated by the public. Its calculation is based on several parameters related to the behavioral signal (such as, for example, eye tracking of the security elements of the ticket, automatic monitoring of the participant's interaction gestures with the ticket) and voluntary subject response values. Through the modeling of these parameters, an absolute index can be obtained that allows the comparison of new designs and security elements in the same banknote or the comparison of current designs and security elements of different types of banknote.
  • the neurometric indicators 4 are statistically processed to satisfactorily characterize a ticket or communication materials.
  • the general response of the banknote, or communication materials is measured using data aggregation techniques (for example the arithmetic mean, or standard deviation) and, on the other hand, depending on specific conditions and cases, it is carry out different additional analyzes to determine if there are significant differences that allow to infer final conclusions regarding the objective of the neuroevaluation study.
  • correlation techniques and grouping techniques can be used. Everything This statistical analysis is implemented automatically ensuring the reproducibility and comparison of the same studies completed on various dates and in various locations. Therefore, the statistical inference analysis extracts the significant differences in the biometric variables with numerical metrics of interest 33.
  • different models such as analysis of variance or the Kruskal-Wallis test
  • the indicators calculated according to different groupings are compared. These analyzes are applied to analyze the differences in the neurometric indicators between different banknotes presented, and / or the differences with different designs of the same banknote (due to changes in the design, size or position of elements of the banknote design), which can be weighted by additional factors such as the user's gender, age, or cash handling familiarity.
  • the output module 5 calculates a final metric that encompasses all the indicators calculated and offers a snapshot of the performance of the banknote, or communication material, which allows a quick assessment , comparison and classification against other evaluated banknotes.
  • This final metric is based on a score from 1 to 10 through a mathematical equation in which each of the calculated neurometric indicators influences a given weight.
  • the model recalculates the value canceling the impact of the value of that neurometric indicator.
  • the indicator is dynamic and reflects only the indicators that are of interest in each specific case (for example, the previous final score can be recalculated so that it only reflects the impact of the visual and cognitive indicators or even only one of them) .
  • One of the embodiments contemplates the graphic representation, for example by means of heat maps, two-dimensional axes, curves or percentages, of all the biometric variables, neurometric indicators and statistical inferences obtained during the process carried out by each of the modules of the invention.
  • Figure 5 represents one of these particular views, where one side of a banknote is represented and, associated with each of the defined areas of interest, the values of the indicators (not shown in the figure) obtained for said areas of interest.
  • the represented indicators encode the neuro-evaluation obtained from the users' perception of that security element.
  • each of the areas of interest is associated with a score in percentage of the visit time, of the visitors and of the return visits, which is also complemented by a heat map and the sequence of visits of the different areas of interest. For example, after analyzing the area of interest included in hologram 52, a visit time of 14.92% of the total time invested in inspecting the ticket is obtained, 86.53% of users who have observed it and 78, 72% of users who have revisited it. These types of measures are what make it possible to build the indicators for the comparison between banknotes, comparison of elements and classification.
  • the present invention classifies in the output module 5 a complete sample of banknotes according to the indicators obtained associated with the areas of interest that include security elements.
  • the level of security of the security elements is determined by the perception of the public and is a determining factor in assessing their incorporation into future legal tender bills.
  • the classification of the banknotes based on the perception of the users of the security elements, allows selecting the security elements between acceptable and not acceptable to be incorporated in legal tender, establishing a minimum threshold in the indicators to determine that the Public perception of the security element is sufficient to be incorporated into the ticket. These minimum thresholds can be calibrated using modified security elements and analyzing how the perception of the users varies with the modifications of different security elements.
  • the modified security elements that obtain a better classification in the perception of users will be the most appropriate security elements to be incorporated into legal tender banknotes.
  • the eye-tracking signals the number of return visits of the user to the security element or the time spent viewing said element with respect to the rest of the ticket is decisive.
  • the neuroanalysis of users 'perception will make it possible to determine whether color variations have an influence on the perception of security elements, characterize the different banknotes based on users' perception and finally classify them in an objective way, being the banknote best classified the one corresponding to the most appropriate color for the security of the note.
  • a gray color for the bill could greatly nullify the security of a hologram-like element or a metallic-looking security thread element, which would be practically camouflaged and would go unnoticed by a user. That is, according to the approach of the example, the classification will indicate how each of the test colors disturbs the perception of the security elements integrated in the banknote, with which the final classification determines the color to be included in the banknote to be manufactured .
  • banknote samples and the areas of interest are selected so that it is precisely those parameters that vary from one banknote to another and, in a manner analogous to the previous case, the characterization of the perception of the users indicates in an objective way the influence that said parameters have on the ticket. For example, defining an area of interest 56 that collects the value of the banknote (50 euros for example), it is interesting to compare the influence that different sizes and positions have on the perception of the design and security elements of the banknote.
  • the watermark 53 may see its perceived security affected from a certain size of the representation of the banknote value, or a position that is too close, since it attracts the visual attention of the user in excess and would cancel or reduce the perception of the watermark, which reduces the security of the ticket to the user.
  • Even other elements of the banknote that apparently have no more than a purely aesthetic function, such as the decoration collected by the area of interest 57, are also important in the overall valuation of the banknote and their color, size or position can influence the security of the banknote. itself, so that in one of the embodiments the analysis of absolutely all the banknote elements is contemplated.
  • other comparative results are contemplated that can be graphically displayed.
  • Figure 6 schematizes the possibilities of presenting objects for the neuro-evaluation of the present invention, preferably banknotes or communication materials, both in real and virtual format.
  • the samples of banknotes or communication materials to be analyzed include different security characteristics, design or content of the communication materials according, among others, to different materials, designs, sizes and positions, which influence the perception that the public has of the ticket.
  • the context of the banknote samples can be presented to the user using different techniques 21, which include not providing any context 211, adding a real context 212 or adding a virtualized context 213 in which different digital and computer graphics techniques are reproduced scenarios, among which are contemplated: a virtual reality scenario, where the evaluation configuration is used in laboratory conditions under a virtual replica of the real world, which can consist of two-dimensional (2D) models of the real context; an augmented reality scenario, where the assessment settings are used in real life conditions, but supplemented with some virtual 3D elements; and an augmented virtuality scenario, where the assessment configuration is used under laboratory conditions, but an augmented virtual replica of the real context is presented to the user.
  • a virtual reality scenario where the evaluation configuration is used in laboratory conditions under a virtual replica of the real world, which can consist of two-dimensional (2D) models of the real context
  • an augmented reality scenario where the assessment settings are used in real life conditions, but supplemented with some virtual 3D elements
  • an augmented virtuality scenario where the assessment configuration is used under laboratory conditions, but an
  • the context can be provided through a single or a combination of the following immersive interfaces: visual devices (such as conventional monitors, upright monitors with stereoscopic 3D vision and 3D tracking of the position of the main user (interface "fish tank"), monitor in horizontal position with stereoscopic 3D vision and 3D tracking of the position of the main user (or interface "bank of work "), surround screens composed of large projection-based screens and / or large monitors, hemispheric displays, or virtual reality helmets (HMD-Head Mounted Displays) and / or augmented reality and / or mixed reality); screens auditory (where for example contextual sounds are reproduced using 3D sound generation techniques with headphones and / or external speakers); olfactory screens (where aromas are delivered through electronic noses and / or any commercial olfactory screen); or screens haptic (where tactile and kinesthetic cues are provided through a haptic display touch device, such as earth landmarks,
  • the present invention also contemplates several alternatives shown in figure 6. Mainly two techniques are used depending on their fidelity capacity to reproduce real life situations: using a physical ticket 221, where a real physical model of the ticket is presented to the user; or use a digital ticket 222, where a digital replica of the ticket is presented using either a virtual ticket model that reproduces, in two or 3 dimensions, a digital image of the real ticket, or in a virtual ticket model based on a tangible interface that the user can manipulate with their hands.
  • This tangible interface can render graphic elements on physical paper in three dimensions using spatial augmented reality techniques.
  • the final result of the overlay techniques can be presented to the user by means of a virtual reality headset or alternatively, this type of device can be dispensed with and opt for digital projectors that display the information directly on the physical ticket.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)

Abstract

The present invention relates to a system and a method for classifying banknotes based on neuroanalysis, which comprises: providing a user with visual banknote information; acquiring biometric signals from the user by means of sensors of an input module; segmenting, in a processing module, the biometric signals acquired in predetermined time periods; identifying certain events as a result of comparing each of the segments with predetermined patterns; obtaining at least one biometric variable based on the identified events; analysing the biometric variables, in accordance with known results previously stored in a database; establishing a neurometric indicator as a function of the preceding analysis; and classifying, in an output module, the banknote in accordance with the established neurometric indicators.

Description

MÉTODO Y SISTEMA DE CLASIFICACION DE BILLETES BASADO EN BANKNOTE CLASSIFICATION METHOD AND SYSTEM BASED ON
NEUROANÁLISIS NEUROANALYSIS
DESCRIPCIÓN DESCRIPTION
OBJETO DE LA INVENCIÓN OBJECT OF THE INVENTION
La presente invención se refiere al campo técnico del neuroanálisis de objetos a través del procesamiento de señales biométricas de los usuarios expuestos a dichos objetos y, más concretamente, a la caracterización de billetes y material de comunicación de los mismos en función de información cuantificable extraída de las señales biométricas, lo que permite clasificar los billetes y material de comunicación de los mismos según una percepción objetiva de los usuarios de ciertos parámetros sobre el diseño y los elementos de seguridad. The present invention relates to the technical field of neuroanalysis of objects through the processing of biometric signals of users exposed to said objects and, more specifically, to the characterization of banknotes and communication material thereof based on quantifiable information extracted from biometric signals, which makes it possible to classify banknotes and their communication material according to an objective perception of users of certain parameters on the design and security elements.
ANTECEDENTES DE LA INVENCIÓN BACKGROUND OF THE INVENTION
Actualmente, se garantiza la integridad de cualquier billete utilizado como medio de pago mediante la combinación de diseños y medidas de seguridad en continuo desarrollo, comunicando dichas características a través de materiales de comunicación (campañas de comunicación, folletos, material formativo, etc.). Currently, the integrity of any banknote used as a means of payment is guaranteed by combining designs and security measures in continuous development, communicating these characteristics through communication materials (communication campaigns, brochures, training material, etc.).
Además, la creación de dichos billetes debe responder a criterios estéticos y funcionales que permitan su fácil reconocimiento, detectar su autenticidad o simplificar su manejo cumpliendo a la vez con una multitud de requisitos técnicos tanto del público como de fabricantes y organismos emisores. Dado que el billete es un medio de comunicación en sí mismo con el que se pretende comunicar el mensaje expresado en su diseño, entre los requisitos del público se debería tener en cuenta los procesos intelectuales y emocionales del público sobre cómo perciben dichos aspectos estéticos y funcionales para asegurar que el mensaje integrado en el diseño de los billetes es recibido por el público de manera fiel al propósito de comunicación del diseño. In addition, the creation of said banknotes must respond to aesthetic and functional criteria that allow their easy recognition, detect their authenticity or simplify their handling while complying with a multitude of technical requirements both from the public and from manufacturers and issuing bodies. Given that the banknote is a means of communication in itself with which it is intended to communicate the message expressed in its design, the public's requirements should take into account the public's intellectual and emotional processes on how they perceive these aesthetic and functional aspects. to ensure that the message embedded in the banknote design is received by the public in a manner true to the communication purpose of the design.
Asimismo, también los materiales de comunicación deben ser elaborados atendiendo a los procesos intelectuales y emocionales del público con el objetivo de que generen el mayor impacto comunicativo posible en el mismo, para así maximizar la garantía de que el público ha recibido el mensaje formativo y, además, lo ha entendido como se esperaba que lo hiciera. Para ello, tan importante es evaluar los contenidos incorporados en los materiales de comunicación, como los materiales en sí (folletos, imágenes, videos, anuncios, etc.), como la distribución de dichos materiales en los diferentes canales de comunicación (web, radio, TV, prensa escrita, etc.),. Likewise, the communication materials must also be prepared taking into account the intellectual and emotional processes of the public in order to generate the greatest possible communicative impact on it, in order to maximize the guarantee that the public has received the training message and, moreover, he has understood it as he was expected to. For this, it is so important to evaluate the content incorporated in the Communication materials, such as the materials themselves (brochures, images, videos, advertisements, etc.), such as the distribution of said materials in the different communication channels (web, radio, TV, written press, etc.).
Tradicionalmente, la evaluación de la percepción humana de dichos aspectos del billete y materiales de comunicación de los mismos se justifica en las teorías de toma de decisión que asumen que podemos verbalizar intencionada y exactamente nuestras actitudes, emociones y conductas. Por tanto, tales teorías se basan en respuestas explícitas obtenidas a través de cuestionarios y entrevistas. Sin embargo, se ha demostrado que tales medidas explícitas pueden estar condicionadas por los "efectos de deseabilidad social", que pueden conducir a relatos falsos de conductas, actitudes y creencias. Además, siempre puede haber diferentes interpretaciones, lo que da lugar a resultados con una menor fiabilidad y menor validez. Por otro lado, algunas preguntas que recurren a la autoevaluación de un usuario requieren que las personas tengan un conocimiento abierto de sus disposiciones y esto no siempre ocurre. Traditionally, the evaluation of human perception of such aspects of the ticket and communication materials thereof is justified in decision-making theories that assume that we can intentionally and accurately verbalize our attitudes, emotions and behaviors. Therefore, such theories are based on explicit responses obtained through questionnaires and interviews. However, it has been shown that such explicit measures can be conditioned by "social desirability effects", which can lead to false accounts of behaviors, attitudes and beliefs. In addition, there may always be different interpretations, leading to results with less reliability and less validity. On the other hand, some questions that resort to a user's self-assessment require that people have an open knowledge of its provisions and this does not always happen.
Por el contrario, estudios recientes demuestran la considerable influencia de los procesos implícitos en las construcciones psicológicas y mecanismos neurocognitivos de especial relevancia para los humanos, como las actitudes, los estereotipos, la confianza en sí mismo, relaciones personales, toma de decisiones, o apego personal. On the contrary, recent studies demonstrate the considerable influence of implicit processes in psychological constructions and neurocognitive mechanisms of special relevance for humans, such as attitudes, stereotypes, self-confidence, personal relationships, decision-making, or attachment. personal.
Las medidas implícitas se refieren a los métodos y técnicas capaces de capturar o rastrear procesos mentales implícitos o sus resultados, incluyendo imágenes cerebrales, monitoreo del comportamiento y resultados psicosomáticos. La neurociencia ha demostrado que en la mayoría de los procesos cerebrales que regulan nuestras emociones, actitudes, comportamientos y decisiones no interviene nuestra conciencia. Es decir, estos procesos implícitos son funciones cerebrales que ocurren automáticamente y sin control consciente ni conciencia, lo que contrasta con los procesos explícitos que ocurren a través de un control consciente ejecutivo. Implicit measures refer to methods and techniques capable of capturing or tracking implicit mental processes or their results, including brain imaging, behavioral monitoring, and psychosomatic outcomes. Neuroscience has shown that in most of the brain processes that regulate our emotions, attitudes, behaviors and decisions, our conscience does not intervene. That is, these implicit processes are brain functions that occur automatically and without conscious control or awareness, which is in contrast to explicit processes that occur through conscious executive control.
La neurociencia y, más específicamente, las técnicas de medición basadas en la respuesta biométrica de seres humanos, han mejorado mucho en los últimos años permitiendo ser utilizadas en estudios de valoración de productos, contenidos digitales e incluso en espacios reales. Evidentemente, la aportación de las medidas implícitas no invalida totalmente los resultados y construcciones modeladas a partir de procesos explícitos sino que la complementa, puesto que cualquier actividad de investigación sobre decisiones humanas basada en datos que provienen única y exclusivamente de las medidas de proceso explícitas, resulta incompleta y, en ocasiones inexacta. Neuroscience and, more specifically, measurement techniques based on the biometric response of human beings, have improved greatly in recent years, allowing them to be used in product valuation studies, digital content and even in real spaces. Obviously, the contribution of the implicit measures does not totally invalidate the results and constructions modeled from processes rather, it complements it, since any research activity on human decisions based on data that comes solely and exclusively from explicit process measures, is incomplete and sometimes inaccurate.
De acuerdo con todo lo anterior, disponer por parte de diseñadores, bancos centrales y entidades emisoras de una metodología basada en medidas implícitas y explícitas de la percepción del público de los billetes y material de comunicación de los mismos, sería altamente beneficiosa para diseñar familias de billetes y material de comunicación eficientes. Entendida esta eficiencia como la combinación en el billete de un diseño y elementos de seguridad eficaces que capten la atención del público, comuniquen adecuadamente el mensaje integrado en su diseño y faciliten el reconocimiento del billete, aumentando, por consiguiente, su seguridad; y la elaboración de material de comunicación de billetes capaz de generar el mayor impacto comunicativo posible de tal forma que maximice la comunicación al público del reconocimiento del billete, su diseño y medidas de seguridad. In accordance with all of the above, having a methodology based on implicit and explicit measurements of the public's perception of banknotes and their communication material on the part of designers, central banks and issuing entities, would be highly beneficial to design families of banknotes. efficient tickets and communication material. Understanding this efficiency as the combination in the banknote of a design and effective security elements that capture the public's attention, adequately communicate the message integrated into its design and facilitate the recognition of the banknote, thus increasing its security; and the development of banknote communication material capable of generating the greatest possible communicative impact in such a way as to maximize communication to the public of the recognition of the banknote, its design and security measures.
DESCRIPCIÓN DE LA INVENCIÓN DESCRIPTION OF THE INVENTION
Con el fin de alcanzar los objetivos y evitar los inconvenientes mencionados anteriormente, la presente invención describe, en un primer aspecto, un método para clasificar billetes, basado en neuroanálisis, que comprende los pasos de: proporcionar a un usuario una información visual de un billete; adquirir, mediante un sensor de un módulo de entrada al menos una señal biométrica del usuario, como respuesta a la información visual del billete; segmentar, en un módulo de proceso, las señales biométricas adquiridas en períodos de tiempo predeterminados; comparar cada uno de los segmentos con unos patrones preestablecidos; identificar ciertos eventos como resultado de la comparación de cada uno de los segmentos con los patrones preestablecidos; obtener al menos una variable biométrica basada en los eventos identificados; analizar, en el módulo de proceso, las variables biométricas, de acuerdo a resultados conocidos previamente almacenados en una base datos; establecer, en el módulo de proceso, un indicador neurométrico en función del análisis anterior; y clasificar, en un módulo de salida, el billete de acuerdo al indicador neurométrico establecido. In order to achieve the objectives and avoid the aforementioned drawbacks, the present invention describes, in a first aspect, a method for classifying banknotes, based on neuroanalysis, comprising the steps of: providing a user with visual information on a banknote ; acquiring, by means of a sensor of an input module at least one biometric signal from the user, in response to the visual information of the ticket; segmenting, in a processing module, the biometric signals acquired in predetermined periods of time; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with the pre-established patterns; obtain at least one biometric variable based on the identified events; analyze, in the process module, the biometric variables, according to previously known results stored in a database; establish, in the process module, a neurometric indicator based on the previous analysis; and classifying, in an output module, the bill according to the established neurometric indicator.
De acuerdo a una de las realizaciones de la invención, la información visual del billete se proporciona de forma física, de forma virtual o mediante una combinación de las dos en una interfaz tangible sobre la que se representan elementos virtuales añadidos a un billete físico mediante tecnología de realidad aumentada. According to one of the embodiments of the invention, the visual information of the banknote is provided physically, virtually or through a combination of the two in a tangible interface on which virtual elements added to a physical ticket using augmented reality technology.
La señal biométrica, según una realización particular de la invención, comprende información de al menos un proceso implícito del usuario, a seleccionar entre: análisis de gestos en la interacción del billete con las manos, seguimiento ocular y análisis de expresión facial. The biometric signal, according to a particular embodiment of the invention, comprises information from at least one implicit process of the user, to be selected from: analysis of gestures in the interaction of the ticket with the hands, eye tracking and analysis of facial expression.
La señal biométrica, según una realización particular de la invención, comprende información de una respuesta fisiológica del usuario a seleccionar entre: una respuesta cerebral, una variación del ritmo cardíaco y la conductancia de la piel. The biometric signal, according to a particular embodiment of the invention, comprises information on a physiological response of the user to be selected from: a cerebral response, a variation of the heart rate and the conductance of the skin.
La presente invención contempla la posibilidad de obtener una variable biométrica del seguimiento ocular del usuario, donde los eventos identificados resultan de la comparación de la señal de seguimiento ocular con un patrón que establece un primer umbral de velocidad de movimiento del ojo del usuario que determina la presencia de un evento de fijación o un evento de movimiento sacádico. Adicionalmente, se contempla la posibilidad de, una vez detectado un movimiento sacádico, determinar si corresponde a un movimiento sacádico ambiental o un movimiento sacádico focal, de acuerdo a un segundo umbral preestablecido de desviación angular del ojo del usuario durante dicho evento. The present invention contemplates the possibility of obtaining a biometric variable of the user's eye tracking, where the identified events result from the comparison of the eye tracking signal with a pattern that establishes a first threshold of movement speed of the user's eye that determines the presence of a fixation event or a saccadic event. Additionally, the possibility of, once a saccadic movement has been detected, is contemplated, determining whether it corresponds to an environmental saccadic movement or a focal saccadic movement, according to a second pre-established threshold of angular deviation of the user's eye during said event.
Las variables biométricas obtenidas por la presente invención, basadas en los eventos identificados, se contempla que comprendan una información cuantificable de dichos eventos identificados, a seleccionar entre: cantidad de eventos identificados, duración promedio de los eventos identificados, frecuencia de cada evento identificado en un tiempo preestablecido, secuencia de los eventos identificados y número de visitas a una misma área predefinida. The biometric variables obtained by the present invention, based on the identified events, are contemplated to comprise quantifiable information on said identified events, to be selected from: number of identified events, average duration of identified events, frequency of each identified event in a preset time, sequence of events identified and number of visits to the same predefined area.
Adicionalmente, en una de las realizaciones de la invención, se contempla definir al menos un área de interés en el billete y asociar la variable biométrica adquirida del usuario a dicho área de interés. Particularmente, en una de las realizaciones de la presente invención donde la información visual comprende un elemento de seguridad dispuesto en el billete, se contempla que el área de interés sea mayor o igual que el área del billete ocupada por el elemento de seguridad y donde el área de interés incluye el área del billete ocupada por dicho elemento de seguridad. Así, ventajosamente es posible evaluar cada uno de los elementos del billete por separado. Additionally, in one of the embodiments of the invention, it is contemplated to define at least one area of interest in the bill and to associate the biometric variable acquired from the user to said area of interest. Particularly, in one of the embodiments of the present invention where the visual information comprises a security element arranged on the bill, it is contemplated that the area of interest is greater than or equal to the area of the bill occupied by the security element and where the area of interest includes the area of the bill occupied by said security element. Thus, it is advantageously possible evaluate each of the elements of the bill separately.
Según una realización de la presente invención, analizar las variables biométricas de acuerdo a resultados conocidos previamente, comprende entrenar un sistema de aprendizaje supervisado del módulo de proceso de acuerdo a los siguientes pasos: According to an embodiment of the present invention, analyzing the biometric variables according to previously known results, comprises training a supervised learning system of the process module according to the following steps:
- repetir los pasos de: proporcionar a un usuario una información visual de un billete; adquirir, mediante un sensor de un módulo de entrada al menos una señal biométrica del usuario, como respuesta a la información visual del billete; y segmentar, en un módulo de proceso, las señales biométricas adquiridas en períodos de tiempo predeterminados; para una pluralidad de billetes diferentes y usuarios diferentes; - repeating the steps of: providing a user with visual information on a ticket; acquiring, by means of a sensor of an input module at least one biometric signal from the user, in response to the visual information of the ticket; and segmenting, in a processing module, the biometric signals acquired in predetermined periods of time; for a plurality of different notes and different users;
- agrupar, para cada billete, los eventos identificados de cada usuario, de acuerdo a un número previamente establecido de grupos; - grouping, for each ticket, the identified events of each user, according to a previously established number of groups;
- asignar a cada billete un valor inicial del indicador neurométrico, donde dicho valor está basado en un análisis de los grupos de eventos identificados por un usuario experto. - assigning to each ticket an initial value of the neurometric indicator, where said value is based on an analysis of the groups of events identified by an expert user.
Adicionalmente, se contempla la posibilidad de analizar las variables biométricas mediante el módulo de aprendizaje supervisado del módulo de proceso, siguiendo los pasos de: proporcionar el valor inicial del indicador neurométrico, asignado a cada billete, en una entrada del sistema de aprendizaje; aplicar un modelo predictivo, por el sistema de aprendizaje supervisado, sobre las variables biométricas obtenidas por el módulo de proceso y el valor inicial asignado; y validar, mediante un proceso de validación cruzada, con un número de iteraciones determinado previamente, el modelo predictivo. Additionally, the possibility of analyzing the biometric variables through the supervised learning module of the process module is contemplated, following the steps of: providing the initial value of the neurometric indicator, assigned to each ticket, in an input of the learning system; apply a predictive model, by the supervised learning system, on the biometric variables obtained by the process module and the assigned initial value; and validate, through a cross-validation process, with a previously determined number of iterations, the predictive model.
Las métricas parciales de la presente invención, definidos en el presente documento como indicadores neurométricos, representan uno o más de los siguientes procesos cognitivos cerebrales del usuario: interés visual, atención, emociones evocadas, motivación, carga mental, estrés y nivel de excitación. The partial metrics of the present invention, defined herein as neurometric indicators, represent one or more of the following user's brain cognitive processes: visual interest, attention, evoked emotions, motivation, mental load, stress, and arousal level.
Opcionalmente, se contempla en una de las realizaciones de la invención que el usuario sea provisto de información táctil y sonora del billete. Optionally, it is contemplated in one of the embodiments of the invention that the user is provided with tactile and audible information about the bill.
Un segundo aspecto de la invención se refiere a un sistema para clasificar billetes, basado en neuroanálisis, que comprende los siguientes elementos: - un módulo de entrada que comprende al menos un sensor, configurado para adquirir una señal biométrica del usuario, como respuesta a una información visual del billete proporcionada a dicho usuario; A second aspect of the invention refers to a system for classifying banknotes, based on neuroanalysis, comprising the following elements: - an input module comprising at least one sensor, configured to acquire a biometric signal from the user, in response to visual information of the ticket provided to said user;
- un módulo de proceso, configurado para segmentar la señal biométrica en períodos de tiempo predeterminados; comparar cada uno de los segmentos con unos patrones preestablecidos; identificar ciertos eventos como resultado de la comparación de cada uno de los segmentos con los patrones preestablecidos; obtener al menos una variable biométrica basada en los eventos identificados; analizar las variables biométricas de acuerdo a resultados conocidos previamente almacenados en una base datos; y establecer un indicador neurométrico en función del análisis; y - a processing module, configured to segment the biometric signal in predetermined periods of time; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with the pre-established patterns; obtain at least one biometric variable based on the identified events; analyze biometric variables according to previously known results stored in a database; and establish a neurometric indicator based on the analysis; and
- un módulo de salida configurado para clasificar el billete, de acuerdo al indicador neurométrico. - an output module configured to classify the bill, according to the neurometric indicator.
Opcionalmente, en una de las realizaciones, el módulo de salida cuenta con unos medios de visualización, configurados para representar visualmente los indicadores neurométricos del billete y una métrica final de clasificación, basada en los indicadores neurométricos, asociada con la información visual de cada billete. Optionally, in one of the embodiments, the output module has display means, configured to visually represent the neurometric indicators of the banknote and a final classification metric, based on the neurometric indicators, associated with the visual information of each banknote.
La presente invención implica, por tanto, una serie de ventajas sobre el estado del arte. Resulta muy ventajoso para el diseño e incorporación de elementos de seguridad en los billetes, el neuroanálisis llevado a cabo por la presente invención, donde a diferencia de los estudios conocidos en el estado del arte, contempla la integración de métricas que cuantifican el comportamiento gestual de interacción del público con el billete, integra técnicas de seguimiento ocular para mapear fijaciones sobre el billete, equipos de medida cerebral sincronizados con la valoración de cada billete, integra la señal de variabilidad de ritmo cardíaco como indicador del impacto a nivel de valencia y excitación del diseño del billete y en definitiva, produce una clasificación de los billetes en función de una precisa caracterización objetiva de la percepción humana. La clasificación de billetes realizada por el método y el sistema de la presente invención sigue un proceso que asegura su replicabilidad y comparación entre estudios realizados, con el mismo equipamiento, en cualquier lugar del mundo. The present invention therefore implies a series of advantages over the state of the art. It is very advantageous for the design and incorporation of security elements in the banknotes, the neuroanalysis carried out by the present invention, where unlike the studies known in the state of the art, it contemplates the integration of metrics that quantify the gestural behavior of interaction of the public with the banknote, integrates eye-tracking techniques to map fixations on the banknote, brain measurement equipment synchronized with the valuation of each banknote, integrates the heart rate variability signal as an indicator of the impact at the valence and excitation level of the banknote design and ultimately, it produces a banknote classification based on a precise objective characterization of human perception. The banknote classification carried out by the method and system of the present invention follows a process that ensures their replicability and comparison between studies carried out, with the same equipment, anywhere in the world.
La presente invención contempla la generación de un clasificador con impacto neurocomportamental, que tiene en cuenta métricas provenientes del sistema de análisis ocular, fisiológicas y respuestas voluntarias, para aportar indicadores de impacto del diseño que ayudan a la comparación de diferentes parámetros de diseño con el fin de determinar el diseño y los elementos de seguridad que conformarán un billete. The present invention contemplates the generation of a classifier with neurobehavioral impact, which takes into account metrics from the analysis system ocular, physiological and voluntary responses, to provide indicators of design impact that help to compare different design parameters in order to determine the design and security elements that will make up a banknote.
BREVE DESCRIPCIÓN DE LAS FIGURAS BRIEF DESCRIPTION OF THE FIGURES
Para completar la descripción de la invención y con objeto de ayudar a una mejor comprensión de sus características, de acuerdo con un ejemplo preferente de realización de la misma, se acompaña un conjunto de dibujos en donde, con carácter ilustrativo y no limitativo, se han representado las siguientes figuras: To complete the description of the invention and in order to help a better understanding of its characteristics, according to a preferred example of its embodiment, a set of drawings is attached in which, with an illustrative and non-limiting nature, they have been represented the following figures:
- La figura 1 muestra un diagrama de bloques que recoge la metodología completa seguida en una realización de la invención. - Figure 1 shows a block diagram that collects the complete methodology followed in an embodiment of the invention.
- La figura 2 muestra esquemáticamente el proceso de identificación y cuantificación de la información extraída de una señal biométrica de seguimiento ocular adquirida en una de las realizaciones de la invención. - Figure 2 schematically shows the process of identification and quantification of the information extracted from a biometric eye-tracking signal acquired in one of the embodiments of the invention.
- La figura 3 muestra un diagrama de bloques que recoge el proceso de generación y entrenamiento del clasificador utilizado por la presente invención. - Figure 3 shows a block diagram that collects the classifier generation and training process used by the present invention.
- La figura 4 asocia gráficamente varios ejemplos de las señales medidas a cada usuario para el cálculo de diferentes indicadores neurométricos. Se representan concretamente cinco indicadores diferentes. - Figure 4 graphically associates several examples of the signals measured to each user for the calculation of different neurometric indicators. Five different indicators are concretely represented.
- La figura 5 muestra una de las posibles visualizaciones proporcionadas a la salida de una realización particular de la invención, donde se han definido varias áreas de interés sobre el billete asociadas tanto a elementos de seguridad como a elementos de diseño. - Figure 5 shows one of the possible displays provided at the exit of a particular embodiment of the invention, where various areas of interest have been defined on the bill associated with both security elements and design elements.
- La figura 6 esquematiza las posibilidades de presentación de objetos para la neuroevaluación de la presente invención, preferiblemente billetes de banco, tanto en formato real como virtual, con contexto o sin contexto. - Figure 6 schematizes the possibilities of presenting objects for the neuro-evaluation of the present invention, preferably banknotes, both in real and virtual format, with or without context.
DESCRIPCIÓN DETALLADA DE LA INVENCIÓN DETAILED DESCRIPTION OF THE INVENTION
La presente invención divulga un método y un sistema para clasificar billetes de banco, basado en técnicas de neuroanálisis. Así, permite determinar qué elementos de diseño y seguridad deben ser integrados en la fabricación de un nuevo billete de banco y su configuración óptima, en función de la monitorización de ciertos procesos conscientes e inconscientes del público expuesto a tales elementos. The present invention discloses a method and system for sorting banknotes, based on neuroanalysis techniques. Thus, it makes it possible to determine which design and security elements should be integrated in the manufacture of a new banknote and its optimal configuration, based on the monitoring of certain conscious and unconscious processes of the public exposed to such elements.
De forma análoga, la presente invención puede aplicarse también al material de comunicación de billetes, lo que permite elaborar de manera eficiente los materiales de comunicación que enfatizan las principales características de los billetes en los folletos informativos, tanto impresos como en páginas web, de las entidades emisoras (accesibles por ejemplo a través de la página web del Banco de España), En estos folletos, cada uno de los elementos de seguridad de un billete (como por ejemplo relieves, marcas de agua, hilos de seguridad, ventanas con retrato, hologramas, colores, propiedades infrarrojas, microtextos o respuesta a la luz ultravioleta estándar o especial) es identificado y resaltado, tanto visualmente como mediante textos explicativos que indican al usuario cómo reconocerlo, por tanto la aplicación de la presente invención sobre dicho material de comunicación permite determinar, de forma análoga que en el caso de evaluar un billete, su efectividad de comunicar al público los elementos de diseño y seguridad integrados en un billete, en función de la monitorización de ciertos procesos conscientes e inconscientes del público expuesto a tales materiales de comunicación. Similarly, the present invention can also be applied to banknote communication material, which makes it possible to efficiently produce communication materials that emphasize the main characteristics of banknotes in information brochures, both printed and on web pages, of the issuing entities (accessible for example through the website of the Bank of Spain), In these brochures, each of the security elements of a banknote (such as reliefs, watermarks, security threads, portrait windows, holograms, colors, infrared properties, micro-texts or response to standard or special ultraviolet light) is identified and highlighted, both visually and through explanatory texts that indicate to the user how to recognize it, therefore the application of the present invention on said communication material allows determine, in the same way that in the case of evaluating a banknote, its effectiveness in communicating to the public l The design and security elements integrated in a banknote, based on the monitoring of certain conscious and unconscious processes of the public exposed to such communication materials.
El neurodiseño de billetes de acuerdo a la presente invención, puede aplicarse a uno sólo o a todos los elementos que se integran actualmente en un billete o material de comunicación. Preferiblemente, es de aplicación sobre los elementos de seguridad, ya que la seguridad de cualquiera de los elementos que se implementan sobre un billete para asegurar su autenticidad, no proviene únicamente de las características técnicas propias de dichos elementos, que impiden o dificultan su imitación, sino que también influye el nivel de seguridad que percibe el público. The neurodesign of banknotes according to the present invention can be applied to only one or to all the elements that are currently integrated in a banknote or communication material. Preferably, it is applicable to security elements, since the security of any of the elements that are implemented on a banknote to ensure its authenticity does not come solely from the technical characteristics of said elements, which prevent or hinder their imitation, It is also influenced by the level of security perceived by the public.
Por tanto, la percepción del público de un elemento de seguridad es fundamental para mejorar su eficacia porque si un elemento de seguridad, como por ejemplo una lámina holográfica, aun en el hipotético caso de que fuera imposible su imitación, se integrara en un billete de manera que pasara totalmente desapercibida para el usuario, la efectividad de dicho elemento en la integridad global del billete sería nula. Therefore, the public's perception of a security element is essential to improve its effectiveness because if a security element, such as a holographic foil, even in the hypothetical case that it is impossible to imitate, is integrated into a banknote. In such a way that it would go completely unnoticed by the user, the effectiveness of said element on the overall integrity of the bill would be null.
La presente invención, por tanto, aumenta la eficacia de los elementos que componen el billete y los materiales de comunicación proporcionando una evaluación de los mismos basada en varias medidas implícitas del usuario, las cuales son obtenidas como resultado de una cuantificación de eventos detectados, mediante la comparación con ciertos patrones preestablecidos de las señales biométricas del usuario captadas por los correspondientes sensores dispuestos en el sistema. La cuantificación de las respuestas conscientes e inconscientes se realiza mediante técnicas provenientes de la neurociencia y la medida del comportamiento, que son utilizadas para inferir, de los eventos detectados en las señales biométricas, diversas variables biométricas que caracterizan dichas señales durante el tiempo de exposición de un usuario a un estímulo visual. A partir de estas variables biométricas, se comprueba la existencia de patrones en las respuestas inconscientes y sus correlaciones con la evaluación de los elementos del billete bajo estudio, obteniendo indicadores neurométricos que clasifican estos elementos en función de respuestas cognitivas, como el interés visual o la carga de trabajo. The present invention, therefore, increases the effectiveness of the elements that make up the ticket and the communication materials providing an evaluation of the same based on various implicit measurements of the user, which are obtained as a result of a quantification of detected events, by comparing with certain pre-established patterns of the biometric signals of the user captured by the corresponding sensors arranged in the system. The quantification of the conscious and unconscious responses is carried out using techniques from neuroscience and the measurement of behavior, which are used to infer, from the events detected in the biometric signals, various biometric variables that characterize these signals during the exposure time of a user to a visual stimulus. From these biometric variables, the existence of patterns in the unconscious responses and their correlations with the evaluation of the elements of the banknote under study is verified, obtaining neurometric indicators that classify these elements based on cognitive responses, such as visual interest or Workload.
La clasificación del conjunto de variables biométricas en indicadores neurométricos, se realiza mediante técnicas de aprendizaje supervisado como redes neuronales. Posteriormente, cada una de estas neurométricas es ponderada y fusionada en una única métrica final, en función de unos pesos definidos por un grupo de expertos, que permitirá caracterizar a nivel general el elemento de diseño o seguridad o billete completo o material de comunicación que se está analizando, permitiendo así determinar si dicho elemento es apto para ser integrado en el billete o, ser puesto en circulación en caso de estar analizando un billete completo, o divulgar al público si se trata de material de comunicación. The classification of the set of biometric variables into neurometric indicators is carried out using supervised learning techniques such as neural networks. Subsequently, each of these neurometrics is weighted and merged into a single final metric, based on weights defined by a group of experts, which will allow a general characterization of the design or security element or complete bill or communication material that is used. it is analyzing, thus allowing to determine if said element is suitable to be integrated into the banknote or, to be put into circulation if a complete banknote is being analyzed, or to disclose to the public if it is communication material.
La figura 1 muestra un diagrama de bloques que recoge la metodología seguida en una realización completa de la invención. De acuerdo a dicha figura 1 , la presente invención contempla una entrada 1 que puede comprender uno o varios tipos de señales de entrada xl = [x^ x^, ··· , xn l ], como por ejemplo muestras reales de billetes 11 , muestras de billetes reales con elementos de seguridad alterados 12, muestras de prueba de billetes que no están en circulación 13 o materiales de entrenamiento/formación/comunicación sobre billetes 14. Estas entradas se introducen en un módulo configurable de neuroevaluación 2 con una configuración determinada que define el contexto 21 a extraer, (puede no proporcionarse contexto 211 , proporcionarse un contexto real 212 o proporcionarse un contexto virtual 213), el modo de presentación 22 del billete (puede ser un modo de presentación físico 221 o un modo de presentación virtual 222), los usuarios 23 a los que se van a exponer las muestras y los modos 24 de obtención de las respuestas (se contemplan la respuesta por el comportamiento humano 241 , la respuesta fisiológica 242 y las respuestas voluntarias 243). Sobre las entradas anteriores, adquiridas, de acuerdo a la configuración establecida en el módulo configurable de neuroevaluación 2, operan un conjunto de algoritmos /¿ 7 cargados en un módulo de proceso neurométrico 3 para extraer y ofrecer a su salida un conjunto de indicadores neurométricos 4, relacionados con la neuropercepción del billete x° = [x , x , - , 4], que pueden ser mostrados al usuario directamente en el módulo de salida 5 o servir de base para una métrica final de clasificación de los billetes. Figure 1 shows a block diagram that collects the methodology followed in a complete embodiment of the invention. According to said figure 1, the present invention contemplates an input 1 that can comprise one or more types of input signals x l = [x ^ x ^, ···, x n l ], such as real banknote samples 11, actual banknote samples with tampered security features 12, banknote test samples not in circulation 13 or banknote training / education / communication materials 14. These inputs are entered into a configurable neuro-evaluation module 2 with a configuration that defines the context 21 to be extracted, (context 211 may not be provided, a real context 212 provided or a virtual context 213 provided), the ticket presentation mode 22 (it may be a physical presentation mode 221 or a presentation mode virtual 222), users 23 to which the samples are to be exposed and the modes 24 of obtaining the responses (the response by human behavior 241, the physiological response 242 and the voluntary responses 243 are contemplated). On the previous inputs, acquired, according to the configuration established in the configurable neuro-evaluation module 2, a set of algorithms / ¿7 loaded in a neurometric process module 3 operate to extract and offer a set of neurometric indicators 4 at its output. , related to the neuroperception of the banknote x ° = [x, x, -, 4], which can be shown to the user directly in the output module 5 or serve as the basis for a final banknote classification metric.
De forma matricial, x° = A xl , siendo A e Mmxn(M), la matriz neurométrica de los billetes fl,l fl, n In a matrix form, x ° = A x l , where A e M mxn (M) is the neurometric matrix of the banknotes fl, l fl, n
A =
Figure imgf000012_0001
que aglutina el conjunto de operaciones realizadas en el módulo de fm, 1 fm,n A =
Figure imgf000012_0001
that brings together the set of operations carried out in the fm, 1 fm, n module
proceso 3. process 3.
Por tanto, las métricas obtenidas a la salida del módulo de proceso dependen completamente de las técnicas seleccionadas y modos de obtener las respuestas de los usuarios. En una de las realizaciones de la invención se contemplan las siguientes respuestas: Therefore, the metrics obtained at the output of the process module depend entirely on the selected techniques and ways of obtaining user responses. In one of the embodiments of the invention the following responses are contemplated:
- Respuesta de comportamiento humano 241 : - Human Behavioral Response 241:
• seguimiento ocular 2411 : se disponen varias cámaras infrarrojas para registrar las pupilas de los ojos. Después de una calibración, donde el usuario enfoca algunos puntos específicos, la mirada del usuario se determina mediante algoritmos de seguimiento de libre acceso, referenciados en coordenadas bidimensionales; • 2411 eye tracking: multiple infrared cameras are available to record the pupils of the eyes. After a calibration, where the user focuses on some specific points, the user's gaze is determined by free access tracking algorithms, referenced in two-dimensional coordinates;
•análisis de expresión facial 2412: se dispone una cámara frontal para la detección de gestos en la cara del usuario, los cuales serán posteriormente analizados aplicando algoritmos de análisis de expresión facial; y • facial expression analysis 2412: a front camera is available to detect gestures on the user's face, which will be subsequently analyzed by applying facial expression analysis algorithms; and
• seguimiento del comportamiento del usuario ante el billete 2413: comprende una recopilación de las interacciones que el usuario realiza con el billete, las cuales son obtenidas a través de un conjunto de cámaras que registran sus gestos. Para ello, se disponen varias cámaras RGB-D que, junto con algoritmos específicos de visión artificial, permiten detectar y cuantificar los gestos habituales de los usuarios en la interacción con el billete. - Respuesta fisiológica 242: • monitoring of user behavior when faced with ticket 2413: it comprises a compilation of the interactions that the user performs with the ticket, which are obtained through a set of cameras that record their gestures. To do this, several RGB-D cameras are available which, together with specific artificial vision algorithms, allow the detection and quantification of the habitual gestures of users when interacting with the banknote. - Physiological response 242:
• respuesta cerebral 2421 : se dispone, sobre la cabeza del usuario, un casco inalámbrico, en comunicación con el resto del sistema, para medición cerebral de electroencefalogramas; • 2421 brain response: a wireless helmet is placed on the user's head, in communication with the rest of the system, for brain measurement of electroencephalograms;
• variabilidad de ritmo cardiaco 2422, que puede medirse por ejemplo colocando unos electrodos en la zona torácica o por medio de un sensor fotoeléctrico en el dedo índice; y • 2422 heart rate variability, which can be measured for example by placing electrodes on the thoracic area or by means of a photoelectric sensor on the index finger; and
• conductancia de la piel 2423: opcionalmente puede medirse por medio de la aplicación de unos electrodos en la muñeca, en la palma de la mano o en las falanges medias de los dedos índice y anular para la medición de la conductancia de la piel. • skin conductance 2423: can optionally be measured by applying electrodes to the wrist, palm of the hand, or middle phalanges of the index and ring fingers to measure skin conductance.
- Respuesta voluntaria 243: - Voluntary response 243:
No se profundiza más en las respuestas voluntarias solicitadas a los usuarios, ya que corresponde a las medidas explícitas utilizadas de forma común en el estado del arte, es decir, las obtenidas mediante entrevistas, cuestionarios u otras vías contempladas habitualmente. The voluntary responses requested from users are not delved further, since it corresponds to the explicit measures commonly used in the state of the art, that is, those obtained through interviews, questionnaires or other routines commonly contemplated.
De acuerdo a la configuración del módulo 2, se obtienen unas señales biométricas para cada uno de los usuarios en la entrada 31 del módulo de proceso neurométrico 3. Por tanto, la entrada del módulo de proceso neurométrico agrupa las señales sincronizadas obtenidas para cada usuario por los correspondientes sensores, las relativas al comportamiento humano, las relativas a su respuesta fisiológica y las relativas a su respuesta voluntaria. According to the configuration of module 2, biometric signals are obtained for each of the users at the input 31 of the neurometric processing module 3. Therefore, the input of the neurometric processing module groups the synchronized signals obtained for each user by the corresponding sensors, those related to human behavior, those related to its physiological response and those related to its voluntary response.
Estas señales y medidas individuales recogidas para cada uno de los usuarios, se someten en el módulo de proceso neurométrico 3 a un proceso de acondicionamiento 32 que puede comprender técnicas para eliminar los ruidos que se hayan podido generar durante el proceso de medida (especialmente relevante en las señales fisiológicas), técnicas para descartar posibles valores atípicos y técnicas para la normalización de la señal si fuera necesario. These signals and individual measurements collected for each of the users are subjected in the neurometric processing module 3 to a conditioning process 32 that may include techniques to eliminate the noises that may have been generated during the measurement process (especially relevant in physiological signals), techniques to rule out possible outliers and techniques for signal normalization if necessary.
El acondicionamiento es un proceso necesario, excepto para las respuestas voluntarias, previo a la extracción de métricas relevantes de las señales. Cada una de las señales utilizadas recibe un acondicionamiento específico como los que se detallan a continuación. Conditioning is a necessary process, except for voluntary responses, prior to extracting relevant metrics from signals. Each of the signs used receives a specific conditioning such as those detailed below.
Así, por ejemplo, es preciso eliminar el ruido excesivo en la señal de seguimiento ocular 2411. Inevitablemente, este ruido va a registrarse debido a la inestabilidad inherente del ojo, y sobre todo, debido a los parpadeos, los cuales generan fuertes perturbaciones de la señal, pero estas perturbaciones pueden eliminarse dependiendo del dispositivo de recodificación de seguimiento ocular disponible. A menudo sucede que el dispositivo en sí tiene capacidad para filtrar los parpadeos, o que simplemente devuelve un valor de (0,0) cuando el rastreador ocular "pierde de vista" las características necesarias para registrar los movimientos oculares. En la práctica, los datos del seguimiento ocular, representados en coordenadas bidimensionales, que caen fuera de un rango rectangular dado pueden considerarse ruido y ser descartados. El uso de una región rectangular para eliminar el ruido de la señal (2D) también aborda otra limitación actual de los dispositivos de seguimiento ocular: su precisión se degrada normalmente en las regiones periféricas extremas. Por esta razón (así como la eliminación de parpadeos), puede ser razonable simplemente ignorar los datos de movimiento de los ojos que caen fuera del "rango operativo efectivo" del dispositivo. Este rango a menudo será especificado en términos de ángulo visual. Thus, for example, it is necessary to eliminate excessive noise in the eye-tracking signal 2411. Inevitably, this noise will register due to the inherent instability of the eye, and above all, due to blinking, which generates strong disturbances of the eye. signal, but these disturbances can be eliminated depending on the available eye-tracking recoding device. It often happens that the device itself has the ability to filter blinks, or that it simply returns a value of (0,0) when the eye tracker "loses sight of" the characteristics needed to record eye movements. In practice, eye-tracking data, represented in two-dimensional coordinates, that fall outside of a given rectangular range can be considered noise and discarded. Using a rectangular region to remove signal noise (2D) also addresses another current limitation of eye tracking devices: their accuracy typically degrades in extreme peripheral regions. For this reason (as well as the elimination of flickers), it may be reasonable to simply ignore eye movement data that falls outside the "effective operating range" of the device. This range will often be specified in terms of visual angle.
En el caso de señales relativas a la expresión facial 2412, el acondicionamiento comprende cuatro subprocesos que consisten principalmente en la detección de rostros, identificación de características, identificación de acciones e identificación de emociones. En primer lugar, se analizan la totalidad de los diferentes fotogramas que componen el video obtenido para identificar la cara del usuario mediante la aplicación de técnicas de visión artificial, como por ejemplo el algoritmo“Viola Jones Cascaded Classifier”. Una vez detectado el rostro del usuario en cada uno de los instantes de la prueba, se realiza una detección de las características de la cara utilizando algoritmos de codificación facial, por ejemplo el sistema FACS (“ Facial Action Coding System"), que pueden identificar características como vectores de los párpados, esquinas de la boca, punta de la nariz, etc. Se crea así una malla de puntos que representa la cara del usuario. A partir de estas características, se procede a la identificación de las denominadas“Unidades de Acción” por el sistema FACS, donde se caracterizan las acciones fundamentales de la cara (como por ejemplo“bajar cejas”,“arrugarla nariz”,“apretarlos labios”,“levantamiento exterior de ceja”, etc.). Por último, a partir de las diferentes Unidades de Acción identificadas, se aplica un clasificador que proporciona la probabilidad estadística en cada instante de estar experimentando una de las emociones básicas, dando una señal de 0 a 1. Las emociones comprendidas son alegría, ira, sorpresa, desprecio, disgusto y tristeza. Estas señales se corrigen posteriormente utilizando una línea base individualizada, utilizando la respuesta del usuario a un estímulo neutral, minimizando así sesgos individuales. Por lo tanto, la señal de expresión facial está compuesta finalmente por seis señales independientes, corregidas individualmente con una línea base, donde cada una de ellas representa la probabilidad de que el sujeto esté experimentando cada una de las emociones básicas en un instante de tiempo. In the case of cues related to facial expression 2412, the conditioning comprises four sub-processes consisting mainly of face detection, feature identification, action identification, and emotion identification. In the first place, all the different frames that make up the video obtained are analyzed to identify the user's face by applying artificial vision techniques, such as the "Viola Jones Cascaded Classifier" algorithm. Once the user's face has been detected in each of the moments of the test, a detection of the characteristics of the face is carried out using facial coding algorithms, for example the FACS system ("Facial Action Coding System"), which can identify characteristics such as vectors of the eyelids, corners of the mouth, tip of the nose, etc. This creates a mesh of points that represents the user's face. From these characteristics, we proceed to the identification of the so-called "Units of Action "by the FACS system, where the fundamental actions of the face are characterized (such as" lower eyebrows "," wrinkle the nose "," press the lips "," outer eyebrow lift ", etc.). Finally, to Based on the different Units of Action identified, the applies a classifier that provides the statistical probability at each moment of experiencing one of the basic emotions, giving a signal from 0 to 1. The emotions understood are joy, anger, surprise, contempt, disgust and sadness. These signals are subsequently corrected using an individualized baseline, using the user's response to a neutral stimulus, thus minimizing individual biases. Therefore, the facial expression signal is finally composed of six independent signals, individually corrected with a baseline, where each one of them represents the probability that the subject is experiencing each of the basic emotions in an instant of time.
Para las medidas y señales relativas al seguimiento de comportamiento humano 2413, el acondicionamiento se concentra principalmente en la detección de gestos del usuario en la señal de video, donde se observan sus manos e interacción con el billete, o material de comunicación. En primer lugar, el video se segmenta para cada uno de los billetes, o materiales de comunicación, presentados a cada usuario. Posteriormente cada segmento de video es analizado para detectar uno o varios eventos, por ejemplo: “el usuario voltea el billete”, “el usuario toca el billete buscando una textura distintiva”, “el usuario gira el billete”,“el usuario mira el billete al trasluz”,“el usuario manipula el billete buscando un sonido distintivo”,“el usuario dobla el billete”. La detección de estos gestos se realiza preferentemente mediante un proceso semi-manual que, apoyado en librerías de código abierto, como“OpenPose” , para caracterizar la posición de las manos, sus falanges y realizar una identificación inicial de los gestos descritos anteriormente, añade una revisión manual para confirmar la correcta identificación de los gestos detectados y procesados por los algoritmos. For the measurements and signals related to the monitoring of human behavior 2413, the conditioning is mainly concentrated in the detection of gestures of the user in the video signal, where their hands are observed and interaction with the bill, or communication material. First, the video is segmented for each of the tickets, or communication materials, presented to each user. Subsequently, each video segment is analyzed to detect one or several events, for example: "the user turns the ticket", "the user touches the ticket looking for a distinctive texture", "the user turns the ticket", "the user looks at the ticket against the light ”,“ the user manipulates the ticket looking for a distinctive sound ”,“ the user folds the ticket ”. The detection of these gestures is preferably carried out through a semi-manual process that, supported by open source libraries, such as "OpenPose", to characterize the position of the hands, their phalanges and perform an initial identification of the gestures described above, adds a manual review to confirm the correct identification of the gestures detected and processed by the algorithms.
Estas medidas y señales relativas al seguimiento de comportamiento humano también contemplan la posibilidad de que el usuario reciba estímulos sonoros y táctiles, como resultado de la manipulación del billete, ya que habitualmente un billete está hecho con un papel diferente al que se utiliza para escribir u otras actividades. Por ello, de la manipulación del billete se desprende un sonido de carteo característico que no se consigue con papel normal, lo que supone una de las medidas de seguridad más conocidas y reconocibles por los usuarios. These measures and signals related to the monitoring of human behavior also contemplate the possibility that the user receives sound and tactile stimuli, as a result of handling the banknote, since a banknote is usually made with a different paper than the one used to write u other activities. For this reason, the handling of the banknote gives off a characteristic playing sound that is not achieved with normal paper, which is one of the most well-known and recognizable security measures for users.
En cuanto al acondicionamiento de las respuestas fisiológicas 242, las señales y medidas relacionadas con la respuesta cerebral 2421 del usuario, se basan en una señal de electroencefalograma (EEG) compuesta por una señal de potencia por cada uno de los electrodos que componen el hardware de adquisición de datos. En primer lugar, los datos de cada canal se analizan para identificar canales dañados, usando el cuarto momento estandarizado (curtosis) de la señal de cada electrodo. Además, el canal también se considera dañado si la señal resulta más plana de un 10% de su duración total. Si se considera que un canal está dañado, se puede interpolar desde sus electrodos vecinos De acuerdo a una de las realizaciones particulares, la línea de base de la señal de electroencefalograma se elimina por sustracción de la media y fijando un filtro de paso de banda entre 0,5 y 40 Hz. La señal resultante es entonces segmentada en períodos de un segundo de duración. Se aplica una detección automática para rechazar períodos en los que más de dos canales contienen muestras que exceden un umbral absoluto, por ejemplo de 100.00 pV y un gradiente de 70.00 pV entre las muestras. Además, se realiza un análisis de componentes independientes (ICA) para identificar y eliminar componentes debidos a parpadeos, movimientos oculares y/o musculares. Dichos componentes son analizados mediante inspección visual por un experto entrenado para confirmar la efectividad de los algoritmos utilizados. Regarding the conditioning of the physiological responses 242, the signals and measures related to the brain response 2421 of the user, are based on a signal of electroencephalogram (EEG) composed of a power signal for each of the electrodes that make up the data acquisition hardware. First, the data from each channel is analyzed to identify damaged channels, using the standardized fourth moment (kurtosis) of the signal from each electrode. Additionally, the channel is also considered damaged if the signal is flatter than 10% of its total duration. If a channel is considered to be damaged, it can be interpolated from its neighboring electrodes According to one of the particular embodiments, the baseline of the EEG signal is removed by subtracting the mean and setting a band pass filter between 0.5 and 40 Hz. The resulting signal is then segmented into periods of one second duration. Automatic detection is applied to reject periods where more than two channels contain samples that exceed an absolute threshold, for example 100.00 pV and a gradient of 70.00 pV between samples. In addition, an Independent Component Analysis (ICA) is performed to identify and eliminate components due to blinking, eye movement and / or muscle. These components are analyzed by visual inspection by a trained expert to confirm the effectiveness of the algorithms used.
Para la variabilidad del ritmo cardíaco (del inglés HRV) 2422, el acondicionamiento de señal comprende analizar una señal de electrocardiograma (ECG), por ejemplo a través del algoritmo Pan-Tompkins, para la detección del intervalo QRS. Esta detección permite obtener una nueva serie temporal que caracteriza el electrocardiograma con el tiempo que pasa entre latidos. Para tener una señal de buena calidad, la detección realizada por el algoritmo Pan-Tompkins es revisada para detectar latidos ectópicos y artefactos y, finalmente, se obtiene una serie de pulsaciones RR que recogen la diferencia temporal entre dos pulsaciones consecutivas y permite realizar el análisis de variabilidad del ritmo cardíaco. For heart rate variability (HRV) 2422, signal conditioning comprises analyzing an electrocardiogram (ECG) signal, for example via the Pan-Tompkins algorithm, for detection of the QRS interval. This detection allows obtaining a new time series that characterizes the electrocardiogram with the time that passes between beats. To have a good quality signal, the detection carried out by the Pan-Tompkins algorithm is reviewed to detect ectopic beats and artifacts and, finally, a series of RR beats is obtained that collect the time difference between two consecutive beats and allows the analysis to be carried out. heart rate variability.
Para la conductancia de la piel 2423, el acondicionamiento consiste en una inspección visual para el diagnóstico y corrección de los artefactos que pueda incorporar la señal. Estos artefactos se corrigen mediante interpolaciones lineales de primer o segundo grado. A continuación, se extrae la componente fásica de la señal a la señal limpia, que es la afectada por los cambios inconscientes derivados de estímulos puntuales, y no está afectada por otros cambios como por ejemplo la temperatura. Finalmente, esta señal con la componente fásica es estandarizada utilizando las fórmulas de Venables and Christie para eliminar las diferencias ínter-sujeto. Una vez que las señales han pasado por el proceso de acondicionamiento 32, el módulo de proceso neurométrico 3 aplica, señal por señal, unos algoritmos para la extracción de variables biométricas numéricas de interés 33 en cada una de las señales acondicionadas. Las variables biométricas individuales de cada usuario son obtenidas y sincronizadas con las fases de la neuroevaluación de los estímulos planteados. Este proceso se repite por cada uno de los usuarios de la muestra completa y por cada una de las señales registradas en el test analizado en cada caso. Los valores de las variables biométricas obtenidas en esta fase generan una base de datos de métricas que es la empleada en la siguiente fase para extraer los indicadores neurométricos, resultado de la neuroevaluación del billete. A continuación se detallan algunos ejemplos de las técnicas matemáticas aplicadas, de acuerdo a una de las realizaciones de la invención, en cada una de las señales para obtener las variables biométricas que conformarán la base de datos sobre la que calcular los indicadores neurométricos. For skin conductance 2423, conditioning consists of a visual inspection for diagnosis and correction of artifacts that the signal may incorporate. These artifacts are corrected by first or second degree linear interpolations. Next, the phasic component of the signal is extracted to the clean signal, which is affected by unconscious changes derived from specific stimuli, and is not affected by other changes such as temperature. Finally, this signal with the phasic component is standardized using the Venables and Christie formulas to eliminate inter-subject differences. Once the signals have passed through the conditioning process 32, the neurometric processing module 3 applies, signal by signal, algorithms for the extraction of numerical biometric variables of interest 33 in each of the conditioned signals. The individual biometric variables of each user are obtained and synchronized with the phases of the neuro-evaluation of the stimuli proposed. This process is repeated for each of the users of the complete sample and for each of the signals recorded in the test analyzed in each case. The values of the biometric variables obtained in this phase generate a database of metrics that is used in the next phase to extract the neurometric indicators, resulting from the neuroevaluation of the banknote. Below are some examples of the mathematical techniques applied, according to one of the embodiments of the invention, in each of the signals to obtain the biometric variables that will make up the database on which to calculate the neurometric indicators.
En el caso de la señal de seguimiento ocular 2411 el proceso sigue el esquema de la figura 2. Así, en un primer paso, se procede a la extracción de parámetros básicos del seguimiento ocular 70. Por medio de una serie de algoritmos, se extraen los principales parámetros del seguimiento ocular, que son diferencias entre fijaciones y movimientos sacádicos. Por fijaciones se entiende los instantes en los que el ojo está enfocando la escena visual para hacer llegar al cerebro la información visual. Por movimientos sacádicos se entiende el desplazamiento del ojo con el fin de volver a enfocar de nuevo otro punto de interés visual. In the case of the eye tracking signal 2411, the process follows the scheme in figure 2. Thus, in a first step, the basic parameters of eye tracking 70 are extracted. By means of a series of algorithms, they are extracted the main parameters of eye tracking, which are differences between fixations and saccades. By fixations we mean the instants in which the eye is focusing on the visual scene to convey visual information to the brain. By saccades is meant the displacement of the eye in order to refocus another point of visual interest.
Para ello se aplica un algoritmo de detección a la señal en bruto, con el fin de extrapolar si la muestra analizada forma parte de una fijación o de un movimiento sacádico. El algoritmo más empleado es el basado en la velocidad del ojo. Aplicando un filtro al movimiento del ojo con una ventana de, por ejemplo, 0,05 segundos, cada dato en bruto de la presente realización se clasifica en uno de los dos siguientes estados: For this, a detection algorithm is applied to the raw signal, in order to extrapolate whether the analyzed sample is part of a fixation or a saccadic movement. The most widely used algorithm is the one based on the speed of the eye. By applying a filter to eye movement with a window of, for example, 0.05 seconds, each raw data of the present embodiment is classified into one of the following two states:
(Ó ³ 100 ( °/sec ) ® el dato es parte de un mov. sacádico (Ó ³ 100 (° / sec) ® the data is part of a saccadic movement
Q < 100 ( °/sec ) ® el dato es parte de una fijación Q <100 (° / sec) ® the data is part of a setting
Las correcciones se calculan a través de los grupos de muestras definidos por parte de la fijación, siempre que la duración alcance un mínimo, establecido por ejemplo en 100 ms. La posición de la fijación se define por el promedio de posición de las muestras asociadas a esa fijación. Las longitudes de los movimientos sacádicos se definen por la distancia entre las fijaciones continuas. Corrections are calculated across the groups of samples defined by the fixture, as long as the duration reaches a minimum, set for example to 100 ms. The position of the fixation is defined by the average position of the samples associated with that fixation. The lengths of the saccades are defined by the distance between continuous fixings.
Adicionalmente, se contempla una división de los movimientos sacádicos, aplicable a la visión del billete o material de comunicación, que divide estos movimientos del ojo entre movimientos sacádicos ambientales (los que barren el billete por completo) o movimientos sacádicos focales (los que se mueven en torno a una zona concreta del billete de interés). En este caso concreto, para diferencias entre movimientos ambientales y focales se aplican los siguientes umbrales: Additionally, a division of saccades is contemplated, applicable to the vision of the bill or communication material, which divides these eye movements between environmental saccades (those that sweep the bill completely) or focal saccades (those that move around a specific area of the note of interest). In this specific case, for differences between environmental and focal movements, the following thresholds apply:
(Q ³ 4.8 0 ® mov. sacádico ambiental (Q ³ 4.8 0 ® mov. Saccadic environmental
t Q < 4.8 0 ® mov. sacádico focal t Q <4.8 0 ® mov. focal saccadic
Una vez se han extraído los parámetros básicos del seguimiento ocular 70, de acuerdo a lo anterior, se procede a la traslación 71 de los parámetros de seguimiento ocular en tres dimensiones al diseño del billete en dos dimensiones. Exceptuando el caso en el que el diseño del billete se presente en un monitor digital, donde el billete virtual ya está localizado desde un principio por la programación del motor gráfico, en el resto de situaciones los parámetros se ajustan a un sistema de coordenadas tridimensional, el cual debe ser trasladado a un modelo bidimensional del billete para facilitar el cálculo posterior de métricas relativas al billete por completo y a zonas internas de interés. Para ello se genera un procedimiento semiautomático que ayuda a trasladar el sistema de coordenadas de fijaciones y movimientos sacádicos de un sistema 3D a un sistema 2D, especialmente centrado sobre el billete que está siendo evaluado en cada instante de la prueba. Dicho procedimiento aplica algoritmos de segmentación e identificación de objetos por análisis de imagen para identificar el billete bajo estudio en el espacio, de manera que la posición del billete en el sistema de coordenadas 3D es conocida en todo momento. Al mismo tiempo y de manera sincronizada, la posición del ojo del usuario es monitorizada en ese mismo sistema de coordenadas 3D, con lo que puede realizarse un emparejamiento de ambos valores sobre un espacio bidimensional 2D, en el que representar el billete como una imagen en ambas caras sobre la que proyectar las fijaciones y movimientos sacádicos obtenidos. Once the basic parameters of the eye tracking 70 have been extracted, according to the above, we proceed to the translation 71 of the eye tracking parameters in three dimensions to the design of the bill in two dimensions. Except for the case in which the design of the ticket is presented on a digital monitor, where the virtual ticket is already located from the beginning by the programming of the graphic engine, in the rest of the situations the parameters are adjusted to a three-dimensional coordinate system, which must be transferred to a two-dimensional model of the bill to facilitate the subsequent calculation of metrics relative to the bill as a whole and to internal areas of interest. For this, a semiautomatic procedure is generated that helps to transfer the coordinate system of fixations and saccades from a 3D system to a 2D system, especially centered on the note that is being evaluated at each moment of the test. Said procedure applies algorithms for segmentation and identification of objects by image analysis to identify the banknote under study in space, so that the position of the banknote in the 3D coordinate system is known at all times. At the same time and in a synchronized way, the position of the user's eye is monitored in the same 3D coordinate system, with which a pairing of both values can be made on a 2D two-dimensional space, in which the banknote is represented as an image in both faces on which to project the fixations and saccades obtained.
La referencia a un proceso“semiautomático”, se debe al mismo hecho de que con las etapas anteriores, donde los procesos se llevan a cabo en una primera instancia por la ejecución del algoritmo de forma automática, es recomendable un revisión manual por personal cualificado que permita confirmar los resultados obtenidos de forma automática, realizar correcciones donde sea necesario y contribuir a afinar los algoritmos para sucesivos análisis. The reference to a "semiautomatic" process is due to the same fact that with the previous stages, where the processes are carried out in the first instance by executing the algorithm automatically, a manual review by qualified personnel is recommended. allows you to confirm the results obtained automatically, make corrections where necessary and help to fine-tune the algorithms to successive analyzes.
Siguiendo el esquema representado en la figura 2 para la extracción de métricas de interés de la señal de seguimiento ocular 2411 , en el caso de considerar relevante el interés visual del usuario en determinadas zonas del billete o material de comunicación, éste debe segmentarse en todas las zonas de interés que se deseen. Así, se contempla una etapa de predefinición de las áreas de interés del billete 72. Cada una de estas zonas puede abarcar elementos de diseño, elementos de seguridad o elementos de comunicación del billete sobre los que resulte interesante conocer la percepción de los usuarios. Únicamente será necesario marcar con una herramienta software, en cada una de las caras, las coordenadas de los vértices de las zonas de interés. Following the scheme represented in figure 2 for the extraction of metrics of interest from the eye-tracking signal 2411, if the visual interest of the user is considered relevant in certain areas of the ticket or communication material, it must be segmented in all the areas of interest that are desired. Thus, a stage of predefinition of the areas of interest of the note 72 is contemplated. Each of these areas can include design elements, security elements or communication elements of the note about which it is interesting to know the perception of the users. It will only be necessary to mark with a software tool, on each of the faces, the coordinates of the vertices of the areas of interest.
Independientemente de que se definan áreas de interés en el billete, el procedimiento de extracción de métricas de la señal de seguimiento ocular contempla una extracción 73 de métricas relativas a la atención visual del usuario sobre todo el billete o material de comunicación en general. Estas métricas tendrán en cuenta uno o varios de los siguientes eventos: “fijaciones en el billete entero (por ambas caras)’’, “movimientos sacádicos en el billete”,“parpadeos de la visión en el billete (medida que suele aportar el equipo de seguimiento ocular)”,“tamaño de la pupila (medida que suele aportare! equipo de seguimiento ocular)’’. La identificación de eventos en la señal de seguimiento ocular, propicia la aplicación de una serie de operaciones matemáticas, para traducir esos eventos en información cuantificable, que comprenden por ejemplo: contar la cantidad de eventos (fijaciones, movimientos sacádicos, parpadeos) que suceden dentro del billete entero (por ambas caras); contar el tiempo que dura cada evento de promedio; contar la frecuencia de estos eventos en un período de tiempo definido; u obtener la secuencia de estos eventos. Regardless of whether areas of interest are defined on the bill, the procedure for extracting metrics from the eye-tracking signal contemplates an extraction 73 of metrics related to the user's visual attention on the entire bill or communication material in general. These metrics will take into account one or more of the following events: "fixations on the entire bill (on both sides)", "saccades on the bill", "flashes of vision on the bill (measure usually provided by the team eye tracking) ”,“ pupil size (measurement usually provided by eye tracking equipment) ”. The identification of events in the eye-tracking signal encourages the application of a series of mathematical operations to translate those events into quantifiable information, including, for example: counting the number of events (fixations, saccades, blinks) that happen within of the entire bill (on both sides); count the time each average event lasts; count the frequency of these events in a defined period of time; or get the sequence of these events.
Por otro lado, en el caso de que algunas áreas concretas del billete o material de comunicación tengan un interés especial y estas áreas hayan sido predefinidas en la etapa 72 de la figura 2, el procedimiento de extracción de métricas de la señal de seguimiento ocular contempla una extracción 74 de métricas relativas a la atención visual del usuario sobre dichas áreas de interés predefinidas. En este caso se calcula previamente un parámetro básico adicional, asociado a las áreas de interés, que es el término“visita". Por“ visita” se entiende un tipo de evento en el que concurren más de una fijación continua y que el tiempo entre fijaciones no supera un umbral de tiempo preestablecido, por ejemplo de un segundo. A las métricas con información cuantificable descritas anteriormente, se añaden ahora las obtenidas por eventos de tipo“visita", como por ejemplo detectar si en el caso de las visitas se produce de nuevo una visita a la misma zona o lo que es lo mismo, si se producen“ revisitas” y cuántas. On the other hand, in the event that some specific areas of the ticket or communication material have a special interest and these areas have been predefined in step 72 of figure 2, the procedure for extracting metrics from the eye tracking signal includes an extraction 74 of metrics related to the visual attention of the user on said predefined areas of interest. In this case, an additional basic parameter is previously calculated, associated with the areas of interest, which is the term “visit.” By “visit” we mean a type of event in which more than one continuous fixation occurs and that the time between fixings does not exceed a time threshold preset, for example one second. To the metrics with quantifiable information described above, those obtained by "visit" type events are now added, such as detecting if, in the case of visits, a visit to the same area occurs again or what is the same, if there are “revisits” and how many.
La extracción de variables biométricas numéricas de interés 33, para el caso concreto de la señal de expresión facial 2412 comprende caracterizar la respuesta de cada usuario, a cada uno de los billetes mostrados, a partir de varias emociones independientes identificadas y procesadas. Para ello, las señales son segmentadas conforme al tiempo de presentación de los estímulos, extrayendo varias señales independientes que caracterizan cada billete. De estas señales se obtienen tres tipos de variables: las primeras son métricas generales, computando la media de la señal en el estímulo (ej: promedio de la probabilidad de “alegría”) las segundas son métricas basadas en umbrales, donde a cada señal se le aplica una función que analiza si la probabilidad de estar en una emoción particular es superior a X, para posteriormente calcular el porcentaje de tiempo que el sujeto ha estado por encima de dicho umbral, donde dicho umbral puede definirse en dos niveles, por ejemplo 0,5 para detectar el porcentaje de tiempo que el sujeto ha estado experimentado esa emoción, independientemente de la intensidad, y 0,8 para calcular el porcentaje de tiempo que el sujeto ha estado experimentado intensamente esa emoción; por último el tercer tipo de métricas son las métricas ratio, como por ejemplo la ratio entre emociones positivas y negativas. The extraction of numerical biometric variables of interest 33, for the specific case of the facial expression signal 2412, comprises characterizing the response of each user, to each of the banknotes displayed, from several independent identified and processed emotions. For this, the signals are segmented according to the presentation time of the stimuli, extracting several independent signals that characterize each bill. Three types of variables are obtained from these signals: the first are general metrics, computing the mean of the signal in the stimulus (eg: average probability of "joy"), the second are metrics based on thresholds, where each signal is applies a function that analyzes whether the probability of being in a particular emotion is higher than X, to later calculate the percentage of time that the subject has been above said threshold, where said threshold can be defined in two levels, for example 0 , 5 to detect the percentage of time that the subject has been experiencing that emotion, regardless of intensity, and 0.8 to calculate the percentage of time that the subject has been experiencing that emotion intensely; Finally, the third type of metrics are ratio metrics, such as the ratio between positive and negative emotions.
Para las variables biométricas de seguimiento de comportamiento humano 2413, a partir de la señal acondicionada, se contabiliza el número de veces que un gesto es ejecutado durante la visualización de un billete, y el porcentaje que representa frente al número total de gestos. For the biometric variables for monitoring human behavior 2413, from the conditioned signal, the number of times that a gesture is executed while viewing a ticket is counted, and the percentage it represents compared to the total number of gestures.
De las señales asociadas a la respuesta cerebral 2421, la extracción de variables biométricas numéricas de interés comprende, a partir de las señales acondicionadas tras el proceso de acondicionamiento 32, un análisis espectral de la señal de encefalograma para estimar la potencia espectral en cada segundo, dentro de la banda de frecuencia clásica: Q (4-8 Hz), a (8-12 Hz), b (13-25 Hz), y (25-40 Hz). De acuerdo a una de las realizaciones, se realiza usando el método de Welch con un 50% de solapamiento, de donde derivan métricas que caracterizan la potencia de cada una de las bandas en cada segundo y, a partir de ellas, se derivan otras métricas como la asimetría frontal, que puede ser interpretada como la cantidad de motivación (acercamiento) o rechazo frente a un estímulo. Es definida como: From the signals associated with the brain response 2421, the extraction of numerical biometric variables of interest comprises, from the signals conditioned after the conditioning process 32, a spectral analysis of the encephalogram signal to estimate the spectral power in each second, within the classical frequency band: Q (4-8 Hz), a (8-12 Hz), b (13-25 Hz), and (25-40 Hz). According to one of the embodiments, it is carried out using the Welch method with 50% overlap, from which metrics that characterize the power of each of the bands are derived in each second and, from them, other metrics are derived. like frontal asymmetry, which It can be interpreted as the amount of motivation (approach) or rejection in the face of a stimulus. It is defined as:
siendo F4 y F3 los electrodos
Figure imgf000021_0001
J where F4 and F3 are the electrodes
Figure imgf000021_0001
J
colocados en esa posición según el sistema internacional 10-20. placed in that position according to the international 10-20 system.
Además de las métricas derivadas de la potencia espectral, en una de las realizaciones de la invención también se calculan las que caracterizan los estados cognitivos. Estas variables utilizan clasificadores entrenados previamente que, a partir de unas tareas iniciales que debe realizar el usuario para calibrar el clasificador, permiten predecir el nivel de“ enganche” y de“carga de trabajo". El“ enganche” refleja el nivel general de enganche, compromiso, atención y concentración durante el escaneo visual de recogida de información del usuario, mientras que por“carga de trabajo” se entiende cualquier proceso cognitivo que implique un proceso ejecutivo, como por ejemplo el razonamiento analítico, la resolución de problemas o la memoria de trabajo. In addition to the metrics derived from spectral power, in one of the embodiments of the invention those that characterize the cognitive states are also calculated. These variables use pre-trained classifiers that, based on initial tasks that the user must perform to calibrate the classifier, allow predicting the level of “hook” and “workload.” The “hook” reflects the general level of hook , commitment, attention and concentration during the visual scanning of the user's information collection, while by "workload" is understood any cognitive process that implies an executive process, such as analytical reasoning, problem solving or memory of work.
La extracción de variables biométricas numéricas de interés 33, para el caso concreto de la señal de variabilidad del ritmo cardíaco 2422 comprende tres tipos de variables: las derivadas del dominio del tiempo, las derivadas del dominio de frecuencia y las que cuantifican las dinámicas no-lineales. The extraction of numerical biometric variables of interest 33, for the specific case of the heart rate variability signal 2422, comprises three types of variables: those derived from the time domain, those derived from the frequency domain and those that quantify non-dynamics. linear.
El análisis en el dominio del tiempo incluye las siguientes características: promedio y desviación estándar de los intervalos RR, la raíz cuadrada de la media de la suma de los cuadrados de las diferencias entre los intervalos RR adyacentes (RMSSD), el número de diferencias sucesivas de intervalos que difieren en más de 50 ms (pNN50), la interpolación triangular del histograma de variabilidad del ritmo cardíaco (HRV) y el ancho de referencia del histograma RR evaluado mediante interpolación triangular (TINN). The time domain analysis includes the following characteristics: mean and standard deviation of the RR intervals, the square root of the mean of the sum of squares of the differences between the adjacent RR intervals (RMSSD), the number of successive differences of intervals that differ by more than 50 ms (pNN50), the triangular interpolation of the heart rate variability histogram (HRV) and the reference width of the RR histogram evaluated by triangular interpolation (TINN).
Las características en el dominio de la frecuencia se calculan usando la densidad del espectro de potencia (PSD), aplicando la Transformada Rápida de Fourier. El análisis se realiza en tres bandas: VLF (frecuencia muy baja, <0,04 Hz), LF (frecuencia baja, 0,04- 0,15 Hz) y HF (frecuencia alta, 0,12-0,4 Hz). Para cada una de las tres bandas de frecuencias se calcula el valor máximo (que corresponde a la frecuencia que tiene la magnitud máxima) y la potencia de cada banda de frecuencia en términos absolutos y porcentuales. Se calcula la potencia normalizada (n.u.) para las bandas LF y HF y el porcentaje de potencia total, restando previamente la potencia de VLF a la potencia total. La relación LF/HF se calcula para cuantificar el equilibrio simpatovagal y para reflejar modulaciones simpáticas. Además, se calcula la potencia total. The characteristics in the frequency domain are calculated using the power spectrum density (PSD), applying the Fast Fourier Transform. The analysis is performed in three bands: VLF (very low frequency, <0.04 Hz), LF (low frequency, 0.04-0.15 Hz) and HF (high frequency, 0.12-0.4 Hz) . For each of the three frequency bands, the maximum value (which corresponds to the frequency with the maximum magnitude) and the power of each frequency band are calculated in absolute and percentage terms. The normalized power (nu) for the LF and HF bands and the percentage of total power are calculated, previously subtracting the VLF power from the total power. The LF / HF ratio is calculated to quantify sympathovagal balance and to reflect sympathetic modulations. Also, the total power is calculated.
Finalmente, también son extraídas varias características utilizando análisis no lineales, ya que han demostrado ser cuantificadores importantes de la dinámica de control cardiovascular. En primer lugar, se aplica un análisis de Poincaré, que es una técnica visual y cuantitativa, en la que la forma de una trama se clasifica en clases funcionales, proporcionando información resumida del comportamiento del corazón. Un eje transversal (SD1) se asocia con una rápida variabilidad latido a latido y un eje longitudinal (SD2) analiza la variabilidad a largo plazo de R-R. Se incluye además un análisis de entropía, utilizando métodos existentes en el estado del arte como“Sample entropy” (SampEn), “Approximate entropy” (ApEn) y correlaciones DFA. Finally, several characteristics are also extracted using non-linear analyzes, since they have been shown to be important quantifiers of cardiovascular control dynamics. First, a Poincaré analysis is applied, which is a visual and quantitative technique, in which the shape of a frame is classified into functional classes, providing summary information on the behavior of the heart. A transverse axis (SD1) is associated with rapid beat-to-beat variability and a longitudinal axis (SD2) analyzes the long-term variability of R-R. An entropy analysis is also included, using existing methods in the state of the art such as “Sample entropy” (SampEn), “Approximate entropy” (ApEn) and DFA correlations.
Para la conductividad de la piel 2423, a partir de la señal limpia que representa la componente fásica del EDA (actividad electrodérmica), se generarán dos tipos de variables biométricas que caracterizan el nivel de activación del usuario al visualizar un billete o material de comunicación. El primer tipo se compone del promedio de la señal en el segmento de cada estímulo, mientras que el segundo tipo de variable analiza los picos experimentados por el usuario durante la visualización del billete. Estos picos estarán caracterizados por el número de picos por minuto y su amplitud promedio. For the conductivity of the skin 2423, from the clean signal that represents the phasic component of the EDA (electrodermal activity), two types of biometric variables will be generated that characterize the level of activation of the user when viewing a ticket or communication material. The first type is composed of the average of the signal in the segment of each stimulus, while the second type of variable analyzes the peaks experienced by the user while viewing the bill. These peaks will be characterized by the number of peaks per minute and their average amplitude.
En cuanto a la extracción de variables biométricas de las respuestas voluntarias 243 del usuario, en caso de incorporar tareas como el reconocimiento del billete, lectura o visionado de material de comunicación, estas respuestas se cuantifican con el porcentaje de aciertos y fallos. Además, se calcula el promedio del tiempo de respuesta en cada una de las tareas. Ejemplos de entrevistas y cuestionarios llevados a cabo son los siguientes: tras la visualización de cada billete (anverso y reverso) en el monitor por el usuario, se pregunta sobre ciertos ejes semánticos como estética, calidad, diseño, durabilidad, placer o aspectos emocionales, además de una evaluación y asociación inconsciente de atributos abiertos para cada uno de los billetes; tras la visualización de todos los billetes por el usuario, se completa un cuestionario compuesto por preguntas para saber qué billetes, qué elementos de seguridad se recuerdan, en qué parte del billete se ubica cierto elemento de seguridad o qué contenido incorpora el material de comunicación, y preguntas de reconocimiento que muestran imágenes de billetes que preguntan al usuario si se mostraron o no durante la prueba; tras la interacción física con cada billete por parte del usuario, se completa un cuestionario para evaluar el soporte físico del billete (papel, plástico o sus variantes) o del material de comunicación y atributos similares a la fase anterior, pero agregando atributos relacionados con la manipulación del billete como la geometría, la textura, el sonido y/o el relieve. Regarding the extraction of biometric variables from the user's voluntary responses 243, in the case of incorporating tasks such as ticket recognition, reading or viewing communication material, these responses are quantified with the percentage of hits and misses. In addition, the average response time is calculated for each of the tasks. Examples of interviews and questionnaires carried out are the following: after viewing each banknote (front and back) on the monitor by the user, questions are asked about certain semantic axes such as aesthetics, quality, design, durability, pleasure or emotional aspects, in addition to an evaluation and unconscious association of open attributes for each of the banknotes; After viewing all the tickets by the user, a questionnaire consisting of questions is completed to find out which tickets, what security elements are remembered, where on the ticket is a certain security element located or what content the communication material incorporates, and recognition questions showing banknote images that ask the user whether or not they were shown during the test; after physical interaction with each banknote By the user, a questionnaire is completed to evaluate the physical support of the banknote (paper, plastic or their variants) or of the communication material and attributes similar to the previous phase, but adding attributes related to the handling of the banknote such as geometry, texture, sound and / or relief.
Tras la etapa completa de extracción de variables biométricas de interés 33 con información cuantificable de las señales acondicionadas 32 obtenidas previamente mediante los diferentes sensores biométricos, de acuerdo a la configuración establecida en el módulo configurable de neuroevaluación 2, y presentadas en la entrada 31 del módulo de proceso neurométrico, el módulo de proceso neurométrico 3 de la presente invención aplica un algoritmo de clasificación en un módulo predictivo 34, para obtener a la salida un conjunto de indicadores neurométricos 4 de la neurovaluación del usuario. After the complete stage of extraction of biometric variables of interest 33 with quantifiable information of the conditioned signals 32 previously obtained by means of the different biometric sensors, according to the configuration established in the configurable neuro-evaluation module 2, and presented in the input 31 of the module of neurometric processing, the neurometric processing module 3 of the present invention applies a classification algorithm in a predictive module 34, to obtain at the output a set of neurometric indicators 4 of the user's neuro-evaluation.
El algoritmo de clasificación, que posteriormente será aplicado a cada una de las respuestas de los usuarios en los billetes, precisa ser calibrado previamente. La figura 3 comprende un diagrama de bloques que representa las dos partes en las que se divide la calibración: primero la generación de un conjunto de referencia verdadero 300 (“ ground truth” en inglés) y segundo, la creación del modelo predictivo 310. Así, para la generación del conjunto de referencia verdadero, se utilizarán las variables biométricas 33 obtenidas para un conjunto de billetes, por ejemplo cien billetes. Preferiblemente el conjunto de billetes abarca un rango lo más amplio posible de respuestas a nivel cognitivo, emocional y de comportamiento. Este conjunto es elegido preferiblemente por un equipo multidisciplinar de expertos seleccionados de diferentes campos/sectores (como banca, psicología o neurociencia) y contiene tanto billetes reales como diseños ad-hoc que garanticen una gran disparidad de respuestas. El grupo de expertos selecciona 301 únicamente las variables biométricas relacionadas con el indicador neurométrico, del conjunto de indicadores neurométricos 4, que se está generando en cada momento (se incluyen algunos ejemplos más adelante de la relación entre las variables biométricas seleccionadas y los diferentes indicadores de neuroevaluación). Con los valores de las métricas seleccionadas en el conjunto de billetes o material de comunicación evaluado por cada uno de los usuarios, se aplica un algoritmo de aprendizaje automático no supervisado de tipo agrupamiento (k-means) para agrupar 302 los billetes en función de sus respuestas. De esta manera, se dividen los cien billetes en distintos grupos según su respuesta en las diferentes métricas que componen los indicadores. Posteriormente, se calcula la media de cada grupo, que representa la respuesta promedio en cada grupo. El equipo de expertos valida 308 los grupos y analiza 303 en profundidad las respuestas de cada grupo a partir de su media y asigna un valor 304 del indicador a este grupo de billetes, por ejemplo siguiendo una escala Likert del 1 al 5. The classification algorithm, which will later be applied to each of the users' responses to the banknotes, needs to be previously calibrated. Figure 3 comprises a block diagram that represents the two parts into which the calibration is divided: first, the generation of a true reference set 300 (“ground truth” in English) and second, the creation of the predictive model 310. Thus For the generation of the true reference set, the biometric variables 33 obtained for a set of banknotes, for example one hundred banknotes, will be used. Preferably the banknote set covers the widest possible range of responses on a cognitive, emotional and behavioral level. This set is preferably chosen by a multidisciplinary team of experts selected from different fields / sectors (such as banking, psychology or neuroscience) and contains both real banknotes and ad-hoc designs that guarantee a great disparity of answers. The group of experts selects 301 only the biometric variables related to the neurometric indicator, from the set of neurometric indicators 4, which is being generated at each moment (some examples are included below of the relationship between the selected biometric variables and the different indicators of neuroevaluation). With the values of the selected metrics in the set of banknotes or communication material evaluated by each of the users, an unsupervised machine learning algorithm of the grouping type (k-means) is applied to group 302 the banknotes according to their answers. In this way, the hundred bills are divided into different groups according to their response to the different metrics that make up the indicators. Subsequently, the mean of each group is calculated, which represents the average response in each group. He A team of experts validates 308 the groups and analyzes in depth 303 the responses of each group based on their mean and assigns a value 304 of the indicator to this group of banknotes, for example following a Likert scale from 1 to 5.
Una vez generado 300 el conjunto de referencia de los cien billetes del ejemplo, donde a cada uno se le ha asignado 304 un valor en cada uno de los indicadores, se procede a la creación 310 del modelo de clasificación. Para ello se crea un conjunto de datos donde las entradas son las variables biométricas seleccionadas 301 y la salida es el valor ya asignado 304 al indicador neurométrico correspondiente. Con este conjunto de datos se diseña el modelo predictivo 306 basado en redes neuronales artificiales. El entrenamiento 305 de la red neuronal, que es alimentada con las métricas seleccionadas 301 y los valores asignados 304, es validado 307 aplicando un algoritmo de validación cruzada de k-iteraciones con una k de 10 y, posteriormente, el modelo se testea con el 15% de la muestra, que ha sido extraída con anterioridad del proceso de validación. Una vez validado y testeado el modelo predictivo 306, podrá ser aplicado a las variables biométricas de cualquier billete, dando una valoración en cada uno de los indicadores neurométricos. Once the reference set of the one hundred banknotes in the example has been generated 300, where each one has been assigned 304 a value in each of the indicators, the classification model 310 is created. For this, a data set is created where the inputs are the selected biometric variables 301 and the output is the value already assigned 304 to the corresponding neurometric indicator. With this data set the predictive model 306 based on artificial neural networks is designed. The training 305 of the neural network, which is fed with the selected metrics 301 and the assigned values 304, is validated 307 applying a cross-validation algorithm of k-iterations with a k of 10 and, subsequently, the model is tested with the 15% of the sample, which has been extracted prior to the validation process. Once the predictive model 306 has been validated and tested, it can be applied to the biometric variables of any banknote, giving an assessment on each of the neurometric indicators.
La salida del módulo predictivo 34 comprende los indicadores generados de acuerdo a los modelos predictivos obtenidos, los cuales son aplicados a las variables biométricas numéricas de interés 33 y producen como resultado un valor para cada uno de los indicadores de la neuroevaluación de cada billete para cada usuario. The output of the predictive module 34 comprises the indicators generated according to the predictive models obtained, which are applied to the numerical biometric variables of interest 33 and produce as a result a value for each of the indicators of the neuro-evaluation of each banknote for each user.
La figura 4 muestra un esquema con las señales medidas de cada usuario a tener en cuenta para el cálculo de ciertos indicadores. De acuerdo a una de las realizaciones de la invención, en la que se contemplan cinco indicadores, para el cálculo de un primer indicador de interés visual 41 (BVIS), se consideran relevantes las respuestas de comportamiento humano 241 representadas por las señales de seguimiento ocular 2411 y análisis de expresión facial 2412, no es necesaria ninguna de las respuestas fisiológicas 242 y sí son tenidas en cuenta respuestas voluntarias en forma de entrevista 2433, cuestionarios 2434 y respuesta a tareas 2431 ; para el cálculo de un segundo indicador de enganche 42 (BEI), se considera relevante la respuesta de comportamiento humano 241 representada por las señales de seguimiento ocular 2411, la respuestas fisiológicas 242 representadas por la respuesta cerebral 2421 y la variabilidad de ritmo cardíaco 2422, y las respuestas voluntarias en forma de cuestionarios 2434; para el cálculo de un tercer indicador de carga de trabajo 43 (BWI), se consideran relevantes las respuestas de comportamiento humano 241 representadas por las señales de seguimiento ocular 2411, de análisis de expresión facial 2412 y de seguimiento del comportamiento del usuario 2413, las respuestas fisiológicas 242 representadas por la respuesta cerebral 2421 y las repuestas voluntarias en forma de respuesta a tareas 2431 y tiempo de reacción 2432; para el cálculo de un cuarto indicador emocional 44 (BEII) se consideran relevantes las respuestas de comportamiento humano 241 representadas por el análisis de expresión facial 2412, las respuestas fisiológicas 242 representadas por la variabilidad de ritmo cardíaco 2422 y la conductancia de la piel 2423, y las respuestas voluntarias en forma de entrevista 2433 y cuestionarios 2434; para el cálculo de un quinto indicador de seguridad 45 (BSCI), se consideran relevantes las respuestas de comportamiento humano 241 representadas por las señales de seguimiento ocular 2411 y de seguimiento del comportamiento del usuario 2413, las respuestas fisiológicas 242 representadas por la conductancia de la piel 2423 y las repuestas voluntarias en forma de entrevista 2433, cuestionario 2434, respuesta a tareas 2431 y tiempo de reacción 2432. Figure 4 shows a diagram with the measured signals of each user to be taken into account for the calculation of certain indicators. According to one of the embodiments of the invention, in which five indicators are contemplated, for the calculation of a first indicator of visual interest 41 (BVIS), the human behavior responses 241 represented by the eye-tracking signals are considered relevant. 2411 and analysis of facial expression 2412, none of the physiological responses 242 is necessary and voluntary responses are taken into account in the form of interviews 2433, questionnaires 2434 and response to tasks 2431; For the calculation of a second engagement indicator 42 (BEI), the human behavior response 241 represented by the eye tracking signals 2411, the physiological responses 242 represented by the brain response 2421 and the heart rate variability 2422 are considered relevant, and voluntary responses in the form of 2434 questionnaires; For the calculation of a third workload indicator 43 (BWI), the human behavior responses 241 represented by the signals of eye tracking 2411, facial expression analysis 2412 and user behavior monitoring 2413 are considered relevant. physiological responses 242 represented by brain response 2421 and voluntary responses in the form of task response 2431 and reaction time 2432; For the calculation of a fourth emotional indicator 44 (BEII), the human behavioral responses 241 represented by the facial expression analysis 2412, the physiological responses 242 represented by the heart rate variability 2422 and the skin conductance 2423 are considered relevant, and voluntary responses in the form of interviews 2433 and questionnaires 2434; For the calculation of a fifth safety indicator 45 (BSCI), the human behavior responses 241 represented by the eye tracking 2411 and user behavior monitoring 2413 signals, the physiological responses 242 represented by the conductance of the skin 2423 and the voluntary responses in the form of interview 2433, questionnaire 2434, response to tasks 2431 and reaction time 2432.
El indicador de interés visual 41 BVIS (del inglés“Banknote Visual Interest Score“), es una métrica relacionada con el interés a nivel visual que despierta el diseño del billete. Esta métrica de alto nivel se centra en un modelo no lineal que establece una puntuación del interés a nivel visual que la percepción del diseño del billete genera y que permite su comparación entre diferentes tipos de diseño. Para ello el indicador se calcula a través de técnicas de aprendizaje supervisado aplicado sobre las variables biométricas de interés 33, extraídas de las señales acondicionadas seleccionadas, las cuales contienen información cuantificable y que en esta realización concretamente comprende: The indicator of visual interest 41 BVIS (Banknote Visual Interest Score), is a metric related to the interest at a visual level that the banknote design arouses. This high-level metric focuses on a non-linear model that establishes a score of interest at the visual level that the perception of the banknote design generates and that allows its comparison between different types of design. For this, the indicator is calculated through supervised learning techniques applied to the biometric variables of interest 33, extracted from the selected conditioned signals, which contain quantifiable information and which in this embodiment specifically comprise:
• métricas relativas al tiempo de visionado de las zonas de interés relativas al diseño del billete o material de comunicación vs. el tiempo de visionado de las zonas de seguridad u otra zona de interés relativa al contenido de los materiales de comunicación; • metrics related to viewing time of the areas of interest relative to the design of the ticket or communication material vs. the viewing time of the security zones or other areas of interest related to the content of the communication materials;
• métricas relativas al tiempo total destinado a la visualización del billete o material de comunicación frente a la navegación visual fuera del billete o material de comunicación; • metrics related to the total time spent viewing the ticket or communication material versus visual navigation outside the ticket or communication material;
• métricas relativas a cómo el ojo explora el billete o material de comunicación y a la relación entre exploración (movimientos sacádicos ambientales) y a la focalización (movimientos sacádicos focales); • métricas relativas a la secuencia de la mirada en la visión de los elementos de diseño del billete o material de comunicación. vs. los elementos de seguridad u otra zona de interés relativa al contenido de los materiales de comunicación; • metrics related to how the eye explores the bill or communication material and the relationship between exploration (environmental saccades) and targeting (focal saccades); • metrics related to the sequence of the gaze in the vision of the design elements of the ticket or communication material. vs. the security elements or other area of interest related to the content of the communication materials;
• ratio de cuadrantes por segundo del billete que navega el ojo del usuario, dividiendo el billete en un número determinado de cuadrantes; • ratio of quadrants per second of the banknote that the user's eye navigates, dividing the banknote into a certain number of quadrants;
• porcentaje de billete explorado; y • percentage of banknote scanned; and
• ratio entre el número de movimientos amplios vs movimientos cortos del ojo dentro del billete. • ratio between the number of wide movements vs short movements of the eye within the banknote.
Adicionalmente, en este indicador de interés visual, se contemplan algunos valores relativos a la respuesta voluntaria como una valoración global del diseño de los billetes evaluados; el recuerdo de los billetes y de áreas de interés del billete; y los tiempos destinados a realizar las tareas de evaluación del billete. Additionally, in this indicator of visual interest, some values related to the voluntary response are considered as a global assessment of the design of the evaluated banknotes; the memory of the tickets and areas of interest of the ticket; and the times allocated to carry out the banknote evaluation tasks.
Uno de los indicadores cognitivos, el indicador de enganche 42 BEI (del inglés“Banknote Engagement Index’), hace referencia al nivel de atención sostenida funcional que la persona está aplicando a la percepción del billete o material de comunicación. Este indicador es de mucho interés porque refleja si el billete o material de comunicación suscita el interés suficiente para focalizarse en él. Además, permite discernir si el sujeto está concentrado en la tarea y por tanto el resto de métricas obtenidas en ese instante son de valor. One of the cognitive indicators, the 42 BEI down payment indicator (Banknote Engagement Index ”), refers to the level of sustained functional attention that the person is applying to the perception of the banknote or communication material. This indicator is of great interest because it reflects whether the bill or communication material arouses enough interest to focus on it. In addition, it allows to discern if the subject is focused on the task and therefore the rest of the metrics obtained at that moment are of value.
Uno de los indicadores cognitivos utilizado en una de las realizaciones de la presente invención, el indicador de carga de trabajo 43 BWI (del inglés “Banknote Workload Index”), hace referencia a la carga cognitiva o esfuerzo mental que supone para el sujeto el proceso de percepción y valoración de ciertos atributos del billete o material de comunicación. Es muy importante debido a que una carga cognitiva elevada puede suponer que existe una saturación de información, lo cual lleva al rechazo, pero al mismo tiempo un valor bajo puede indicar aburrimiento del sujeto, lo cual también es negativo. One of the cognitive indicators used in one of the embodiments of the present invention, the workload indicator 43 BWI (Banknote Workload Index), refers to the cognitive load or mental effort that the process entails for the subject. of perception and assessment of certain attributes of the ticket or communication material. It is very important because a high cognitive load can mean that there is an information saturation, which leads to rejection, but at the same time a low value can indicate boredom of the subject, which is also negative.
En una de las realizaciones de la invención se contempla un indicador cognitivo que combina los dos anteriores, indicador de enganche 42 BEI e indicador de carga de trabajo 43 BWI. In one of the embodiments of the invention, a cognitive indicator that combines the previous two, engagement indicator 42 BEI and workload indicator 43 BWI, is contemplated.
El indicador emocional 44 BEII (del inglés“Banknote Emotional Induction Indetf’) utilizado en una de las realizaciones de la invención, es una métrica relativa a la capacidad de inducción emocional del billete o material de comunicación. Concretamente, el indicador BEI se sustenta en el cálculo y representación de un punto en un eje espacial bidimensional en el que se extrae la capacidad de excitación emocional ( Arousal ) y la capacidad de generar una emoción positiva o negativa (Valencia). Para calcular estas dos dimensiones que sustentan al indicador BEII se hace uso del procesamiento de la señal proveniente de las medidas comportamentales (por ejemplo las micro expresiones faciales durante el visionado del billete) y de la respuesta fisiológica (asimetría de los hemisferios cerebrales, variabilidad cardiaca y conductancia de la piel). The 44 BEII emotional indicator (Banknote Emotional Induction Indetf ') used In one of the embodiments of the invention, it is a metric relative to the emotional induction capacity of the bill or communication material. Specifically, the BEI indicator is based on the calculation and representation of a point on a two-dimensional spatial axis from which the capacity for emotional arousal (Arousal) and the capacity to generate a positive or negative emotion (Valencia) are extracted. To calculate these two dimensions that support the BEII indicator, the processing of the signal from behavioral measures (for example, micro facial expressions during the viewing of the banknote) and the physiological response (asymmetry of the cerebral hemispheres, cardiac variability is used and skin conductance).
El indicador de seguridad 45 BSCI (del inglés “Banknote Security Capacity Index”) utilizado en una de las realizaciones de la invención, es una métrica relativa a la seguridad del billete. Concretamente, este indicador refleja la capacidad que tiene el diseño y los elementos de seguirdad del billete de ser autenticados por el público. Su cálculo se sustenta en varios parámetros relativos a la señal de comportamiento (como por ejemplo el seguimiento ocular de los elementos de seguridad del billete, seguimiento automático de los gestos de interacción del participante con el billete) y valores de respuesta del sujeto voluntaria. A través de la modelización de estos parámetros se puede obtener un índice absoluto que permite la comparación de nuevos diseños y elementos de seguridad en un mismo billete o la comparación de diseños y elementos de seguridad actuales de diferentes tipos de billete. The security indicator BSCI (English "Banknote Security Capacity Index") used in one of the embodiments of the invention, is a metric related to the security of the banknote. Specifically, this indicator reflects the capacity of the banknote's design and security elements to be authenticated by the public. Its calculation is based on several parameters related to the behavioral signal (such as, for example, eye tracking of the security elements of the ticket, automatic monitoring of the participant's interaction gestures with the ticket) and voluntary subject response values. Through the modeling of these parameters, an absolute index can be obtained that allows the comparison of new designs and security elements in the same banknote or the comparison of current designs and security elements of different types of banknote.
Una vez aplicados los modelos predictivos 306 a las variables biométricas seleccionadas, que contienen métricas numéricas de interés con información cuantificable, y obtenidos los indicadores de neuroevaluación para cada billete o materiales de comunicación, estos indicadores son procesados en un módulo de salida 5 dotado de distintas funcionalidades. En este módulo de salida 5, los indicadores neurométricos 4 se tratan estadísticamente para caracterizar satisfactoriamente un billete o materiales de comunicación. Por un lado, se mide la respuesta general del billete, o materiales de comunicación, utilizando técnicas de agregación de datos (por ejemplo la media aritmética, o la desviación estándar) y, por otro lado, en función de condiciones y casos concretos, se llevan a cabo diferentes análisis adicionales para determinar si existen diferencias significativas que permitan inferir conclusiones finales relativas al objetivo del estudio de neuroevaluación. Por ejemplo, además de las técnicas de comparación de las medias, pueden emplearse técnicas de correlación y técnicas de agrupamiento. Todo este análisis estadístico se implementa automáticamente asegurando la reproducibilidad y la comparación de los mismos estudios completados en varias fechas y en varios lugares. Por tanto, el análisis de inferencia estadística extrae las diferencias significativas en las variables biométricas con métricas numéricas de interés 33. Contrastando diferentes modelos, como por ejemplo análisis de varianza o prueba de Kruskal-Wallis, se comparan los indicadores calculados según diferentes agrupaciones. Estos análisis son aplicados para analizar las diferencias en los indicadores neurométricos entre diferentes billetes presentados, y/o las diferencias con diferentes diseños de un mismo billete (por cambios en el diseño, tamaño o posición de elementos del diseño del billete), lo que puede estar ponderado por factores adicionales como el género, la edad o la familiaridad de manejo del dinero en efectivo del usuario. Once the predictive models 306 have been applied to the selected biometric variables, which contain numerical metrics of interest with quantifiable information, and the neuro-evaluation indicators are obtained for each banknote or communication materials, these indicators are processed in an output module 5 equipped with different functionalities. In this output module 5, the neurometric indicators 4 are statistically processed to satisfactorily characterize a ticket or communication materials. On the one hand, the general response of the banknote, or communication materials, is measured using data aggregation techniques (for example the arithmetic mean, or standard deviation) and, on the other hand, depending on specific conditions and cases, it is carry out different additional analyzes to determine if there are significant differences that allow to infer final conclusions regarding the objective of the neuroevaluation study. For example, in addition to means comparison techniques, correlation techniques and grouping techniques can be used. Everything This statistical analysis is implemented automatically ensuring the reproducibility and comparison of the same studies completed on various dates and in various locations. Therefore, the statistical inference analysis extracts the significant differences in the biometric variables with numerical metrics of interest 33. By contrasting different models, such as analysis of variance or the Kruskal-Wallis test, the indicators calculated according to different groupings are compared. These analyzes are applied to analyze the differences in the neurometric indicators between different banknotes presented, and / or the differences with different designs of the same banknote (due to changes in the design, size or position of elements of the banknote design), which can be weighted by additional factors such as the user's gender, age, or cash handling familiarity.
Posteriormente al cálculo de los indicadores, en una de las realizaciones de la invención, el módulo de salida 5 calcula una métrica final que engloba todos los indicadores calculados y ofrece una instantánea del rendimiento del billete, o material de comunicación, que permite una rápida valoración, comparación y clasificación frente a otros billetes evaluados. Esta métrica final se basa en una puntuación de 1 a 10 a través de una ecuación matemática en la que cada uno de los indicadores neurométricos calculados influye con un peso determinado. After calculating the indicators, in one of the embodiments of the invention, the output module 5 calculates a final metric that encompasses all the indicators calculated and offers a snapshot of the performance of the banknote, or communication material, which allows a quick assessment , comparison and classification against other evaluated banknotes. This final metric is based on a score from 1 to 10 through a mathematical equation in which each of the calculated neurometric indicators influences a given weight.
Cuanto más alto sea el puntaje, mejor será el desempeño del diseño evaluado. Si en algún caso se quiere prescindir de algún indicador el modelo recalcula el valor anulando el impacto del valor de ese indicador neurométrico. De esta manera el indicador es dinámico y refleja únicamente los indicadores que sean de interés en cada caso concreto (por ejemplo, se puede recalcular el marcador final anterior para que sólo refleje el impacto de los indicadores visual y cognitivo o incluso sólo uno de ellos). The higher the score, the better the performance of the evaluated design. If in any case you want to dispense with an indicator, the model recalculates the value canceling the impact of the value of that neurometric indicator. In this way, the indicator is dynamic and reflects only the indicators that are of interest in each specific case (for example, the previous final score can be recalculated so that it only reflects the impact of the visual and cognitive indicators or even only one of them) .
Una de las realizaciones contempla la representación gráfica, por ejemplo mediante mapas de calor, ejes bidimensionales, curvas o porcentajes, de todas las variables biométricas, indicadores neurométricos e inferencias estadísticas obtenidas durante el proceso llevado a cabo por cada uno de los módulos de la invención. La figura 5 representa una de estas visualizaciones particulares, donde se representa una cara de un billete y, asociadas a cada una de las áreas de interés definidas, se representan los valores de los indicadores (no mostrados en la figura) obtenidos para dichas áreas de interés. Por ejemplo, para un área de interés definida para abarcar un elemento de seguridad incorporado en el billete, como un holograma 52, una marca de agua 53, una impresión de tinta especial 54 o una ventana 55, los indicadores representados codifican la neuroevaluación obtenida de la percepción de los usuarios de ese elemento de seguridad. En una realización, a cada una de las áreas de interés se le asocia una puntuación en porcentaje del tiempo de visita, de los visitantes y de las revisitas, lo que además está complementado por un mapa de calor y la secuencia de visitas de las diferentes áreas de interés. Por ejemplo, tras el análisis del área de interés que incluye el holograma 52 se obtiene un tiempo de visita del 14,92% del tiempo total invertido en inspeccionar el billete, un 86,53% de usuarios que lo han observado y un 78,72% de usuarios que lo han revisitado. Este tipo de medidas son las que hacen posible construir los indicadores para la comparación entre billetes, comparación de elementos y clasificación. One of the embodiments contemplates the graphic representation, for example by means of heat maps, two-dimensional axes, curves or percentages, of all the biometric variables, neurometric indicators and statistical inferences obtained during the process carried out by each of the modules of the invention. . Figure 5 represents one of these particular views, where one side of a banknote is represented and, associated with each of the defined areas of interest, the values of the indicators (not shown in the figure) obtained for said areas of interest. For example, for an area of interest defined to encompass an item of security incorporated in the banknote, such as a hologram 52, a watermark 53, a special ink print 54 or a window 55, the represented indicators encode the neuro-evaluation obtained from the users' perception of that security element. In one embodiment, each of the areas of interest is associated with a score in percentage of the visit time, of the visitors and of the return visits, which is also complemented by a heat map and the sequence of visits of the different areas of interest. For example, after analyzing the area of interest included in hologram 52, a visit time of 14.92% of the total time invested in inspecting the ticket is obtained, 86.53% of users who have observed it and 78, 72% of users who have revisited it. These types of measures are what make it possible to build the indicators for the comparison between banknotes, comparison of elements and classification.
En una de las realizaciones, la presente invención clasifica en el módulo de salida 5 una muestra completa de billetes de acuerdo a los indicadores obtenidos asociados a las áreas de interés que abarcan elementos de seguridad. El nivel de seguridad de los elementos de seguridad está determinado por la percepción del público y resulta un factor determinante para valorar su incorporación en futuros billetes de curso legal. La clasificación de los billetes en función de la percepción de los usuarios de los elementos de seguridad, permite seleccionar los elementos de seguridad entre aceptables y no aceptables para ser incorporados en moneda de curso legal, estableciéndose un umbral mínimo en los indicadores para determinar que la percepción del público del elemento de seguridad es suficiente para ser incorporado en el billete. Estos umbrales mínimos pueden calibrarse utilizando elementos de seguridad modificados y analizando cómo varía la percepción de los usuarios ante las modificaciones de distintos elementos de seguridad. Así los elementos de seguridad modificados que obtengan una mejor clasificación en la percepción de los usuarios, serán los elementos de seguridad más apropiados para ser incorporados a los billetes de curso legal. Atendiendo por ejemplo a las señales de seguimiento ocular, es determinante el número de revisitas del usuario al elemento de seguridad o el tiempo empleado en visualizar dicho elemento respecto al resto del billete. In one of the embodiments, the present invention classifies in the output module 5 a complete sample of banknotes according to the indicators obtained associated with the areas of interest that include security elements. The level of security of the security elements is determined by the perception of the public and is a determining factor in assessing their incorporation into future legal tender bills. The classification of the banknotes based on the perception of the users of the security elements, allows selecting the security elements between acceptable and not acceptable to be incorporated in legal tender, establishing a minimum threshold in the indicators to determine that the Public perception of the security element is sufficient to be incorporated into the ticket. These minimum thresholds can be calibrated using modified security elements and analyzing how the perception of the users varies with the modifications of different security elements. Thus, the modified security elements that obtain a better classification in the perception of users will be the most appropriate security elements to be incorporated into legal tender banknotes. Considering, for example, the eye-tracking signals, the number of return visits of the user to the security element or the time spent viewing said element with respect to the rest of the ticket is decisive.
Aparte de la comparación entre elementos del mismo tipo, en una de las realizaciones de la invención resulta particularmente ventajoso monitorizar la influencia de unos parámetros sobre otros y, principalmente, la influencia de la variación de un parámetro sobre otro. Por ejemplo, el color del billete frente a la seguridad percibida de un cierto elemento de seguridad. Si el objetivo es determinar el color del billete que más seguridad proporciona, el conjunto de billetes que serán sometidos a neuroanálisis diferirán únicamente en el color de su diseño, pero mantendrán inalterados sus elementos de seguridad. El neuroanálisis de la percepción de los usuarios permitirá determinar si las variaciones de color tienen influencia en la percepción de los elementos de seguridad, caracterizar los distintos billetes en función de la percepción de los usuarios y finalmente clasificarlos ordenadamente de una manera objetiva, siendo el billete mejor clasificado el correspondiente al color más apropiado para la seguridad del billete. Por ejemplo, un color gris para el billete podría anular en gran medida la seguridad de un elemento de tipo holograma o un elemento de hilo de seguridad de apariencia metálica, que quedarían prácticamente camuflados y pasarían desapercibidos para un usuario. Es decir, de acuerdo al planteamiento del ejemplo, la clasificación indicará cómo perturba cada uno de los colores de prueba la percepción de los elementos de seguridad integrados en el billete, con lo que la clasificación final determina el color a incluir en el billete a fabricar. Apart from the comparison between elements of the same type, in one of the embodiments of the invention it is particularly advantageous to monitor the influence of some parameters on others and, mainly, the influence of the variation of a parameter over another. For example, the color of the bill versus the perceived security of a certain security item. If the objective is to determine the color of the banknote that provides the most security, the set of banknotes that will be subjected to neuroanalysis will differ only in the color of their design, but will keep their security elements unaltered. The neuroanalysis of users 'perception will make it possible to determine whether color variations have an influence on the perception of security elements, characterize the different banknotes based on users' perception and finally classify them in an objective way, being the banknote best classified the one corresponding to the most appropriate color for the security of the note. For example, a gray color for the bill could greatly nullify the security of a hologram-like element or a metallic-looking security thread element, which would be practically camouflaged and would go unnoticed by a user. That is, according to the approach of the example, the classification will indicate how each of the test colors disturbs the perception of the security elements integrated in the banknote, with which the final classification determines the color to be included in the banknote to be manufactured .
De acuerdo a otros objetivos que persiguen el diseño de otros parámetros del billete diferentes al color, como por ejemplo el tamaño del billete, el tamaño de un cierto elemento, la posición de un cierto elemento o la utilización de diferentes materiales, las muestras de billetes y las áreas de interés se seleccionan para que sean precisamente esos parámetros los que varíen de unos billetes a otros y, de una forma análoga al caso anterior, la caracterización de la percepción de los usuarios indica de una manera objetiva la influencia que tienen dichos parámetros en el billete. Por ejemplo, definiendo un área de interés 56 que recoja el valor del billete (50 euros por ejemplo), resulta interesante comparar la influencia que tienen distintos tamaños y posiciones frente a la percepción de los elementos de diseño y seguridad del billete. En este caso concreto, la marca de agua 53 puede ver afectada su seguridad percibida a partir de un cierto tamaño de la representación del valor de billete, o una posición demasiado cercana, ya que atrae la atención visual del usuario en exceso y anularía o reduciría la percepción de la marca de agua, lo que reduce la seguridad del billete ante el usuario. Incluso otros elementos del billete que en apariencia no tienen más que una función meramente estética, como la decoración recogida por el área de interés 57, también son importantes en la valoración global del billete y su color, tamaño o posición pueden influir en la seguridad del mismo, por lo que en una de las realizaciones se contempla el análisis de absolutamente todos los elementos del billete. Además de la representación gráfica mostrada en la figura 5, se contemplan otros resultados comparativos que pueden mostrarse gráficamente. Principalmente se contempla la comparación de los tiempos de visionado de las áreas de interés asociadas a elementos de diseño del billete normalizados en referencia al espacio físico que ocupan; curvas del efecto de la posición vs. el indicador de interés visual BVIS (utilidad para el caso de presentar variantes de posición de un mismo elemento del billete a neuroevaluar); y curvas del efecto del tamaño vs. indicador de interés visual BVIS (utilidad para el caso de presentar variantes de tamaño de un mismo elemento del billete a neuroevaluar). According to other objectives that pursue the design of other parameters of the banknote other than color, such as the size of the banknote, the size of a certain element, the position of a certain element or the use of different materials, banknote samples and the areas of interest are selected so that it is precisely those parameters that vary from one banknote to another and, in a manner analogous to the previous case, the characterization of the perception of the users indicates in an objective way the influence that said parameters have on the ticket. For example, defining an area of interest 56 that collects the value of the banknote (50 euros for example), it is interesting to compare the influence that different sizes and positions have on the perception of the design and security elements of the banknote. In this specific case, the watermark 53 may see its perceived security affected from a certain size of the representation of the banknote value, or a position that is too close, since it attracts the visual attention of the user in excess and would cancel or reduce the perception of the watermark, which reduces the security of the ticket to the user. Even other elements of the banknote that apparently have no more than a purely aesthetic function, such as the decoration collected by the area of interest 57, are also important in the overall valuation of the banknote and their color, size or position can influence the security of the banknote. itself, so that in one of the embodiments the analysis of absolutely all the banknote elements is contemplated. In addition to the graphical representation shown in Figure 5, other comparative results are contemplated that can be graphically displayed. Mainly, the comparison of the viewing times of the areas of interest associated with standardized ticket design elements in reference to the physical space they occupy is contemplated; position effect curves vs. the visual interest indicator BVIS (useful in the case of presenting position variants of the same element of the banknote to be neuro-evaluated); and curves of the effect of size vs. BVIS visual interest indicator (useful in the case of presenting size variants of the same banknote item to be neuro-evaluated).
La figura 6 esquematiza las posibilidades de presentación de objetos para la neuroevaluación de la presente invención, preferiblemente billetes de banco o materiales de comunicación, tanto en formato real como virtual. Las muestras de billetes o materiales de comunicación a analizar comprenden distintas características de seguridad, diseño o contenido de los materiales de comunicación de acuerdo, entre otros, a distintos materiales, diseños, tamaños y posiciones, que influyen en la percepción que el público tiene del billete. El contexto de las muestras de billetes pueden presentarse al usuario mediante distintas técnicas 21 , que pasan por no aportar contexto alguno 211 , añadir un contexto real 212 o añadir un contexto virtualizado 213 en el que utilizando técnicas de gráficos digitales y de computadora se reproducen distintos escenarios, entre los que se contemplan: un escenario de realidad virtual, donde la configuración de evaluación se usa en condiciones de laboratorio bajo una réplica virtual del mundo real, que puede consistir en modelos bidimensionales (2D) del contexto real; un escenario de realidad aumentada, donde la configuración de la evaluación se usa en condiciones de la vida real, pero complementado con algunos elementos virtuales en 3D; y un escenario de virtualidad aumentada, donde la configuración de la evaluación se usa en condiciones de laboratorio, pero se presenta al usuario una réplica virtual aumentada del contexto real. Figure 6 schematizes the possibilities of presenting objects for the neuro-evaluation of the present invention, preferably banknotes or communication materials, both in real and virtual format. The samples of banknotes or communication materials to be analyzed include different security characteristics, design or content of the communication materials according, among others, to different materials, designs, sizes and positions, which influence the perception that the public has of the ticket. The context of the banknote samples can be presented to the user using different techniques 21, which include not providing any context 211, adding a real context 212 or adding a virtualized context 213 in which different digital and computer graphics techniques are reproduced scenarios, among which are contemplated: a virtual reality scenario, where the evaluation configuration is used in laboratory conditions under a virtual replica of the real world, which can consist of two-dimensional (2D) models of the real context; an augmented reality scenario, where the assessment settings are used in real life conditions, but supplemented with some virtual 3D elements; and an augmented virtuality scenario, where the assessment configuration is used under laboratory conditions, but an augmented virtual replica of the real context is presented to the user.
Por otro lado, dependiendo del canal sensorial humano que se pretenda aprovechar, el contexto puede proporcionarse mediante una sola o una combinación de las siguientes interfaces inmersivas: dispositivos visuales (como monitores convencionales, monitores en posición vertical con visión 3D estereoscópica y seguimiento 3D de la posición del usuario principal (interfaz "tanque de peces"), monitor en posición horizontal con visión 3D estereoscópica y seguimiento 3D de la posición del usuario principal (o interfaz "banco de trabajo"), pantallas envolventes compuestas de grandes pantallas basadas en proyección y/o monitores de gran tamaño, exhibiciones hemisféricas, o cascos de realidad virtual (HMD-Head Mounted Displays) y/o realidad aumentada y/o realidad mixta); pantallas auditivas (donde por ejemplo los sonidos contextúales se reproducen utilizando técnicas de generación de sonido 3D con auriculares y/o altavoces externos); pantallas olfativas (donde los aromas se entregan a través de narices electrónicas y/o cualquier pantalla olfativa comercial); o pantallas hápticas (donde se proporcionan señales táctiles y kinestésicas a través de un dispositivo táctil háptico de visualización, como por ejemplo referencias terrestres, referencias corporales, táctiles, o combinación de las anteriores). On the other hand, depending on the human sensory channel to be harnessed, the context can be provided through a single or a combination of the following immersive interfaces: visual devices (such as conventional monitors, upright monitors with stereoscopic 3D vision and 3D tracking of the position of the main user (interface "fish tank"), monitor in horizontal position with stereoscopic 3D vision and 3D tracking of the position of the main user (or interface "bank of work "), surround screens composed of large projection-based screens and / or large monitors, hemispheric displays, or virtual reality helmets (HMD-Head Mounted Displays) and / or augmented reality and / or mixed reality); screens auditory (where for example contextual sounds are reproduced using 3D sound generation techniques with headphones and / or external speakers); olfactory screens (where aromas are delivered through electronic noses and / or any commercial olfactory screen); or screens haptic (where tactile and kinesthetic cues are provided through a haptic display touch device, such as earth landmarks, body landmarks, tactile, or a combination of the above).
En cuanto a la presentación de los billetes 22, dejando a un lado el contexto, la presente invención contempla también varias alternativas mostradas en la figura 6. Principalmente se utilizan dos técnicas en función de su capacidad de fidelidad para reproducir situaciones de la vida real: utilizar un billete físico 221, donde se presenta al usuario un modelo real físico del billete; o utilizar un billete digital 222, donde se presenta una réplica digital del billete usando bien un modelo de billete virtual que reproduce, en dos o 3 dimensiones, una imagen digital del billete real, o en un modelo de billete virtual basado en una interfaz tangible que el usuario puede manipular con sus manos. Esta interfaz tangible puede representar en tres dimensiones los elementos gráficos en el papel físico utilizando técnicas de realidad aumentada espacial. El resultado final de las técnicas de superposición se puede presentar al usuario mediante un casco de realidad virtual o alternativamente puede prescindirse de este tipo de dispositivos y optar por proyectores digitales que muestran la información directamente sobre el billete físico. Regarding the presentation of banknotes 22, leaving aside the context, the present invention also contemplates several alternatives shown in figure 6. Mainly two techniques are used depending on their fidelity capacity to reproduce real life situations: using a physical ticket 221, where a real physical model of the ticket is presented to the user; or use a digital ticket 222, where a digital replica of the ticket is presented using either a virtual ticket model that reproduces, in two or 3 dimensions, a digital image of the real ticket, or in a virtual ticket model based on a tangible interface that the user can manipulate with their hands. This tangible interface can render graphic elements on physical paper in three dimensions using spatial augmented reality techniques. The final result of the overlay techniques can be presented to the user by means of a virtual reality headset or alternatively, this type of device can be dispensed with and opt for digital projectors that display the information directly on the physical ticket.
La presente invención no debe verse limitada a las formas de realización aquí descritas. Otras configuraciones pueden ser realizadas por los expertos en la materia a la vista de la presente descripción. En consecuencia, el ámbito de la invención queda definido por las siguientes reivindicaciones. The present invention should not be limited to the embodiments described herein. Other configurations can be made by those skilled in the art in light of the present description. Accordingly, the scope of the invention is defined by the following claims.

Claims

REIVINDICACIONES
1. Método para clasificar billetes basado en neuroanálisis, caracterizado por que comprende los siguientes pasos: 1. Method for classifying banknotes based on neuroanalysis, characterized in that it comprises the following steps:
a) proporcionar a un usuario una información visual de un billete; a) providing a user with visual information on a ticket;
b) adquirir, mediante un sensor de un módulo de entrada (2) al menos una señal biométrica del usuario, como respuesta a la información visual del billete; b) acquiring, by means of a sensor of an input module (2) at least one biometric signal from the user, in response to the visual information of the ticket;
c) segmentar, en un módulo de proceso (3), las señales biométricas adquiridas en períodos de tiempo predeterminados; c) segmenting, in a processing module (3), the biometric signals acquired in predetermined periods of time;
d) comparar cada uno de los segmentos con unos patrones preestablecidos; e) identificar ciertos eventos como resultado de la comparación de cada uno de los segmentos con los patrones preestablecidos; d) comparing each of the segments with pre-established patterns; e) identify certain events as a result of comparing each of the segments with the pre-established patterns;
f) obtener al menos una variable biométrica basada en los eventos identificados; g) analizar, en el módulo de proceso, las variables biométricas, de acuerdo a resultados conocidos previamente almacenados en una base de datos; f) obtaining at least one biometric variable based on the identified events; g) analyze, in the process module, the biometric variables, according to previously known results stored in a database;
h) establecer, en el módulo de proceso, un indicador neurométrico en función del análisis del paso anterior; y h) establish, in the process module, a neurometric indicator based on the analysis of the previous step; and
i) clasificar, en un módulo de salida (5), el billete de acuerdo al indicador neurométrico establecido. i) classify, in an output module (5), the banknote according to the established neurometric indicator.
2. Método de acuerdo a la reivindicación 1 , donde la información visual del billete se proporciona de forma física, de forma virtual o mediante una combinación de las dos en una interfaz tangible sobre la que se representan elementos virtuales añadidos a un billete físico mediante tecnología de realidad aumentada. 2. Method according to claim 1, where the visual information of the ticket is provided physically, virtually or through a combination of the two in a tangible interface on which virtual elements added to a physical ticket are represented by technology of augmented reality.
3. Método de acuerdo a cualquiera de las reivindicaciones anteriores, donde la señal biométrica, comprende información de al menos un proceso implícito del usuario, a seleccionar entre: análisis de gestos en la interacción del billete con las manos, seguimiento ocular y análisis de expresión facial. 3. Method according to any of the preceding claims, where the biometric signal comprises information from at least one implicit process of the user, to be selected from: analysis of gestures in the interaction of the ticket with the hands, eye tracking and expression analysis facial.
4. Método de acuerdo a cualquiera de las reivindicaciones anteriores, donde la señal biométrica comprende información de una respuesta fisiológica del usuario a seleccionar entre: una respuesta cerebral, una variación del ritmo cardíaco y la conductancia de la piel. 4. Method according to any of the preceding claims, wherein the biometric signal comprises information on a physiological response of the user to be selected from: a brain response, a variation of the heart rate and the conductance of the skin.
5. Método de acuerdo a la reivindicación 3, que comprende obtener una variable biométrica del seguimiento ocular del usuario, donde los eventos identificados resultan de la comparación de la señal de seguimiento ocular con un patrón que establece un primer umbral de velocidad de movimiento del ojo del usuario que determina la presencia de un evento de fijación o un evento de movimiento sacádico. 5. Method according to claim 3, which comprises obtaining a variable biometric of the user's eye tracking, where the identified events result from the comparison of the eye tracking signal with a pattern that establishes a first threshold of speed of movement of the user's eye that determines the presence of a fixation event or an event of saccadic movement.
6. Método de acuerdo a la reivindicación 5 donde un evento de movimiento sacádico, además comprende determinar si corresponde a un movimiento sacádico ambiental o un movimiento sacádico focal, de acuerdo a un segundo umbral preestablecido de desviación angular del ojo del usuario durante dicho evento. 6. Method according to claim 5, wherein a saccadic event, further comprises determining whether it corresponds to an environmental saccadic movement or a focal saccadic movement, according to a second preset threshold of angular deviation of the user's eye during said event.
7. Método de acuerdo a cualquiera de las reivindicaciones anteriores, donde la al menos una variable biométrica comprende una información cuantificable de los eventos identificados a seleccionar entre: cantidad de eventos identificados, duración promedio de los eventos identificados, frecuencia de cada evento identificado en un tiempo preestablecido, secuencia de los eventos identificados y número de visitas a una misma área predefinida. 7. Method according to any of the preceding claims, wherein the at least one biometric variable comprises quantifiable information on the identified events to be selected from: number of identified events, average duration of the identified events, frequency of each identified event in a preset time, sequence of events identified and number of visits to the same predefined area.
8. Método de acuerdo a cualquiera de las reivindicaciones anteriores que además comprende definir al menos un área de interés en el billete y asociar la variable biométrica adquirida del usuario a dicha área de interés. 8. Method according to any of the preceding claims, which further comprises defining at least one area of interest in the bill and associating the biometric variable acquired from the user to said area of interest.
9. Método de acuerdo a la reivindicación 8, donde la información visual comprende un elemento de seguridad dispuesto en el billete, que además comprende definir un área de interés mayor o igual que el área del billete ocupada por el elemento de seguridad y donde el área de interés incluye el área del billete ocupada por dicho elemento de seguridad. Method according to claim 8, where the visual information comprises a security element arranged on the bill, which further comprises defining an area of interest greater than or equal to the area of the bill occupied by the security element and where the area of interest includes the area of the note occupied by said security element.
10. Método de acuerdo a cualquiera de las reivindicaciones anteriores, donde analizar las variables biométricas, de acuerdo a resultados conocidos previamente, además comprende entrenar un sistema de aprendizaje supervisado del módulo de proceso de acuerdo a los siguientes pasos: 10. Method according to any of the preceding claims, where analyzing the biometric variables, according to previously known results, also comprises training a supervised learning system of the process module according to the following steps:
- repetir los pasos a)-c) de la reivindicación 1 para una pluralidad de billetes diferentes y usuarios diferentes; - repeating steps a) -c) of claim 1 for a plurality of different banknotes and different users;
- agrupar, para cada billete, los eventos identificados de cada usuario, de acuerdo a un número previamente establecido de grupos; - asignar a cada billete un valor inicial del indicador neurométrico, donde dicho valor está basado en un análisis de los grupos de eventos identificados por un usuario experto. - grouping, for each ticket, the identified events of each user, according to a previously established number of groups; - assigning to each ticket an initial value of the neurometric indicator, where said value is based on an analysis of the groups of events identified by an expert user.
11. Método de acuerdo a la reivindicación 10, donde analizar las variables biométricas mediante el sistema de aprendizaje supervisado además comprende los pasos de: 11. Method according to claim 10, wherein analyzing the biometric variables through the supervised learning system also comprises the steps of:
- proporcionar el valor inicial del indicador neurométrico, asignado a cada billete, en una entrada del sistema de aprendizaje; - providing the initial value of the neurometric indicator, assigned to each ticket, in an input of the learning system;
- aplicar un modelo predictivo, por el sistema de aprendizaje supervisado, sobre las variables biométricas obtenidas por el módulo de proceso y el valor inicial asignado; y - apply a predictive model, by the supervised learning system, on the biometric variables obtained by the process module and the assigned initial value; and
- validar, mediante un proceso de validación cruzada, con un número de iteraciones determinado previamente, el modelo predictivo. - validate, through a cross-validation process, with a previously determined number of iterations, the predictive model.
12. Método de acuerdo a cualquiera de las reivindicaciones anteriores donde los indicadores neurométricos representan uno o más de los siguientes procesos cognitivos cerebrales del usuario: interés visual, atención, emociones evocadas, motivación, carga mental, estrés y nivel de excitación. 12. Method according to any of the preceding claims, wherein the neurometric indicators represent one or more of the following cognitive brain processes of the user: visual interest, attention, evoked emotions, motivation, mental load, stress and level of arousal.
13. Método de acuerdo a cualquiera de las reivindicaciones anteriores donde adquirir la señal biométrica del usuario además comprende una interacción física del usuario con el billete, donde dicha interacción física proporciona al usuario una información táctil y sonora del billete. Method according to any of the preceding claims, where acquiring the biometric signal of the user also comprises a physical interaction of the user with the ticket, where said physical interaction provides the user with tactile and audible information about the ticket.
14.- Sistema para clasificar billetes basado en neuroanálisis, caracterizado por que comprende: 14.- System for classifying banknotes based on neuroanalysis, characterized in that it comprises:
- un módulo de entrada (2) que comprende al menos un sensor, configurado para adquirir una señal biométrica del usuario, como respuesta a una información visual del billete proporcionada a dicho usuario; - an input module (2) comprising at least one sensor, configured to acquire a biometric signal from the user, in response to visual information of the ticket provided to said user;
- un módulo de proceso (3), configurado para segmentar la señal biométrica en períodos de tiempo predeterminados; comparar cada uno de los segmentos con unos patrones preestablecidos; identificar ciertos eventos como resultado de la comparación de cada uno de los segmentos con los patrones preestablecidos; obtener al menos una variable biométrica basada en los eventos identificados; analizar las variables biométricas de acuerdo a resultados conocidos previamente almacenados en una base datos; y establecer un indicador neurométrico en función del análisis; y - a processing module (3), configured to segment the biometric signal in predetermined periods of time; compare each of the segments with pre-established patterns; identify certain events as a result of comparing each of the segments with the pre-established patterns; obtain at least one biometric variable based on the identified events; analyze biometric variables according to known results previously stored in a database; and establish a neurometric indicator based on the analysis; and
- un módulo de salida (5) configurado para clasificar el billete, de acuerdo al indicador neurométrico. - an output module (5) configured to classify the bill, according to the neurometric indicator.
15. Sistema de acuerdo a la reivindicación 14, donde el módulo de salida comprende unos medios de visualización, configurados para representar visualmente los indicadores neurométricos del billete y una métrica final de clasificación, basada en los indicadores neurométricos resultado del neuroanálisis de cada billete. System according to claim 14, wherein the output module comprises display means, configured to visually represent the neurometric indicators of the bill and a final classification metric, based on the neurometric indicators resulting from the neuroanalysis of each bill.
PCT/ES2020/070383 2019-06-26 2020-06-11 Method and system for classifying banknotes based on neuroanalysis WO2020260735A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
ES201930590A ES2801024A1 (en) 2019-06-26 2019-06-26 BANKNOTE CLASSIFICATION METHOD AND SYSTEM BASED ON NEUROANALYSIS (Machine-translation by Google Translate, not legally binding)
ESP201930590 2019-06-26

Publications (1)

Publication Number Publication Date
WO2020260735A1 true WO2020260735A1 (en) 2020-12-30

Family

ID=71138529

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/ES2020/070383 WO2020260735A1 (en) 2019-06-26 2020-06-11 Method and system for classifying banknotes based on neuroanalysis

Country Status (4)

Country Link
EP (1) EP3757950B1 (en)
DK (1) DK3757950T3 (en)
ES (2) ES2801024A1 (en)
WO (1) WO2020260735A1 (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070066916A1 (en) * 2005-09-16 2007-03-22 Imotions Emotion Technology Aps System and method for determining human emotion by analyzing eye properties
US20080065468A1 (en) * 2006-09-07 2008-03-13 Charles John Berg Methods for Measuring Emotive Response and Selection Preference
US20170083927A1 (en) * 2015-09-22 2017-03-23 Health Care Direct, Inc. d/b/a HCD Research Systems and Methods for Assessing the Marketability of a Product

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8684742B2 (en) * 2010-04-19 2014-04-01 Innerscope Research, Inc. Short imagery task (SIT) research method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070066916A1 (en) * 2005-09-16 2007-03-22 Imotions Emotion Technology Aps System and method for determining human emotion by analyzing eye properties
US20080065468A1 (en) * 2006-09-07 2008-03-13 Charles John Berg Methods for Measuring Emotive Response and Selection Preference
US20170083927A1 (en) * 2015-09-22 2017-03-23 Health Care Direct, Inc. d/b/a HCD Research Systems and Methods for Assessing the Marketability of a Product

Also Published As

Publication number Publication date
EP3757950A1 (en) 2020-12-30
ES2963861T3 (en) 2024-04-02
DK3757950T3 (en) 2023-11-06
EP3757950B1 (en) 2023-08-02
ES2801024A1 (en) 2021-01-07

Similar Documents

Publication Publication Date Title
Fridman et al. Cognitive load estimation in the wild
Palmer et al. Face pareidolia recruits mechanisms for detecting human social attention
Wang et al. Atypical visual saliency in autism spectrum disorder quantified through model-based eye tracking
CN105631439B (en) Face image processing process and device
US20160098592A1 (en) System and method for detecting invisible human emotion
Wang et al. An EEG-based brain–computer interface for dual task driving detection
Parks et al. Augmented saliency model using automatic 3d head pose detection and learned gaze following in natural scenes
Abouelenien et al. Human acute stress detection via integration of physiological signals and thermal imaging
EP2829221A1 (en) Asperger&#39;s diagnosis assistance method and system, and asperger&#39;s diagnosis assistance device
US20100039618A1 (en) System and method for identifying the existence and position of text in visual media content and for determining a subject&#39;s interactions with the text
US9386949B2 (en) Device to determine visuo-spatial ability
Hasan et al. Pain level detection from facial image captured by smartphone
Su et al. Detection of hypomimia in patients with Parkinson’s disease via smile videos
Cruz-Garza et al. EEG-based investigation of the impact of classroom design on cognitive performance of students
Hu et al. First impressions: Integrating faces and bodies in personality trait perception
Jin et al. Differences in brain signal complexity between experts and novices when solving conceptual science problem: a functional near-infrared spectroscopy study
ES2963861T3 (en) Method and system to select parameters of a design or security element of banknotes based on neuroanalysis
Menzel et al. Low-level image properties in facial expressions
ES1299461U (en) BANKNOTE CLASSIFICATION SYSTEM BASED ON NEUROANALYSIS (Machine-translation by Google Translate, not legally binding)
Van de Nieuwenhuijzen et al. Spatiotemporal dynamics of cortical representations during and after stimulus presentation
CN112255921B (en) AR glasses intelligent control system and method
Keskinarkaus et al. Pain fingerprinting using multimodal sensing: pilot study
de J Lozoya-Santos et al. Current and Future Biometrics: Technology and Applications
TW201839635A (en) Emotion detection system and method
König et al. Modeling visual exploration in rhesus macaques with bottom-up salience and oculomotor statistics

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20831618

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20831618

Country of ref document: EP

Kind code of ref document: A1