CN102755162B - Audio-visual cognitive event-related electroencephalogram-based identification method - Google Patents
Audio-visual cognitive event-related electroencephalogram-based identification method Download PDFInfo
- Publication number
- CN102755162B CN102755162B CN201210196442.9A CN201210196442A CN102755162B CN 102755162 B CN102755162 B CN 102755162B CN 201210196442 A CN201210196442 A CN 201210196442A CN 102755162 B CN102755162 B CN 102755162B
- Authority
- CN
- China
- Prior art keywords
- event
- cognitive
- characteristic
- index
- phase
- 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.)
- Active
Links
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses an audio-visual cognitive event-related electroencephalogram-based identification method, which comprises the following steps of: performing wavelet packet decomposition and reconstruction on a series of filtered independent components to acquire electroencephalogram signals within electroencephalogram activity source rhythm ranges, and performing empirical mode decomposition on electroencephalogram signals of each rhythm to obtain corresponding feature mode components which reflect feature rhythm vibration modes; extracting inter-cognitive event phase locking strength features, inter-event synchronous features and driving and response coupling features from the feature mode components by adopting an inter-trial coherence index, a phase intrinsic coherence index, a phase shift intrinsic coherence index and a partial direct coherence index; extracting the power spectrum features of an audio-visual cognitive event-related electroencephalogram by adopting event-related spectral perturbation; and classifying the inter-cognitive event phase locking strength features, the inter-event synchronous features, the driving and response coupling features and the power spectrum features of cognitive events of a plurality of subjects by adopting a support vector machine multi-classifier to obtain identification results. According to the audio-visual cognitive event-related electroencephalogram-based identification method increases the identification rate.
Description
Technical field
The invention belongs to identification field, more particularly to a kind of personal identification method based on the cognitive event-related EEG of audiovisual.
Background technology
With the progress and the raising of quality of life of society, the protection of information security will concern the interests of personal or even entire society.Now, identification and the authentication question of identity have been directed in many fields.For example:In terms of information security, coded and decoded applied to information and the safety of resource is transmitted.Due to the drawback such as reliability is low, be easily lost in the way of traditional " being recognized people by thing ", the demand in the present age can not be met, the biological characteristic having by people itself has been the substitute is, for example:Fingerprint and iris etc. carry out identification.However, each technology has limitation, researchers untiringly make great efforts to explore new living things feature recognition means.Research shows, even for same outside stimulus or main body when same event is thought deeply, and the EEG signals produced by the brain of different people are also different, i.e. brain electricity has significant individual difference.Based on this point, while having that generality is strong in view of brain electricity, stablizing relatively, high specificity, being difficult to replicate and the advantage such as forges, it is thus proposed that applied brain is electric as a kind of new biological characteristic among identification.Particularly complicated task, need that subject highly the participates in and closely related task of thinking activities, the brain electricity individual difference inspired is also more obvious, so as to be more suitable for the induction normal form of identification.
For a cognitive EEG signals, the energy variation and phase place change in its correspondence time and space in each subtask event are generally investigated.The traditional analysis of cognitive brain electricity can be carried out along time domain and frequency domain both direction respectively.In time domain, it is overlapped averagely in cognitive event during by observation brain electric array lock, obtains ERP(Event related potential)Signal.On frequency domain, then by whole EEG(Brain electricity)The change of its mean power is calculated by frequency in same event during the power spectrum lock of data, one is obtained and is referred to as the related perturbation of spectra of event or disturbance(ERSP)Two dimension(Time-frequency)Image.
But either ERP obtained by time domain average or the average gained ERSP of frequency domain can not all provide the feature of generation event related cognitive brain electricity comprehensively.Because filtered out by superposed average in observation brain electricity can not be with stimulating periods of events accurately to repeat but still a large amount of useful informations relevant with cognitive event induction by ERP, simultaneously phase-lock section information when only leaving a small number of relevant with cognition event induction locks.And induce produced power or the characteristic wave bands of energy oscillation change to be difficult almost to find corresponding characteristic component in the ERP produced by being induced by same event by cognitive event in ERSP.Vice versa.Therefore, even if ERP and ERSP are combined together, whole features in cognitive brain electricity also can not be intactly extracted comprehensively.
Inventor is during the present invention is realized, discovery at least has following shortcoming and defect in the prior art:
But at present for still being come with some shortcomings in the signal decomposition and feature extracting method of cognitive EEG signals, so as to reduce due to the separability of brain electrical feature caused by individual difference, it is impossible to preferably carry out identification.
The content of the invention
The invention provides a kind of personal identification method based on the cognitive event-related EEG of audiovisual, this method enhances the separability of the brain electrical feature caused by individual difference so that can preferably carry out identification, described below:
A kind of personal identification method based on the cognitive event-related EEG of audiovisual, the described method comprises the following steps:
(1) evoked brain potential time frequency space filtering is carried out using extension maximum informational entropy independent component analysis method, to extend maximum informational entropy as object function, by going back to original time domain distribution of electrodes space to evoked brain potential signal Xie Hun matrixes back projection, a series of independent element components are obtained;Space filtering is carried out to a series of independent element components using based on wavelet packet region independent component analysis method;
(2) WAVELET PACKET DECOMPOSITION reconstructing method is used to obtain EEG signals of δ, θ, α, β and γ wave band for the Cortical ECoG active source rhythm and pace of moving things scope of representative to a series of filtered independent element components, empirical mode decomposition is carried out to each rhythm and pace of moving things EEG signals, the characteristic modes component of each self-corresponding reflection feature rhythm and pace of moving things vibration mode is obtained;
(3) synchronous characteristic between phase strength characteristic, event, driving and response coupling feature are locked using being directly concerned between index extracts the cognitive event in the characteristic modes component respectively in relevant index and part in the index that is concerned with, phase shift in the index that is concerned with, phase in event;The power spectrum characteristic of cognitive event-related EEG is extracted using the related perturbation of spectrum of event;
(4) synchronous characteristic, the driving and the power spectrum characteristic of response coupling feature and the cognitive event locking phase strength characteristic, the event the cognitive event of multiple subjects are classified using SVMs multi-categorizer, obtains identification result.
The beneficial effect for the technical scheme that the present invention is provided is:Spontaneous EEG or the related EEG signal of event are decomposed into clearly by a series of locus using independent component analysis and empirical mode decomposition method, the characteristic component sum with function connects meaning;By in the related perturbation of spectrum of event and event when relevant index can realize dynamic monitoring signal lock, lock phase character, from multi-angular analysis and cognitive brain electrical feature can be extracted deeper into information change and transformational relation of the Cortical ECoG active source before and after cognitive event is detected with the index that is directly concerned with relevant and part in relevant, phase shift in phase simultaneously;Signal detection and processing to event related potential, carry out features described above parameter extraction, achieve very good effect, reduce influence of the interference signal to EEG signals, EEG signals are used for identification, and then improve identification rate, the need for meeting in practical application.
Brief description of the drawings
The schematic diagram based on the cognitive event-related EEG feature extraction of audiovisual with pattern recognition analysis overall plan that Fig. 1 provides for the present invention;
The schematic diagram of time-frequency characteristics before the ICA filtering that Fig. 2 a provide for the present invention;
The schematic diagram of time-frequency characteristics after the ICA filtering that Fig. 2 b provide for the present invention;
The schematic diagram for the power spectrum density time domain variation characteristic that Fig. 2 c provide for the present invention;
The schematic diagram that Fig. 2 d are compared for the ERSP values that the present invention is provided with the ERP signals containing P300;
The schematic diagram that Fig. 2 e are compared for the ITC value that the present invention is provided with the ERP signals containing P300;
The schematic diagram that Fig. 2 f are compared for the ERSP values that the present invention is provided with the ERP signals containing P300;
The schematic diagram that Fig. 2 g are compared for the ITC value that the present invention is provided with the ERP signals containing P300;
A kind of flow chart for personal identification method based on the cognitive event-related EEG of audiovisual that Fig. 3 provides for the present invention.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, embodiment of the present invention is described further in detail.
Cognitive event-related EEG and sensation, cognitive activities are closely related, are to perceive nerve pathway and stimulus to the sense organ and the combined reaction of inherent Cognitive Thinking to external world of each functional areas of cerebral cortex.Audio-visual combined stimulation is relative to the cognitive event EEG signals that the vision of unipath or acoustic stimuli are obtained, and wave-shape amplitude is higher, incubation period is more stable and space-time characteristic is obvious.
It is often that, by the mixed signal of the multiple signals of not homologous generation, and EEG signals typically have non-stationary and time variation, therefore more applicable use independent component analysis due to inducing obtained cognitive EEG signals(ICA)And empirical mode decomposition(EMD)Method is electric by scalp brain(Spontaneous and cognitive EEG)It is decomposed into a series of component sum that locus are determined, the time is relatively independent.
Introducing event correlation perturbation of spectrum(ERSP), in cognitive event relevant(ITC)Relevant in index, phase(PIC), in phase shift relevant(PsIC)Parameter and part are directly concerned with(PDC)When being locked between important frequencies component of the various features parameter index to detect Cortical ECoG active source, phase, phase replacement and synchronized oscillation feature are locked, so as to strengthen the separability of the electric biological characteristic of brain, identification is preferably carried out.
It is described below the embodiments of the invention provide a kind of personal identification method based on the cognitive event-related EEG of audiovisual referring to Fig. 1 and Fig. 3 in order to strengthen the separability of the brain electrical feature caused by individual difference so that can preferably carry out identification:
Independent component analysis(ICA)Refer to the technology that source signal is isolated from the linear hybrid signal of multiple source signals.In addition to known source signal is statistical iteration, without other prioris, ICA provides a kind of effective blind source separating(BSS)Method.ICA eliminate noise while, the details to other signals is not almost destroyed, and denoising performance also tend to it is well more many than traditional filtering method.Empirical mode decomposition (EMD) method is suitable for analyzing non-linear and non-stationary signal sequence, with very high signal to noise ratio.The key of this method is empirical mode decomposition, and it can make sophisticated signal be decomposed into limited intrinsic mode functions (IMF), decomposites the local feature signal that each IMF components come contain the different time scales of original signal.Empirical mode decomposition can make Non-stationary Data carry out tranquilization processing, then carry out Hilbert transform and obtain time-frequency spectrum, obtain the frequency of physical significance.Compared with the method such as short time discrete Fourier transform and wavelet decomposition, this method be intuitively, it is direct, posterior and adaptive because basic function is to be decomposed to obtain in itself by data.
It is often that, by the mixed signal of the multiple signals of not homologous generation, and EEG signals typically have non-stationary and time variation due to inducing obtained cognitive EEG signals, therefore uses independent component analysis(ICA)And empirical mode decomposition(EMD)Method is electric by scalp brain(Spontaneous and cognitive EEG)It is decomposed into a series of component sum that locus are determined, the time is relatively independent.
101:Evoked brain potential time frequency space filtering is carried out using extension maximum informational entropy independent component analysis method (ICA), to extend maximum informational entropy as object function, by going back to original time domain distribution of electrodes space to evoked brain potential signal Xie Hun matrixes back projection, a series of independent element components are obtained;Space filtering is carried out to a series of independent element components using based on wavelet packet region independent component analysis (WPICA) method;
Wavelet packet character subspace is chosen according to the distribution of the feature band of EEG signals, a series of independent element components expansion isolated component is decomposed respectively, a series of different signal of height frequencies is decomposed into;Wavelet Packet Domain uncoiling is carried out to a series of independent element components by being embedded in multi-resolution analysis of wavelet packet method in isolated component decomposable process;Again by wavelet packet inverse transformation, the brain power supply signal of feature band is projected back in the electric time domain space of original brain, interference signal is filtered out from the angle of frequency, a series of purer independent element components are obtained.
Wherein, known to those skilled in the art using the specific steps and the mixed matrix of solution of extension maximum informational entropy independent component analysis method (ICA) progress evoked brain potential space filtering, the embodiment of the present invention is not limited herein.
102:WAVELET PACKET DECOMPOSITION reconstructing method is used to obtain EEG signals of δ, θ, α, β and γ wave band for the Cortical ECoG active source rhythm and pace of moving things scope of representative to a series of filtered independent element components, EMD decomposition is carried out to each rhythm and pace of moving things EEG signals, the characteristic modes component of each self-corresponding reflection feature rhythm and pace of moving things vibration mode is obtained;
With the related perturbation of spectrum of the event of the energy envelope CURVE STUDY EEG signals for the characteristic modes component being fitted in algorithmic procedure(ERSP)Feature.
Wherein, false mode function problem is also easy to produce in order to avoid original eeg data directly carries out EMD decomposition, uses WAVELET PACKET DECOMPOSITION reconstructing method to obtain EEG signals of δ, θ, α, β and γ wave band for the Cortical ECoG active source rhythm and pace of moving things scope of representative.Pass through the related perturbation of spectrum of the event of energy envelope CURVE STUDY EEG signals(ERSP)Feature.
103:It is being concerned with using in event(ITC)Relevant in index, phase(PIC)Relevant in index, phase shift(PsIC)Index and part are directly concerned with(PDC)Index extracts lock phase strength characteristic in characteristic modes component, synchronous characteristic, driving and response coupling feature between event respectively;The power spectrum characteristic of cognitive event-related EEG is extracted using the related perturbation of spectrum ERSP of event;
Wherein, for n cognitive event, ERSP is defined as
F in formulakWhen (f, t) is the cognitive brain electricity of kth time event(t)- frequency(f)Distribution.ERSP reflects the influence that cognitive process is composed to each frequency band power.
Wherein, ITC is then used for detecting that the degree that lock mutually induces occurs in the cognitive process, is defined as
ITC value is between 0 and 1, and ITC=1 represents that cognitive brain electricity is strictly locked in the stimulation initial state of cognitive event.
Although the power spectral density change that ERSP can reflect in cognitive process, the detectable lock phase degree of ITC, does not provide synchronized oscillation information yet.To evaluate the synchronized oscillation characteristic between Cortical ECoG active source, introduce in phase in relevant (PIC) measurement, be defined as
CPIC(f, t) value is also between 0 and 1.CPIC(f, t)=1 represents cognitive brain electricity lock phase completely.And for the non-lock phase behavior of signal, can also introduce and be measured in phase shift in relevant (PsIC) parameter, it is defined as
CPsIC(f, t) value is still between 0 and 1.CPsIC(f, t)=1 represents cognitive brain electricity non-lock phase completely.
For the Dynamics Coupling relation between each frequency range component of the cognitive brain electricity of further detection, directly relevant (PDC) index of introducing portion is defined as
In formulaAI, j(f, t) is i, j frequency range cross-spectral density coefficients.Di←j PDCRepresent directly be concerned with effect of the j component to i component.DPDCValue is between 0 and 1, DPDC=1 represents maximum coherence.DPDCThe linear correlation that two time series signals are asked is described from frequency domain, to evaluate its function connects degree, driving and response coupled relation.
104:Synchronous characteristic, driving and the power spectrum characteristic of response coupling feature and cognitive event locking phase strength characteristic, event the cognitive event of multiple subjects are classified using SVMs multi-categorizer, identification result is obtained.
A kind of personal identification method based on the cognitive event-related EEG of audiovisual provided in an embodiment of the present invention is verified with a specific experiment below, it is described below:
Referring to Fig. 2 a, Fig. 2 b, Fig. 2 c, Fig. 2 d, Fig. 2 e, Fig. 2 f and Fig. 2 g, Time-frequency Filter:(a) time-frequency characteristics are not obvious before ICA filtering;(b) after filtering, the energy rise phenomenon of corresponding band substantially bursts time-frequency characteristics.Space filtering:A ERP time-frequency characteristics after wavelet packet independent component analysis (WPICA) space filtering are protruded, and spatial distribution differences are big;The corresponding power spectrum density time domain variation characteristics of B are obvious.Can be interior in relevant (ITC) index dynamic monitoring signal lock, lock phase character by the related perturbation of spectrum (ERSP) of event and event.P300 be the typical endogenous component of ERP signals, only by superposed average extract ERP signals, lock phase character detection when-frequency analysis example, ERSP (dB), ITC value are compared with the ERP signals containing P300:P300 signals, which go out current moment correspondence, an ERSP and ITC peak value, indication induced response along with lock when, lock phase effect;After being pre-processed through ICA space filterings, the effect is more prominent.
The feature extracted is caused preferably by above-mentioned processing, influence of the interference signal to EEG signals is reduced, EEG signals is used for identification, and then improves identification rate, the need for meeting in practical application.
In summary, the embodiments of the invention provide a kind of personal identification method based on the cognitive event-related EEG of audiovisual, a series of clear and definite, the characteristic component sum with function connects meaning that spontaneous EEG or the related EEG signal of event are decomposed into locus by this method using independent component analysis and empirical mode decomposition method;By in the related perturbation of spectrum of event and event when relevant index can realize dynamic monitoring signal lock, lock phase character, from multi-angular analysis and cognitive brain electrical feature can be extracted deeper into information change and transformational relation of the Cortical ECoG active source before and after cognitive event is detected with the index that is directly concerned with relevant and part in relevant, phase shift in phase simultaneously;Signal detection and processing to event related potential, influence of the interference signal to EEG signals is reduced, features described above parameter extraction is carried out, achieves very good effect, and then improve by EEG signals be used for identification recognition correct rate, the need for meeting in practical application.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the embodiments of the present invention are for illustration only, and the quality of embodiment is not represented.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, within the spirit and principles of the invention, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (1)
1. a kind of personal identification method based on the cognitive event-related EEG of audiovisual, it is characterised in that the described method comprises the following steps:
(1) evoked brain potential time frequency space filtering is carried out using extension maximum informational entropy independent component analysis method, to extend maximum informational entropy as object function, by going back to original time domain distribution of electrodes space to evoked brain potential signal Xie Hun matrixes back projection, a series of independent element components are obtained;Space filtering is carried out to a series of independent element components using based on wavelet packet region independent component analysis method;
(2) a series of filtered independent element components are obtained with the EEG signals of the Cortical ECoG active source rhythm and pace of moving things scope of δ, θ, α, β and γ wave band using WAVELET PACKET DECOMPOSITION reconstructing method, empirical mode decomposition is carried out to the EEG signals of the Cortical ECoG active source rhythm and pace of moving things scope, the characteristic modes component of each self-corresponding reflection feature rhythm and pace of moving things vibration mode is obtained;
(3) synchronous characteristic between phase strength characteristic, event, driving and response coupling feature are locked using being directly concerned between index extracts the cognitive event in the characteristic modes component respectively in relevant index and part in the index that is concerned with, phase shift in the index that is concerned with, phase in event;The power spectrum characteristic of cognitive event-related EEG is extracted using the related perturbation of spectrum of event;
(4) synchronous characteristic, the driving and the power spectrum characteristic of response coupling feature and the cognitive event locking phase strength characteristic, the event the cognitive event of multiple subjects are classified using SVMs multi-categorizer, obtains identification result;
Wherein, it is in relevant index in the event:
Fk(f, t) is the electric time-frequency distributions of cognitive brain of kth time event, and t is the time, and f is frequency, and n is the number of times of cognitive event;
Wherein, it is in relevant index in the phase:
Wherein, it is in relevant index in the phase shift:
Wherein, the directly relevant index in the part is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210196442.9A CN102755162B (en) | 2012-06-14 | 2012-06-14 | Audio-visual cognitive event-related electroencephalogram-based identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210196442.9A CN102755162B (en) | 2012-06-14 | 2012-06-14 | Audio-visual cognitive event-related electroencephalogram-based identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102755162A CN102755162A (en) | 2012-10-31 |
CN102755162B true CN102755162B (en) | 2014-04-30 |
Family
ID=47049997
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210196442.9A Active CN102755162B (en) | 2012-06-14 | 2012-06-14 | Audio-visual cognitive event-related electroencephalogram-based identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102755162B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107437011A (en) * | 2016-05-26 | 2017-12-05 | 华为技术有限公司 | The method and apparatus of identification based on EEG signals |
CN106990835B (en) * | 2017-02-20 | 2020-08-28 | 深圳先进技术研究院 | Exercise training evaluation method and device |
CN108564011A (en) * | 2017-08-01 | 2018-09-21 | 南京邮电大学 | A kind of personal identification method that normal form being presented based on brain electricity Rapid Speech |
CN107669267B (en) * | 2017-10-17 | 2020-06-19 | 山东大学 | Electroencephalogram unlocking system and method based on deep learning |
CN108734224A (en) * | 2018-06-05 | 2018-11-02 | 重庆科技学院 | Natural gas purification process exception monitoring method based on isolated component contribution degree weighted analysis |
CN108685577B (en) * | 2018-06-12 | 2020-11-06 | 国家康复辅具研究中心 | Brain function rehabilitation effect evaluation device and method |
CN109657560A (en) * | 2018-11-24 | 2019-04-19 | 天津大学 | Mechanical arm controls online brain-computer interface system and implementation method |
CN109784027B (en) * | 2019-01-11 | 2022-03-22 | 西安电子科技大学 | Identity verification method based on dual electroencephalogram signal characteristics |
CN109875580A (en) * | 2019-03-01 | 2019-06-14 | 安徽工业大学 | A kind of Cognitive efficiency can computation model |
CN111329474B (en) * | 2020-03-04 | 2021-05-28 | 西安电子科技大学 | Electroencephalogram identity recognition method and system based on deep learning and information updating method |
CN113662564B (en) * | 2021-09-24 | 2022-10-14 | 电子科技大学 | Event evoked potential extraction device based on eigenmode function coherent analysis |
CN115363605B (en) * | 2022-08-29 | 2024-02-23 | 天津大学 | Self-adaptive ASSR enhancement device based on high-frequency gamma neural oscillation |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0906029D0 (en) * | 2009-04-07 | 2009-05-20 | Nat Univ Ireland Cork | A method of analysing an electroencephalogram (EEG) signal |
CN101690659B (en) * | 2009-09-29 | 2012-07-18 | 华东理工大学 | Brain wave analysis method |
CN101703405A (en) * | 2009-11-09 | 2010-05-12 | 江西蓝天学院 | Wavelet analysis and Welch algorithm personal identification method |
CN101732047B (en) * | 2009-12-16 | 2011-06-08 | 天津大学 | Energy feature extraction method of composite lower limb imaginary movement EEG |
CN101843491A (en) * | 2010-06-07 | 2010-09-29 | 天津大学 | Resting electroencephalogram identification method based on bilinear model |
CN101862194B (en) * | 2010-06-17 | 2011-11-16 | 天津大学 | Imagination action EEG identification method based on fusion feature |
-
2012
- 2012-06-14 CN CN201210196442.9A patent/CN102755162B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN102755162A (en) | 2012-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102755162B (en) | Audio-visual cognitive event-related electroencephalogram-based identification method | |
Vaid et al. | EEG signal analysis for BCI interface: A review | |
Maiorana et al. | Eigenbrains and eigentensorbrains: Parsimonious bases for EEG biometrics | |
Bharadwaj et al. | Rapid acquisition of auditory subcortical steady state responses using multichannel recordings | |
Başar et al. | Alpha oscillations in brain functioning: an integrative theory | |
US11221672B2 (en) | Asymmetric EEG-based coding and decoding method for brain-computer interfaces | |
Chen et al. | A new multivariate empirical mode decomposition method for improving the performance of SSVEP-based brain–computer interface | |
Mukamel et al. | Phase-based measures of cross-frequency coupling in brain electrical dynamics under general anesthesia | |
Pei et al. | WLPVG approach to the analysis of EEG-based functional brain network under manual acupuncture | |
Gao et al. | A novel concealed information test method based on independent component analysis and support vector machine | |
Parvar et al. | Detection of event-related potentials in individual subjects using support vector machines | |
Cong et al. | Dimension reduction: additional benefit of an optimal filter for independent component analysis to extract event-related potentials | |
Wagner et al. | The detection of transient directional couplings based on phase synchronization | |
Brittain et al. | Single-trial multiwavelet coherence in application to neurophysiological time series | |
Manyakov et al. | Decoding SSVEP responses using time domain classification | |
Sabeti et al. | Event related potential (ERP) as a reliable biometric indicator: A comparative approach | |
CN117064409A (en) | Method, device and terminal for evaluating transcranial direct current intervention stimulation effect in real time | |
Klemm et al. | Coherent EEG indicators of cognitive binding during ambiguous figure tasks | |
Li et al. | GNMF-based quadratic feature extraction in SSTFT domain for epileptic EEG detection | |
Shan et al. | A revised Hilbert-Huang transformation to track non-stationary association of electroencephalography signals | |
Bhattacharya et al. | Nonlinear dynamics of evoked neuromagnetic responses signifies potential defensive mechanisms against photosensitivity | |
Wu et al. | A novel algorithm for learning sparse spatio-spectral patterns for event-related potentials | |
Congedo et al. | EEG source analysis: methods and clinical implications | |
de Sá et al. | Evaluating the entrainment of the alpha rhythm during stroboscopic flash stimulation by means of coherence analysis | |
Zandi et al. | Scalp EEG acquisition in a low-noise environment: A quantitative assessment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |