CN106974648A - The electric allowance recognition methods of brain based on time domain and domain space and device - Google Patents
The electric allowance recognition methods of brain based on time domain and domain space and device Download PDFInfo
- Publication number
- CN106974648A CN106974648A CN201710187188.9A CN201710187188A CN106974648A CN 106974648 A CN106974648 A CN 106974648A CN 201710187188 A CN201710187188 A CN 201710187188A CN 106974648 A CN106974648 A CN 106974648A
- Authority
- CN
- China
- Prior art keywords
- brain
- characteristic quantity
- characteristic
- electric
- space
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/375—Electroencephalography [EEG] using biofeedback
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4848—Monitoring or testing the effects of treatment, e.g. of medication
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of electric allowance recognition methods of brain based on time domain and domain space and device, methods described includes:Pending brain electric array signal is filtered, signal wave is extracted;Each signal wave is cut into slices, calculate the maximum and minimum value of projection of the signal wave in the y-axis of corresponding section, according to maximum and the interval of minimum value at least two equal lengths of formation, and according to the quantity positioned at each interval projection, the grid projection degree of variation of signal wave is obtained, the characteristic quantity in time domain space is obtained;The energy of signal wave is calculated, according to the frequency range of each brain wave and the energy of signal wave, the energy ratio between any two signal wave is calculated, obtains the characteristic quantity in domain space;Characteristic quantity to the characteristic quantity in time domain space and in domain space carries out Classification and Identification, obtains the electric allowance of brain.The present invention can extract the different dimensions of each brain wave and the characteristic quantity in space, so as to realize the electric allowance identification of accurate brain.
Description
Technical field
The present invention relates to relaxation treatment field, more particularly to a kind of electric allowance identification of brain based on time domain and domain space
Method and device.
Background technology
It, using one of most wide technology, is set up and sends out on the basis of Experiment of Psychology that relaxation training, which is in behavior therapy,
Consulting and treatment method that exhibition is got up, it mitigates climacteric in treatment Anxiety depression, nervous headache, insomnia, high blood pressure
Preferable curative effect is achieved in terms of syndrome and transformation bad behavior pattern.
Existing relaxation training mainly has recording to instruct, verbal assistance and biofeedback are instructed.Wherein, recording guidance method
Ossify, do not change, it is impossible to according to the state change content of trainee;Verbal assistance then requires the object requirement to verbal assistance
It is very high, and limited by time, place;Biofeedback instructs that based on brain electricity feedback, the advantage of first two mode can be combined,
Thus receive significant attention.
The allowance that biofeedback is instructed to need to recognize user is carried out, and calculates allowance firstly the need of the brain electricity from user
The brain wave (including Delta, Theta, Alpha, Beta, Gamma ripple) of each frequency range is extracted in signal, then extracts each brain electricity
These features are input to grader and carry out Classification and Identification by the feature of ripple.
Existing feature extracting method typically can only be from the feature of single angle extraction brain wave, and evaluation method is single, no
It can guarantee that the accuracy of classification results.And calculating and the complex disposal process of existing feature extraction algorithm, on the one hand, increase
Requirement to hardware, it is on the other hand, complicated due to calculating, classification results can not be also obtained in time, and then be have impact on to loosen and controlled
The effect for the treatment of.
The content of the invention
In view of the above-mentioned problems, knowing it is an object of the invention to provide a kind of electric allowance of brain based on time domain and domain space
Other method and device, can comprehensively extract the feature of each brain wave.
The invention provides a kind of electric allowance recognition methods of brain based on time domain and domain space, comprise the following steps:
The pending brain electric array signal received is filtered, the signal wave corresponding to each brain wave is extracted;
Each described signal wave is cut into slices, each signal wave is calculated in the y-axis of corresponding each section
The maximum and minimum value of projection, according to maximum and the interval of minimum value at least two equal lengths of formation, and according to positioned at each
The quantity of individual interval projection, obtains the grid projection degree of variation of each signal wave, obtains the pending brain electric array signal
In the characteristic quantity of time domain space;
The energy of the signal wave corresponding to each brain wave is calculated, according to the frequency range of each brain wave and corresponding letter
The energy of number ripple, calculates the energy ratio between any two signal wave, obtains the pending brain electric array signal in frequency domain
The characteristic quantity in space;
The pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space are divided
Class is recognized, obtains the electric allowance of brain.
Preferably, it is described that each described signal wave is cut into slices, calculate each signal wave and each cut in corresponding
The maximum and minimum value of projection in the y-axis of piece, according to maximum and the interval of minimum value at least two equal lengths of formation, and
According to the quantity positioned at each interval projection, the grid projection degree of variation of each signal wave is obtained, the pending brain is obtained
Electric array signal is specifically included in the characteristic quantity of time domain space:
Each signal wave is cut at least two sections with same time interval;
Calculate projection of each signal wave in the y-axis of corresponding each section;
The maximum and minimum value of all projections are counted, and at least two equal lengths are formed according to maximum and minimum value
It is interval;
Statistics is located at the quantity of each interval projection, and calculates the standard deviation of the quantity of each interval projection, obtains
The grid projection degree of variation of each signal wave, obtains characteristic quantity of the pending brain electric array signal in time domain space.
Preferably, it is described to the pending characteristic quantity of the brain electric array signal in time domain space and the spy in domain space
The amount of levying carries out Classification and Identification, obtains the electric allowance of brain and specifically includes:
The characteristic quantity is classified based on training in advance good SVMs, identification is obtained and the pending brain
The electric allowance of the corresponding brain of electric array signal.
Preferably, it is described according to the pending brain electric array signal in the characteristic quantity of time domain space and in domain space
Characteristic quantity carry out Classification and Identification, obtain also including before the electric allowance of brain:
Based on PCA to the pending brain electric array signal in the characteristic quantity of time domain space and in frequency domain sky
Between characteristic quantity carry out dimension-reduction treatment, obtain dimensionality reduction after characteristic quantity.
Preferably, it is described based on PCA to the pending brain electric array signal time domain space characteristic quantity
And dimension-reduction treatment is carried out in the characteristic quantity of domain space, obtain the characteristic quantity after dimensionality reduction and specifically include:
The pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space are set to
Characteristic quantity in input sample space, and data normalization processing is carried out to the input sample space;
The input sample space after being handled according to data normalization obtains covariance matrix;
Calculate the characteristic root and characteristic vector corresponding with each characteristic root of the covariance matrix;Wherein, the feature
The quantity of root is p, and described p characteristic root is in magnitude order;
Obtain in p described characteristic root, contribution rate sum is more than the preceding m characteristic root of predetermined threshold;Wherein, Mei Gete
The contribution rate for levying root is equal to the value sum of the value of the characteristic root divided by p characteristic root of whole;
According to characteristic vector corresponding with described preceding m characteristic root and the input sample space, obtain principal component and obtain
Sub-matrix;Wherein, the characteristic quantity in the principal component scores matrix is the characteristic quantity after the dimensionality reduction.
Present invention also offers a kind of electric allowance identifying device of brain based on time domain and domain space, including:
Signal extraction unit, for being filtered to the pending brain electric array signal received, is extracted corresponding to each
The signal wave of individual brain wave;
Temporal signatures extraction unit, for being cut into slices to each described signal wave, calculates each signal wave right with it
The maximum and minimum value of projection in the y-axis for each section answered, it is isometric according to maximum and minimum value formation at least two
The interval of degree, and according to the quantity positioned at each interval projection, the grid projection degree of variation of each signal wave is obtained, obtain institute
State characteristic quantity of the pending brain electric array signal in time domain space;
Frequency domain character extraction unit, the energy for calculating the signal wave corresponding to each brain wave, according to each brain electricity
The energy of the frequency range of ripple and corresponding signal wave, calculate any two signal wave between energy ratio, obtain described in treat
Handle characteristic quantity of the brain electric array signal in domain space;
Brain electricity allowance recognition unit, for the pending brain electric array signal the characteristic quantity of time domain space and
The characteristic quantity of domain space carries out Classification and Identification, obtains the electric allowance of brain.
Preferably, the temporal signatures extraction unit is specifically included:
Section module, for each signal wave to be cut into at least two sections with same time interval;
Computing module is projected, for calculating projection of each signal wave in the y-axis of corresponding each section;
Interval division module, maximum and minimum value for counting all projections, and according to maximum and minimum value shape
Into the interval of at least two equal lengths;
Grid projection degree of variation computing module, for counting the quantity positioned at each interval projection, and calculates each area
Between projection quantity standard deviation, obtain the grid projection degree of variation of each signal wave, obtain the pending brain electric array
Characteristic quantity of the signal in time domain space.
Preferably, the electric allowance recognition unit of the brain, specifically for based on the good SVMs of training in advance to institute
State characteristic quantity to be classified, identification obtains the electric allowance of brain corresponding with the pending brain electric array signal.
Preferably, in addition to:
Feature Dimension Reduction unit, for based on PCA to the pending brain electric array signal in time domain space
Characteristic quantity and the characteristic quantity after the characteristic quantity of domain space carries out dimension-reduction treatment, acquisition dimensionality reduction.
Preferably, the Feature Dimension Reduction unit is specifically included:
Standardization module, for by the pending brain electric array signal in the characteristic quantity of time domain space and in frequency domain
The characteristic quantity in space is set to the characteristic quantity in input sample space, and the input sample space is carried out at data normalization
Reason;
Covariance matrix computing module, for being handled according to data normalization after the input sample space obtain association side
Poor matrix;
Feature calculation module, for calculate the characteristic root and feature corresponding with each characteristic root of the covariance matrix to
Amount;Wherein, the quantity of the characteristic root is p, and described p characteristic root is in magnitude order;
Screening module, for obtaining in p described characteristic root, contribution rate sum is more than the preceding m feature of predetermined threshold
Root;Wherein, the contribution rate of each characteristic root is equal to the value sum of the value of the characteristic root divided by p characteristic root of whole;
Dimensionality reduction characteristic quantity obtains module, for according to characteristic vector corresponding with described preceding m characteristic root and described defeated
Enter sample space, obtain principal component scores matrix;Wherein, the characteristic quantity in the principal component scores matrix is after the dimensionality reduction
Characteristic quantity.
The electric allowance recognition methods of brain based on time domain and domain space provided in an embodiment of the present invention and device, while from
The characteristic quantity of time domain space, two angle extraction brain electric array sequence numbers of domain space, and the characteristic quantity progress obtained based on extraction
Classification and Identification obtains the electric allowance of final brain.It is more various to the evaluation method of signal compared to the feature extraction of single angle
Change, can more fully embody the characteristic of signal, it is to avoid the feature that the feature extraction of single angle is easily caused is excessively unilateral
Problem and the problem of influence final accuracy of identification.The present invention can greatly improve precision and the degree of accuracy of identification classification, to loosen
Treatment provides accurate foundation.
Brief description of the drawings
In order to illustrate more clearly of technical scheme, the required accompanying drawing used in embodiment will be made below
Simply introduce, it should be apparent that, drawings in the following description are only some embodiments of the present invention, general for this area
For logical technical staff, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is that the flow of the electric allowance recognition methods of the brain provided in an embodiment of the present invention based on time domain and domain space is shown
It is intended to.
Fig. 2 is the schematic diagram of SVM optimal hyperlane classification.
Fig. 3 is the schematic diagram of SVM High Dimensional Mappings.
Fig. 4 is that the structure of the electric allowance identifying device of the brain provided in an embodiment of the present invention based on time domain and domain space is shown
It is intended to.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Referring to Fig. 1, the embodiments of the invention provide a kind of electric allowance identification side of brain based on time domain and domain space
Method, it may include following steps:
S101, is filtered to the pending brain electric array signal received, extracts the letter corresponding to each brain wave
Number ripple.
In embodiments of the present invention, each described brain wave may include Delta ripples, Theta ripples, Alpha ripples, Beta
Ripple, Gamma ripples.Wherein, usually, the frequency range of Delta ripples is 0.5~3Hz, the frequency ranges of Theta ripples is 3~7Hz,
The frequency range of Alpha ripples be 8~13Hz, the frequency range of Beta ripples be 14~17Hz, the frequency range of Gamma ripples be 34~
50Hz。
Wherein, Delta ripples:Deep sleep E.E.G state.
It is deep sleep, automatism when the brain frequency of people is in Delta ripples.People sleep quality quality with
Delta ripples have very direct relation.The sleep of Delta ripples is a kind of very deep sleep state, if when tossing about in bed from
Oneself calls out the approximate wavy states of Delta, just can soon break away from insomnia and enter deep sleep.
Theta ripples:Depth is loosened, the subconsciousness state of no pressure.
When the brain frequency of people is in Theta ripples, the consciousness of people is interrupted, and body is deep to be loosened, for extraneous information
Present height by imply state, i.e., by hypnosis.Theta ripples are helped for triggering deep memory, reinforcing long-term memory etc.
Greatly, so Theta ripples are referred to as " gate for leading to memory and study ".
Alpha ripples:The optimal E.E.G state of study and thinking.
When the brain frequency of people is in Alpha ripples, the Consciousness of people, but body is what is loosened, and it provides consciousness
With subconscious " bridge ".In this state, body and mind energy charge is minimum, and the energy that relative brain is obtained is higher, running
Will quicker, smooth, acumen.Alpha ripples are considered as the optimal E.E.G state of people's study and thinking.
Beta ripples:E.E.G state when anxiety, pressure, brainfag.
When people regain consciousness, most of the time brain frequency is in the wavy states of Beta.With the increase of Beta ripples, body is gradually
In tense situation, thus vivo immuning system ability is reduced, now the energy expenditure aggravation of people, easily tired, if insufficient
Rest, easily accumulates pressure.Appropriate Beta ripples are lifted to notice and the development of cognitive behavior has positive role.
In the present embodiment, it is contemplated that also include various artefact sequence signals, such as tongue in pending brain electric array signal
Electric artefact, perspiration artefact, eye electricity artefact, the interference such as pulse artefact and Muscle artifacts.Wherein, with the electric artefact of eye and Muscle artifacts
The problem of being difficult to remove, this is higher mainly due to the amplitude of its artefact signal, is several times even tens times of EEG signals, and
And have aliasing in frequency domain with EEG signals.
In embodiments of the present invention, can be according to the frequency of each brain wave after the pending brain electric array signal is obtained
Rate scope is electric from the pending brain by filtering (such as Kalman filtering), wavelet transformation or autoregression model extraction algorithm
The signal wave corresponding to each brain wave is extracted in sequence signal.Wherein, it can only be extracted and obtained pair with algorithm during extraction
It should can also be extracted simultaneously by polyalgorithm, then obtained knot is extracted to algorithms of different in the signal wave of each brain wave
Fruit is weighted summation, obtains final signal wave.The extraction of signal wave is carried out using multiple extraction algorithms, single calculation can be avoided
The problem of method extracts the bigger error occurred or not high stability.
S102, cuts into slices to each described signal wave, calculates y-axis of each signal wave in corresponding each section
On projection maximum and minimum value, according to maximum and the interval of minimum value at least two equal lengths of formation, and according to position
In the quantity of each interval projection, the grid projection degree of variation of each signal wave is obtained, the pending brain electric array is obtained
Characteristic quantity of the signal in time domain space.
In embodiments of the present invention, after signal wave corresponding with each brain wave is obtained, you can extract it empty in time domain
Between feature.
In embodiments of the present invention, the grid projection variation of each signal wave can be extracted by grid projection degree of variation algorithm
Spend to obtain the temporal signatures of each signal wave.
Specifically:
First, each signal wave is divided at least two sections by same time interval.
Wherein, each section is exactly a grizzly bar, and time interval is exactly grill width.
Secondly, covering of each signal wave (Delta, Theta, Alpha, Beta, Gamma ripple) in each grizzly bar is calculated
Scope, i.e., the projection shadow in grizzly bar y-axis.
Then, all projection shadow max min is counted, between a minimum value and a maximum value, is divided into some
The interval histnum of individual equal length.
For example, maximum is a, minimum value is for b, it is necessary to be divided into N number of interval, then each interval length is (a-b)/N.
Finally, statistics falls the quantity shadow_hist projected in each interval histnum as shown in formula 1,2, calculates each
The quantity shadow_hist of interval projection standard deviation shadow_stdhist, that is, the grid projection degree of variation needed.
In embodiments of the present invention, calculate respectively and obtain each signal wave (Delta, Theta, Alpha, Beta, Gamma
Ripple) grid projection degree of variation shadow_stdhistP1~shadow_stdhistP5, and can after the same method can be with
The grid projection degree of variation shadow_stdhistEEG of pending brain electric array signal is calculated, that is, has obtained the electric sequence of pending brain
Characteristic quantity of the column signal in time domain space.Wherein, grid projection degree of variation embodies the disperse discrete degree of waveform.
S103, calculates the energy of the signal wave corresponding to each brain wave, according to the frequency range of each brain wave and right
The energy for the signal wave answered, calculates the energy ratio between any two signal wave, obtains the pending brain electric array signal
In the characteristic quantity of domain space.
In embodiments of the present invention, the frequency domain that the signal wave of each brain wave can be extracted by energy density ratio algorithm is special
Levy, obtain characteristic quantity of the pending brain electric array signal in domain space.
Specifically:
S1031, calculates the energy of signal wave corresponding with each brain wave.
Wherein, the energy function formula of each signal wave is as follows:
The π f (4) of ω=2
S1032, according to the frequency range of each brain wave and the energy of corresponding signal wave, calculates any two signal wave
Between energy ratio, obtain the characteristic quantity of the pending brain electric array signal in domain space.
Exemplified by calculating Alpha and Delta energy ratio, as shown in Equation 5.
In embodiments of the present invention, by that analogy, by calculating the energy ratio between signal wave two-by-two, just obtain described
Characteristic quantity of the pending brain electric array signal in domain space.
S104, enters to the pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space
Row Classification and Identification, obtains the electric allowance of brain.
In embodiments of the present invention, the pending brain electric array signal is being obtained in the characteristic quantity of time domain space and in frequency
After the characteristic quantity of domain space, it is entered into the grader pre-set, it is possible to obtain the electric allowance of current brain.
In embodiments of the present invention, after the electric allowance of brain is obtained, it is possible to carry out relaxation treatment according to the electric allowance of brain,
It can such as be carried out loosening the selection of guiding content, mark according to the electric allowance of brain and played, can accurately choose most suitable use
Guiding content is loosened at family, and earphone of arranging in pairs or groups plays to user;Loosen guiding content of the simultaneous based on allowance plays sound
Amount modulation, helps user to loosen body and mind, alleviates anxiety-depression, cultivates one's taste, improves individual character weakness, eliminates Psychology and behavior barrier
Hinder, keep psychology and Body health.
Preferably, the step S104 is specifically included:
The characteristic quantity is classified based on training in advance good SVMs, identification is obtained and the pending brain
The electric allowance of the corresponding brain of electric array signal.
In embodiments of the present invention, after the characteristic quantity of pending brain electric array signal is obtained, be entered into support to
Amount machine (Support Vector Machine, SVM), classifies to the characteristic quantity, and identification is obtained and the pending brain
The electric allowance of the corresponding brain of electric array signal.
Specifically, the basic thought of SVMs is to construct optimal hyperlane in sample space or feature space,
So that the distance between hyperplane and inhomogeneity sample set maximum, so as to reach the generalization ability of maximum, as shown in Figure 2.
SVM principle is explained below.
First, for given two classification samples to { (xi, yi), xi ∈ RN, yi=± 1 } (five classification samples by that analogy
To for { (xi, yi), xi ∈ RN, yi=1,2,3,4,5 }), xi is training sample, and x is sample to be adjudicated.Training sample set is line
When property is inseparable, non-negative slack variable α i need to be introduced, i=1,2 ..., l;The optimization problem of Optimal Separating Hyperplane is converted into public affairs
Shown in formula 6.Wherein, 2/ | | w | | presentation class interval, make class interval maximum be equivalent to make | | w | |2It is minimum.Make | | w | |2It is minimum
Classification just turn into optimal classification surface.C is error punishment parameter, is one of most important adjustable parameter in SVM.
Secondly, radial direction base (RadialBasisFunctionRBF) kernel function is chosen, as shown in Equation 7.Wherein γ is RBF
The width of kernel function, is another important adjustable parameter in SVM.
Kx,xi=exp (- γ * | | x-xi||2) (7)
Finally, using kernel function technology, by the nonlinear problem in the input space, Function Mapping to high dimensional feature sky is passed through
Between in, construct linear discriminant function in higher dimensional space, solve optimal hyperlane so that between hyperplane and inhomogeneity sample set
Distance it is maximum, so as to reach the generalization ability of maximum, as shown in Figure 3.
In embodiments of the present invention, constructed after SVM, it is possible to be trained, specifically, the feature that extraction is obtained
Amount reads " allowance " that equipment synchronous acquisition obtains and is used as goldstandard, that is, SVM as training SVM input sample X using refreshing
Output Y.(X, Y) collectively constitutes SVM training sample pair, carries out SVM training.
After SVM is trained, it is possible to classified using the SVM, so as to realize the Classification and Identification of allowance.
It should be noted that SVM classification performance is influenceed by factors, wherein error punishment parameter C and RBF core letters
Several two factors of width gamma are the most key.C is error punishment parameter, is one of most important adjustable parameter in SVM, is represented pair
Mistake point sample proportion and algorithm complex are compromise, i.e., it is determined that proper subspace in adjust Learning machine fiducial range and experience
Risk ratio, makes the Generalization Ability of Learning machine best.The selection of kernel function and parameter also directly influences svm classifier quality.
When specifically used, parameter optimization can be carried out to the two parameters, such as be searched by combination cross-validation method with grid
Rope algorithm, calculate with reference to leaving-one method and genetic algorithm, with reference to cross-validation method and genetic algorithm, with reference to cross-validation method and population
Method carries out parameter optimization, and these technical schemes are within protection scope of the present invention, and the present invention will not be described here.
The electric allowance recognition methods of brain based on time domain and domain space provided in an embodiment of the present invention, while empty from time domain
Between, the feature of the signal wave of the angle extraction of domain space two each brain wave, obtain the feature of pending brain electric array sequence number
The characteristic quantity measured and obtained based on extraction is carried out Classification and Identification and obtains the electric allowance of final brain.Compared to the feature of single angle
Extract, it is more diversified to the evaluation method of signal, it can more fully embody the characteristic of signal, it is to avoid the feature of single angle is carried
The problem of feature being easily caused of trying to please is excessively unilateral and the problem of influence final accuracy of identification.The present invention can greatly improve identification
The precision of classification and the degree of accuracy, accurate foundation is provided for relaxation treatment.In addition, feature extraction side provided in an embodiment of the present invention
Method calculates simple, quick, low to hardware requirement, thus the timely output category result of energy, is easy to real-time relaxation treatment.
Preferably, before step S104, it can also include:
S105, based on PCA to the pending brain electric array signal in the characteristic quantity of time domain space and in frequency
The characteristic quantity of domain space carries out dimension-reduction treatment, obtains the characteristic quantity after dimensionality reduction.
Specifically:
S1051, by the pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space
The characteristic quantity in input sample space is set to, and data normalization processing is carried out to the input sample space.
Specifically, by pending brain electric array signal in time domain space characteristic quantity and the characteristic quantity in domain space are set
For the element in input sample space X.Data normalization processing is carried out to sample space X is specially:
Wherein:
Wherein, X 'ijIt is the new data after standardization;Mj、SjRespectively represent a certain row of initial data arithmetic mean of instantaneous value and
Standard (inclined) is poor.
S1052, the input sample space after being handled according to data normalization obtains covariance matrix.
Wherein, covariance matrix D=XTX, i.e.,:
Wherein:
S1053, calculates the characteristic root and characteristic vector corresponding with each characteristic root of the covariance matrix;Wherein, institute
It is p to state the quantity of characteristic root, and described p characteristic root is in magnitude order.
Wherein, DP=P λ (13)
When only considering j-th of characteristic value, there is DPj=Pjλj, that is, solve | D- λjI |=0.Each λ is solved successively, and is made
Its order arrangement, i.e. λ by size1≥λ2≥…,≥λp≥0;Then each characteristic value corresponding characteristic vector P, Jin Erte can be obtained
Levy equation solution completion.
S1054, is obtained in p described characteristic root, and contribution rate sum is more than the preceding m characteristic root of predetermined threshold.
Wherein, the contribution rate of each characteristic root is equal to the value sum of the value of the characteristic root divided by p characteristic root of whole.
First, calculate the contribution rate of single principal component and added up, the number of principal component is determined according to contribution rate of accumulative total
M, so that it is determined that the principal component of required selection.The calculation formula of contribution rate is as described in formula 14.Contribution rate of accumulative total is preceding m tribute
Offer rate accumulation and, as shown in Equation 15.The threshold value Dmax is typically taken between 85%~95%.According in previous step
Knowable to characteristic root sequence, λ1≥λ2≥…,≥λp>=0, from front to back (being also from big to small) characteristic root is added up successively,
Work as contribution rate of accumulative totalDuring more than Dmax, stop calculating, now the characteristic root λ of cumulative calculation number is m, then only
Need m principal component before choosing.
S1055, according to characteristic vector corresponding with described preceding m characteristic root and the input sample space, is led
Component score matrix.
Wherein, the characteristic quantity in the principal component scores matrix is the characteristic quantity after the dimensionality reduction.
Wherein, the principal component scores matrix
Wherein, each element in principal component scores matrix T is the characteristic quantity after dimensionality reduction.
It should be noted that in embodiments of the present invention, the load of principal component can be also calculated, wherein, the principal component is carried
Lotus mainly reflects the correlation degree of principal component scores and former variable xj, and calculation formula is:
After the load for obtaining each principal component, it is possible to know that each principal component of selection distinguishes corresponding primitive character, if any need
Will, it can be gone back according to the conversion of the dimension of primitive character.
In embodiments of the present invention, exist filtering out the pending brain electric array signal that is obtained using PCA
In time domain space and the characteristic quantity of domain space after characteristic quantity more important, you can obtain the pending brain electric array after dimensionality reduction
The characteristic quantity of signal.By being carried out to pending brain electric array signal in time domain space and the characteristic quantity of domain space at dimensionality reduction
Reason so that the follow-up data amount of calculation carried out when the electric allowance of brain is recognized reduces, so that the speed of the electric allowance identification of brain is improved,
Realize the Real time identification of the electric allowance of brain.
Referring to Fig. 4, the present invention also provides a kind of brain based on time domain and domain space electric allowance identifying device 100,
Including:
Signal extraction unit 10, for being filtered to the pending brain electric array signal received, extracts and corresponds to
The signal wave of each brain wave;
Temporal signatures extraction unit 20, for being cut into slices to each described signal wave, calculate each signal wave with its
The maximum and minimum value of projection in the corresponding y-axis each cut into slices, according to maximum and minimum value formation at least two etc.
The interval of length, and according to the quantity positioned at each interval projection, the grid projection degree of variation of each signal wave is obtained, obtain
Characteristic quantity of the pending brain electric array signal in time domain space;
Frequency domain character extraction unit 30, the energy for calculating the signal wave corresponding to each brain wave, according to each brain
The energy of the frequency range of electric wave and corresponding signal wave, calculates the energy ratio between any two signal wave, obtains described
Characteristic quantity of the pending brain electric array signal in domain space;
Brain electricity allowance recognition unit 40, for the pending brain electric array signal in the characteristic quantity of time domain space and
Classification and Identification is carried out in the characteristic quantity of domain space, the electric allowance of brain is obtained.
It is highly preferred that the temporal signatures extraction unit 20 is specifically included:
Section module, for each signal wave to be cut into at least two sections with same time interval;
Computing module is projected, for calculating projection of each signal wave in the y-axis of corresponding each section;
Interval division module, maximum and minimum value for counting all projections, and according to maximum and minimum value shape
Into the interval of at least two equal lengths;
Grid projection degree of variation computing module, for counting the quantity positioned at each interval projection, and calculates each area
Between projection quantity standard deviation, obtain the grid projection degree of variation of each signal wave, obtain the pending brain electric array
Characteristic quantity of the signal in time domain space.
It is highly preferred that the electric allowance recognition unit 40 of the brain, specifically for based on the good SVMs of training in advance
The characteristic quantity is classified, identification obtains the electric allowance of brain corresponding with the pending brain electric array signal.
It is highly preferred that the electric allowance identifying device of the brain based on time domain and frequency-region signal feature, in addition to:
Feature Dimension Reduction unit, for based on PCA to the pending brain electric array signal in time domain space
Characteristic quantity and the characteristic quantity after the characteristic quantity of domain space carries out dimension-reduction treatment, acquisition dimensionality reduction.
It is highly preferred that the Feature Dimension Reduction unit is specifically included:
Standardization module, for by the pending brain electric array signal in the characteristic quantity of time domain space and in frequency domain
The characteristic quantity in space is set to the characteristic quantity in input sample space, and the input sample space is carried out at data normalization
Reason;
Covariance matrix computing module, for being handled according to data normalization after the input sample space obtain association side
Poor matrix;
Feature calculation module, for calculate the characteristic root and feature corresponding with each characteristic root of the covariance matrix to
Amount;Wherein, the quantity of the characteristic root is p, and described p characteristic root is in magnitude order;
Screening module, for obtaining in p described characteristic root, contribution rate sum is more than the preceding m feature of predetermined threshold
Root;Wherein, the contribution rate of each characteristic root is equal to the value sum of the value of the characteristic root divided by p characteristic root of whole;
Dimensionality reduction characteristic quantity obtains module, for according to characteristic vector corresponding with described preceding m characteristic root and described defeated
Enter sample space, obtain principal component scores matrix;Wherein, the characteristic quantity in the principal component scores matrix is after the dimensionality reduction
Characteristic quantity.
Above disclosed is only a kind of preferred embodiment of the invention, can not limit the power of the present invention with this certainly
Sharp scope, one of ordinary skill in the art will appreciate that all or part of flow of above-described embodiment is realized, and according to present invention power
Profit requires made equivalent variations, still falls within and invents covered scope.
One of ordinary skill in the art will appreciate that realize all or part of flow in above-described embodiment method, being can be with
The hardware of correlation is instructed to complete by computer program, described program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, described storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (RandomAccess
Memory, RAM) etc..
Claims (10)
1. a kind of electric allowance recognition methods of the brain based on time domain and domain space, it is characterised in that comprise the following steps:
The pending brain electric array signal received is filtered, the signal wave corresponding to each brain wave is extracted;
Each described signal wave is cut into slices, projection of each signal wave in the y-axis of corresponding each section is calculated
Maximum and minimum value, according to maximum and the interval of minimum value at least two equal lengths of formation, and according to positioned at each area
Between projection quantity, obtain the grid projection degree of variation of each signal wave, obtain the pending brain electric array signal when
The characteristic quantity of domain space;
The energy of the signal wave corresponding to each brain wave is calculated, according to the frequency range of each brain wave and corresponding signal wave
Energy, calculate the energy ratio between any two signal wave, obtain the pending brain electric array signal in domain space
Characteristic quantity;
Characteristic quantity to the pending brain electric array signal in time domain space and the characteristic quantity in domain space carry out classification knowledge
Not, the electric allowance of brain is obtained.
2. the electric allowance recognition methods of the brain based on time domain and domain space according to claim 1, it is characterised in that institute
State and each described signal wave is cut into slices, calculate projection of each signal wave in the y-axis of corresponding each section
Maximum and minimum value, according to maximum and the interval of minimum value at least two equal lengths of formation, and according to interval positioned at each
Projection quantity, obtain the grid projection degree of variation of each signal wave, obtain the pending brain electric array signal in time domain
The characteristic quantity in space is specifically included:
Each signal wave is cut at least two sections with same time interval;
Calculate projection of each signal wave in the y-axis of corresponding each section;
The maximum and minimum value of all projections are counted, and according to maximum and the area of minimum value at least two equal lengths of formation
Between;
Statistics is located at the quantity of each interval projection, and calculates the standard deviation of the quantity of each interval projection, obtains each
The grid projection degree of variation of signal wave, obtains characteristic quantity of the pending brain electric array signal in time domain space.
3. the electric allowance recognition methods of the brain based on time domain and domain space according to claim 1, it is characterised in that institute
State the characteristic quantity to the pending brain electric array signal in time domain space and the characteristic quantity in domain space carry out Classification and Identification,
The electric allowance of brain is obtained to specifically include:
The characteristic quantity is classified based on training in advance good SVMs, identification is obtained and the electric sequence of the pending brain
The electric allowance of the corresponding brain of column signal.
4. the electric allowance recognition methods of the brain based on time domain and domain space according to claim 1, it is characterised in that
It is described to be classified according to the pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space
Identification, obtains also including before the electric allowance of brain:
Based on PCA to the pending brain electric array signal in the characteristic quantity of time domain space and in domain space
Characteristic quantity carries out dimension-reduction treatment, obtains the characteristic quantity after dimensionality reduction.
5. the electric allowance recognition methods of the brain based on time domain and domain space according to claim 4, it is characterised in that institute
State based on PCA to the pending characteristic quantity of the brain electric array signal in time domain space and the spy in domain space
The amount of levying carries out dimension-reduction treatment, obtains the characteristic quantity after dimensionality reduction and specifically includes:
The pending characteristic quantity of the brain electric array signal in time domain space and the characteristic quantity in domain space are set to input
Characteristic quantity in sample space, and data normalization processing is carried out to the input sample space;
The input sample space after being handled according to data normalization obtains covariance matrix;
Calculate the characteristic root and characteristic vector corresponding with each characteristic root of the covariance matrix;Wherein, the characteristic root
Quantity is p, and described p characteristic root is in magnitude order;
Obtain in p described characteristic root, contribution rate sum is more than the preceding m characteristic root of predetermined threshold;Wherein, each characteristic root
Contribution rate be equal to the characteristic root value divided by whole p characteristic root value sum;
According to characteristic vector corresponding with described preceding m characteristic root and the input sample space, principal component scores square is obtained
Battle array;Wherein, the characteristic quantity in the principal component scores matrix is the characteristic quantity after the dimensionality reduction.
6. a kind of electric allowance identifying device of the brain based on time domain and domain space, it is characterised in that including:
Signal extraction unit, for being filtered to the pending brain electric array signal received, is extracted corresponding to each brain
The signal wave of electric wave;
Temporal signatures extraction unit, for being cut into slices to each described signal wave, calculates each signal wave corresponding
The maximum and minimum value for the projection in y-axis each cut into slices, at least two equal lengths are formed according to maximum and minimum value
Interval, and according to the quantity positioned at each interval projection, obtains the grid projection degree of variation of each signal wave, obtain described in treat
Handle characteristic quantity of the brain electric array signal in time domain space;
Frequency domain character extraction unit, the energy for calculating the signal wave corresponding to each brain wave, according to each brain wave
The energy of frequency range and corresponding signal wave, calculates the energy ratio between any two signal wave, obtains described pending
Characteristic quantity of the brain electric array signal in domain space;
Brain electricity allowance recognition unit, for the pending brain electric array signal in the characteristic quantity of time domain space and in frequency domain
The characteristic quantity in space carries out Classification and Identification, obtains the electric allowance of brain.
7. the electric allowance identifying device of the brain based on time domain and domain space according to claim 6, it is characterised in that institute
Temporal signatures extraction unit is stated to specifically include:
Section module, for each signal wave to be cut into at least two sections with same time interval;
Computing module is projected, for calculating projection of each signal wave in the y-axis of corresponding each section;
Interval division module, maximum and minimum value for counting all projections, and according to maximum and minimum value formed to
The interval of few two equal lengths;
Grid projection degree of variation computing module, for counting the quantity positioned at each interval projection, and calculates each interval
The standard deviation of the quantity of projection, obtains the grid projection degree of variation of each signal wave, obtains the pending brain electric array signal
In the characteristic quantity of time domain space.
8. the electric allowance identifying device of the brain based on time domain and domain space according to claim 6, it is characterised in that institute
State the electric allowance recognition unit of brain specifically for, the characteristic quantity is classified based on training in advance good SVMs,
Identification obtains the electric allowance of brain corresponding with the pending brain electric array signal.
9. the electric allowance identifying device of the brain based on time domain and domain space according to claim 6, it is characterised in that also
Including:
Feature Dimension Reduction unit, for based on PCA to the pending brain electric array signal time domain space feature
Amount and the characteristic quantity after the characteristic quantity of domain space carries out dimension-reduction treatment, acquisition dimensionality reduction.
10. the electric allowance identifying device of the brain based on time domain and domain space according to claim 9, it is characterised in that
The Feature Dimension Reduction unit is specifically included:
Standardization module, for by the pending brain electric array signal in the characteristic quantity of time domain space and in domain space
Characteristic quantity be set to characteristic quantity in input sample space, and data normalization processing is carried out to the input sample space;
Covariance matrix computing module, for being handled according to data normalization after the input sample space obtain covariance square
Battle array;
Feature calculation module, characteristic root and characteristic vector corresponding with each characteristic root for calculating the covariance matrix;
Wherein, the quantity of the characteristic root is p, and described p characteristic root is in magnitude order;
Screening module, for obtaining in p described characteristic root, contribution rate sum is more than the preceding m characteristic root of predetermined threshold;Its
In, the contribution rate of each characteristic root is equal to the value sum of the value of the characteristic root divided by p characteristic root of whole;
Dimensionality reduction characteristic quantity obtains module, for according to characteristic vector corresponding with described preceding m characteristic root and the input sample
This space, obtains principal component scores matrix;Wherein, the characteristic quantity in the principal component scores matrix is the feature after the dimensionality reduction
Amount.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710187188.9A CN106974648B (en) | 2017-03-27 | 2017-03-27 | Electroencephalogram relaxation degree identification method and device based on time domain and frequency domain space |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710187188.9A CN106974648B (en) | 2017-03-27 | 2017-03-27 | Electroencephalogram relaxation degree identification method and device based on time domain and frequency domain space |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106974648A true CN106974648A (en) | 2017-07-25 |
CN106974648B CN106974648B (en) | 2020-02-14 |
Family
ID=59338963
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710187188.9A Active CN106974648B (en) | 2017-03-27 | 2017-03-27 | Electroencephalogram relaxation degree identification method and device based on time domain and frequency domain space |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106974648B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491792A (en) * | 2018-03-21 | 2018-09-04 | 安徽大学 | Office scene human-computer interaction Activity recognition method based on electro-ocular signal |
CN109344816A (en) * | 2018-12-14 | 2019-02-15 | 中航华东光电(上海)有限公司 | A method of based on brain electricity real-time detection face action |
CN109871121A (en) * | 2019-01-03 | 2019-06-11 | 中国矿业大学 | A kind of massage armchair comfort level automatic regulating system and adjusting method based on brain-computer interface |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040143296A1 (en) * | 2002-12-17 | 2004-07-22 | Xiaoming Wang | Method and apparatus for inducing alpha rhythm to the human body |
CN101843491A (en) * | 2010-06-07 | 2010-09-29 | 天津大学 | Resting electroencephalogram identification method based on bilinear model |
CN106108894A (en) * | 2016-07-18 | 2016-11-16 | 天津大学 | A kind of emotion electroencephalogramrecognition recognition method improving Emotion identification model time robustness |
-
2017
- 2017-03-27 CN CN201710187188.9A patent/CN106974648B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040143296A1 (en) * | 2002-12-17 | 2004-07-22 | Xiaoming Wang | Method and apparatus for inducing alpha rhythm to the human body |
CN101843491A (en) * | 2010-06-07 | 2010-09-29 | 天津大学 | Resting electroencephalogram identification method based on bilinear model |
CN106108894A (en) * | 2016-07-18 | 2016-11-16 | 天津大学 | A kind of emotion electroencephalogramrecognition recognition method improving Emotion identification model time robustness |
Non-Patent Citations (1)
Title |
---|
刘爽等: "脑电时间效应对情绪识别模型的影响及解决措施研究", 《中国生物医学工程学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491792A (en) * | 2018-03-21 | 2018-09-04 | 安徽大学 | Office scene human-computer interaction Activity recognition method based on electro-ocular signal |
CN108491792B (en) * | 2018-03-21 | 2022-07-12 | 安徽大学 | Office scene human-computer interaction behavior recognition method based on electro-oculogram signals |
CN109344816A (en) * | 2018-12-14 | 2019-02-15 | 中航华东光电(上海)有限公司 | A method of based on brain electricity real-time detection face action |
CN109871121A (en) * | 2019-01-03 | 2019-06-11 | 中国矿业大学 | A kind of massage armchair comfort level automatic regulating system and adjusting method based on brain-computer interface |
Also Published As
Publication number | Publication date |
---|---|
CN106974648B (en) | 2020-02-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110811609B (en) | Epileptic spike intelligent detection device based on self-adaptive template matching and machine learning algorithm fusion | |
Hsu et al. | Wavelet-based fractal features with active segment selection: Application to single-trial EEG data | |
Lawhern et al. | Detection and classification of subject-generated artifacts in EEG signals using autoregressive models | |
Luczak et al. | Gating of sensory input by spontaneous cortical activity | |
Vézard et al. | EEG classification for the detection of mental states | |
Duan et al. | Differential entropy feature for EEG-based emotion classification | |
Brankačk et al. | EEG gamma frequency and sleep–wake scoring in mice: comparing two types of supervised classifiers | |
Özdamar et al. | Detection of spikes with artificial neural networks using raw EEG | |
CN106923824A (en) | Brain electricity allowance recognition methods and device based on many spatial signal properties | |
CN106923825A (en) | Brain electricity allowance recognition methods and device based on frequency domain and phase space | |
Kumari et al. | Seizure detection in EEG using time frequency analysis and SVM | |
CN106974648A (en) | The electric allowance recognition methods of brain based on time domain and domain space and device | |
CN107007290A (en) | The electric allowance recognition methods of brain based on time domain and phase space and device | |
CN106175757B (en) | Behaviour decision making forecasting system based on brain wave | |
Sulaiman et al. | Development of EEG-based stress index | |
Kubat et al. | AI-based approach to automatic sleep classification | |
Zhang et al. | Classification of EEG signal by WT-CNN model in emotion recognition system | |
CN108209909A (en) | Bimodulus spy's nerve signal feature selection approach based on action intention task | |
Yu et al. | Cross-correlation based discriminant criterion for channel selection in motor imagery BCI systems | |
Lin et al. | Motion sickness estimation system | |
Majeed et al. | ECG classification system based on multi-domain features approach coupled with least square support vector machine (LS-SVM) | |
CN110192864A (en) | A kind of cross-domain electrocardiogram biometric identity recognition methods | |
Abuhashish et al. | Feature extracted classifiers based on eeg signals: a survey | |
CN106682605A (en) | Method of identifying brain electricity relaxation degree and system thereof | |
Gilmour et al. | Manual rat sleep classification in principal component space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |