CN108470182A - A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification - Google Patents
A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification Download PDFInfo
- Publication number
- CN108470182A CN108470182A CN201810065848.0A CN201810065848A CN108470182A CN 108470182 A CN108470182 A CN 108470182A CN 201810065848 A CN201810065848 A CN 201810065848A CN 108470182 A CN108470182 A CN 108470182A
- Authority
- CN
- China
- Prior art keywords
- brain
- eeg signals
- feature
- test sample
- training set
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Psychiatry (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physiology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Fuzzy Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The brain-machine interface method that the present invention relates to a kind of to enhance and identify for asymmetric brain electrical feature, includes the following steps:Step 1 includes training set X by brain machine interface system foundationk, training sample YlWith the EEG signals module of test sample Y;Step 2 carries out frequency domain filtering and down-sampled data processing to test sample Y in EEG signals module;Step 3 is based on Fisher linear decision rules, to training set X in EEG signals modulekIt carries out that space projection matrix W is calculated;Step 4, to training set X in EEG signals modulekWith test sample Y DSP space filtering acquisitions are carried out according to following formulaAnd WTY feature vectors;Step 5, according toAnd WTY feature vectors carry out CCA space filterings structure projection matrix UkAnd Vk;By obtaining feature vectorWTY, projection matrix UkAnd VkTemplate matches, which are carried out, according to following formula generates feature vector ρl;Using different classifications device model to feature vector ρlIt is exported after being identified;This method improves EEG signals itself signal-to-noise ratio to improve the Classification and Identification efficiency of signal characteristic.
Description
Technical field
The present invention relates to brain-computer interface systems technology fields, and in particular to one kind for asymmetric brain electrical feature enhancing with
The brain-computer interface method of identification.
Background technology
Brain-computer interface (Brain-Computer Interface, BCI) is one and directly turns central nervous system activities
The system manually exported is turned to, it can substitute, repair, enhance, supplement or improve the normal output of central nervous system, from
And improve the reciprocation between central nervous system and internal and external environment.By the brain for acquiring and analyzing subject under different stimulated
Electric signal reuses certain engineering technology means and sets up exchanging between human brain and computer or other electronic equipments and control
Channel processed.BCI technologies realize a kind of completely new information exchange and control mode, can be disabled person's especially those basic limbs
Body motor function is damaged but the patient having a normal thinking provides a kind of approach with extraneous progress communication and control, makes their nothings
It need to carry out language or limb action can be the same as extraneous exchange or manipulation external device.For this purpose, BCI technologies are also increasingly by weight
Depending on.P300-speller and base based on P300 features in event related potential (Event-Related Potential, ERP)
In the SSVEP-BCI of Steady State Visual Evoked Potential (Steady-State Visual Evoked Potential, SSVEP) be to answer
The brain-computer interface system induced with wide visual stimulus, the relevant technologies have developed relatively stable and ripe.
For real-time data acquisition system, in order to eliminate interference signal, it usually needs carry out number to collected data
Filtering, traditional filtering method usually filter out specific band frequency, such as:Low-pass filtering, high-pass filtering, bandpass filtering, trap etc.
Deng.EEG signals have non-linear and non-stationary feature, in brain-computer interface systematic research, how to collected
EEG signals carry out processing analysis, and faint EEG signals feature is extracted from complicated background brain electricity and is carried out to different characteristic
Classification and Identification is to determine the key factor of BCI system performances, since there are frequency characteristic, means of filtering for EEG signals
It is usually used in the processing analysis of EEG signals, usually filtering frequency range can be adjusted according to different brain electrical features.After filtering, to passing
EEG signals of uniting carry out the linear discriminant analysis of classifying identification method (Linear Discriminant Analysis, LDA), altogether
Spatial model (Common Spatial Pattern, CSP), support vector machines (Support Vector Machine, SVM),
The methods of canonical correlation analysis (Canonical Correlation Analysis, CCA).These methods include space filtering
Thought, i.e., select one or several classification planes in higher dimensional space, its vector as spatial filter carry out signal empty
Between filter, it is therefore an objective to high dimensional signal is down to low-dimensional, convenient for classifying to it.Canonical correlation analysis algorithm is generally answered at present
For in SSVEP-BCI systems, and there is research to be further improved the algorithm, i.e., is applied during Processig of EEG information
Template matches principle introduces subject's own signal, improves the recognition correct rate and the rate of information throughput of system, for by BCI
Technology has further established strong basis to application achievements conversion.
Invention content
It is an object of the invention to overcome defect existing for above-mentioned background technology, provide a kind of for asymmetric brain electrical feature
The brain-computer interface method of enhancing and identification, this method are in conjunction with the feature of discrimination model space filtering and template matches principle point
Class method introduces DSP spatial filtering methods, and according to different thorns on the basis of existing template matches CCA classification policies
The coding strategy for swashing normal form builds different solution code masks, and point of signal characteristic is improved to improve EEG signals itself signal-to-noise ratio
Class recognition efficiency.
The present invention, which adopts the following technical scheme that, to be practiced:
A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification, includes the following steps:
Step 1 includes training set X by the foundation of brain-computer interface systemk, training sample YlWith the brain electricity of test sample Y
Signal data collection
Step 2 carries out frequency domain filtering and down-sampled data processing to test sample Y in EEG signals data set;
Step 3 is based on Fisher linear decision rules, to training set X in EEG signals modulekIt carries out that sky is calculated
Between projection matrix W;
Step 4, to training set X in EEG signals data setkWith test sample Y the spaces DSP are carried out according to following formula
Filtering obtainsAnd WTY feature vectors;
SB=∑11+∑22-∑12-∑21
Sw=σ1 2+σ2 2
Step 5, according toAnd WTY feature vectors carry out CCA space filterings structure projection matrix U using following formulak
And Vk;
Step 6, by obtaining feature vectorWTY, projection matrix UkAnd VkTemplate is carried out according to following formula
With generation feature vector ρl;
Step 7, using different classifications device model to feature vector ρlIt is exported after being identified.
The training setK two category features of expression, i.e. k=1,2;The training sample
The test sampleWherein NcIndicate the port number of acquisition brain electricity, NtIndicate intercept signal length, NsIndicate training
Collect number of samples.
Compared with prior art, the present invention has the advantage that:
1, the present invention is the Classification and Identification for asymmetric brain electrical feature, can effectively promote the signal-to-noise ratio of identification signal simultaneously
It is promoted and is divided
Class accuracy.
2, in brain-computer interface system of the present invention for the control of asymmetric brain electrical feature, asymmetric brain electrical feature is put down
Equal classification accuracy rate improves 17.88% compared with conventional sorting methods, it was demonstrated that can further improve brain-computer interface skill using this method
Art promotes the technology to be converted to application achievements;It has wide range of applications.
3, the present invention has been applied to the brain-computer interface system controlled based on asymmetric brain electrical feature, and design implements instruction
Collection for 32 BCI-speller offline and online brain-computer interface system experimentation;Further study the brain-machine that can be improved
Interface system is expected to obtain considerable Social benefit and economic benefit.
Description of the drawings
Fig. 1 is a kind of brain-computer interface method flow chart for enhancing and identifying for asymmetric brain electrical feature of the present invention.
Fig. 2 is that the present invention should be in the brain-computer interface system structure diagram comprising 32 instruction set.
Specific implementation mode
Below by specific embodiments and the drawings, the present invention is further illustrated.The embodiment of the present invention is in order to more
So that those skilled in the art is more fully understood the present invention well, any limitation is not made to the present invention.
As shown in Figure 1, the present invention provides a kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification;
Step 1 101 includes training set X by the foundation of brain-computer interface systemk, training sample YlWith test sample Y's
Brain teledata collection
It is assumed thatFor training set, k indicates two category features, i.e. k=1,2,It is trained for two classes
Sample, l=1,2,For test sample, wherein NcIndicate the port number of acquisition brain electricity, NtIndicate that intercept signal is long
Degree, NsIndicate training set number of samples.Training set and test set have carried out zero-mean processing all in time scale, i.e., each
The numerical value s at time pointtAll subtract time window [t1, t2] in time averageAs shown in formula (1):
All samples of training set are averaged to obtain the template signal of classification k, byIt indicates.Two class templates it
Between covariance matrixIt is expressed as:
Two class signal X1And X2Variance be expressed as:
Step 2 102 is selected from EEG signals data setTest sample carries out frequency domain filtering and down-sampled number
According to processing;
Step 3 103 is based on Fisher linear decision rules, to training set X in EEG signals modulekIt is calculated
Space projection matrix W;
Step 4 104, to training set X in EEG signals data setkWith test sample Y DSP is carried out according to following formula
Space filtering obtainsAnd WTY feature vectors
Based on Fisher linear decision rules, DSP algorithm acquire a projection matrix W make two category feature signals project after
Separability with bigger, the matrix W can be taken as spatial filter, and method for solving is:
SB=∑11+∑22-∑12-∑21 (6)
Sw=σ1 2+σ2 2 (7)
Wherein λiIt is the feature vector of the i-th row in matrix W, NWIndicate the spatial filter number being selected.Through the spaces W
Filtering can filter out the common-mode signal between two class signals, and apply CCA algorithms can be by constructing two projection matrix UkAnd Vk
After calculating DSP space filteringsAnd WTCorrelation between Y, CCA spatial filters UkAnd VkIt is calculated by following formula (8)
It obtains.
Step 5 105, according toAnd WTY feature vectors carry out CCA space filterings structure projection square using following formula
Battle array UkAnd Vk
Wherein,Indicate mathematic expectaion.Canonical correlation analysis is the linear relationship weighed between two multidimensional variables
Statistical analysis technique.It is different from linear regression and is fitted sample point using straight line, CCA is to see multidimensional characteristic vectors
Make an entirety, seeks one group of optimal solution using mathematical method so that the weight for having most relevance between two entirety, even public
The numerical value that formula (8) is calculated is maximum, and here it is the purposes of canonical correlation analysis.
Step 6 106, by obtaining feature vectorWTY, projection matrix UkAnd VkTemplate is carried out according to following formula
Matching generates feature vector ρl;
During template matches, template is built by training set data, according to the difference of stimulation mode, template structure also may be used
It adjusts accordingly, by taking the classification to asymmetric brain electrical feature signal as an example, vector ρ shown in formula (9)kIndicate training template
Similitude between training sample signal l.
Wherein corr (*) indicates that Pearson correlation coefficients, dist (*) indicate Euclidean distance.If ρk1,ρk2,ρk3,ρk4
And ρk5It is bigger, then it represents that YlWithBetween correlation it is bigger.Connect ρ1, lAnd ρ2, lIt can be obtained trained template and training sample
This feature vector ρ obtained after feature extractionM, by shown in formula (10):
ρl=(ρ1·l, ρ2·l), l=1,2 (10)
Step 7 107, using different classifications device model to feature vector ρlIt is exported after being identified.
According to feature vector ρlIt establishes linear discriminant analysis (Linear Discriminant Analysis, LDA), support
The different classifications device model of the different modes recognizers such as vector machine (Support Vector Machine, SVM), test sample
Y is preprocessed to carry out pattern-recognition with feeding grader after feature extraction, and then predicts the classification of the sample and export as a result, such as
Shown in Fig. 1.
Fig. 2 show the brain-computer interface system structure diagram for including 32 instruction set of inventive algorithm application.The system
Including eeg collection systems and computer disposal platform etc. such as liquid crystal display stimulation interface, electrode for encephalograms and eeg amplifiers
Part.The system application visual stimulus normal form induces the asymmetric brain electrical feature of two classes, using the brain electricity of NeuroScan companies production
Digital acquisition system acquires EEG signals, signal is inputted computer after eeg amplifier amplification, filtering, using the present invention
Two class brain electrical feature of algorithm pair is classified, and BCI instructions are converted into after finally decoding EEG signals and are exported.Stimulation is presented
And Data Management Analysis is based on the completion of Matlab platforms.
Calculate the asymmetric brain electrical feature signal of two classes signal-to-noise ratio (signal-to-noise rate, SNR) be respectively-
17.98dB and -14.90dB, SNR are defined as the ratio between signal energy and noise energy, and calculation formula is:
Wherein AMPiIndicate that the average amplitude of the signal in i-th of examination time time window, N indicate examination sub-quantity.
12 subjects of BCI systems pair of inventive algorithm application are tested.The experimental results showed that applying this hair
After bright algorithm, the average correct classification rates of 12 subjects promote 17.88%, significant to promote that (paired-samples T-test result is:t11
=-8.91, p < 0.01), and the signal-to-noise ratio of two category feature signals be promoted to respectively after DSP space filterings -9.71dB and -
8.68dB。
It should be understood that embodiment and example discussed herein simply to illustrate that, to those skilled in the art
For, it can be improved or converted, and all these modifications and variations should all belong to the protection of appended claims of the present invention
Range.
Claims (2)
1. a kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification, which is characterized in that including walking as follows
Suddenly:
Step 1 includes training set X by the foundation of brain-computer interface systemk, training sample YlWith the EEG signals of test sample Y
Data set
Step 2 carries out frequency domain filtering and down-sampled data processing to test sample Y in EEG signals data set;
Step 3 is based on Fisher linear decision rules, to training set X in EEG signals modulekIt carries out that space projection is calculated
Matrix W;
Step 4, to training set X in EEG signals data setkWith test sample Y DSP space filterings are carried out according to following formula
It obtainsAnd WTY feature vectors;
SB=∑11+∑22-∑12-∑21
Sw=σ1 2+σ2 2
Step 5, according toAnd WTY feature vectors carry out CCA space filterings structure projection matrix U using following formulakWith
Vk;
Step 6, by obtaining feature vectorWTY, projection matrix UkAnd VkTemplate matches life is carried out according to following formula
At feature vector ρl;
Step 7, using different classifications device model to feature vector ρlIt is exported after being identified.
2. a kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification according to claim 1, special
Sign is:The training setK two category features of expression, i.e. k=1,2;The training sample
The test sampleWherein NcIndicate the port number of acquisition brain electricity, NtIndicate intercept signal length, NsIndicate training
Collect number of samples.
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810065848.0A CN108470182B (en) | 2018-01-23 | 2018-01-23 | Brain-computer interface method for enhancing and identifying asymmetric electroencephalogram characteristics |
US16/616,834 US11221672B2 (en) | 2018-01-23 | 2018-12-30 | Asymmetric EEG-based coding and decoding method for brain-computer interfaces |
PCT/CN2018/125927 WO2019144776A1 (en) | 2018-01-23 | 2018-12-30 | Coding-decoding method for brain-machine interface system based on asymmetric electroencephalographic features |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810065848.0A CN108470182B (en) | 2018-01-23 | 2018-01-23 | Brain-computer interface method for enhancing and identifying asymmetric electroencephalogram characteristics |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108470182A true CN108470182A (en) | 2018-08-31 |
CN108470182B CN108470182B (en) | 2022-04-29 |
Family
ID=63266061
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810065848.0A Active CN108470182B (en) | 2018-01-23 | 2018-01-23 | Brain-computer interface method for enhancing and identifying asymmetric electroencephalogram characteristics |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108470182B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019144776A1 (en) * | 2018-01-23 | 2019-08-01 | 天津大学 | Coding-decoding method for brain-machine interface system based on asymmetric electroencephalographic features |
CN111158462A (en) * | 2019-11-28 | 2020-05-15 | 燕山大学 | Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model |
CN113591598A (en) * | 2021-07-07 | 2021-11-02 | 河北工业大学 | Brain-computer interface cross-load linear discrimination method based on correlation analysis |
CN113705732A (en) * | 2021-09-26 | 2021-11-26 | 华东理工大学 | Method and device for reducing P300 training time based on general model |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1776572A (en) * | 2005-12-08 | 2006-05-24 | 清华大学 | Computer man-machine interacting method based on steady-state vision induced brain wave |
CN101049236A (en) * | 2007-05-09 | 2007-10-10 | 西安电子科技大学 | Instant detection system and detection method for state of attention based on interaction between brain and computer |
CN101159086A (en) * | 2007-11-22 | 2008-04-09 | 中国人民解放军国防科学技术大学 | Calling device based on brain electric information demodulation |
US20160170996A1 (en) * | 2014-08-21 | 2016-06-16 | Affectomatics Ltd. | Crowd-based scores for experiences from measurements of affective response |
CN106502410A (en) * | 2016-10-27 | 2017-03-15 | 天津大学 | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface |
-
2018
- 2018-01-23 CN CN201810065848.0A patent/CN108470182B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1776572A (en) * | 2005-12-08 | 2006-05-24 | 清华大学 | Computer man-machine interacting method based on steady-state vision induced brain wave |
CN101049236A (en) * | 2007-05-09 | 2007-10-10 | 西安电子科技大学 | Instant detection system and detection method for state of attention based on interaction between brain and computer |
CN101159086A (en) * | 2007-11-22 | 2008-04-09 | 中国人民解放军国防科学技术大学 | Calling device based on brain electric information demodulation |
US20160170996A1 (en) * | 2014-08-21 | 2016-06-16 | Affectomatics Ltd. | Crowd-based scores for experiences from measurements of affective response |
CN106502410A (en) * | 2016-10-27 | 2017-03-15 | 天津大学 | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019144776A1 (en) * | 2018-01-23 | 2019-08-01 | 天津大学 | Coding-decoding method for brain-machine interface system based on asymmetric electroencephalographic features |
US11221672B2 (en) | 2018-01-23 | 2022-01-11 | Tianjin University | Asymmetric EEG-based coding and decoding method for brain-computer interfaces |
CN111158462A (en) * | 2019-11-28 | 2020-05-15 | 燕山大学 | Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model |
CN111158462B (en) * | 2019-11-28 | 2021-02-02 | 燕山大学 | Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model |
CN113591598A (en) * | 2021-07-07 | 2021-11-02 | 河北工业大学 | Brain-computer interface cross-load linear discrimination method based on correlation analysis |
CN113705732A (en) * | 2021-09-26 | 2021-11-26 | 华东理工大学 | Method and device for reducing P300 training time based on general model |
CN113705732B (en) * | 2021-09-26 | 2024-02-02 | 华东理工大学 | Method and device for reducing P300 training time based on general model |
Also Published As
Publication number | Publication date |
---|---|
CN108470182B (en) | 2022-04-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Tiwari et al. | Automated diagnosis of epilepsy using key-point-based local binary pattern of EEG signals | |
CN105877766B (en) | A kind of state of mind detection system and method based on the fusion of more physiological signals | |
CN108470182A (en) | A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification | |
CN109784023B (en) | Steady-state vision-evoked electroencephalogram identity recognition method and system based on deep learning | |
Lee et al. | A brain-wave-actuated small robot car using ensemble empirical mode decomposition-based approach | |
CN105956624B (en) | Mental imagery brain electricity classification method based on empty time-frequency optimization feature rarefaction representation | |
US11221672B2 (en) | Asymmetric EEG-based coding and decoding method for brain-computer interfaces | |
CN109497990B (en) | Electrocardiosignal identity recognition method and system based on canonical correlation analysis | |
CN108577865A (en) | A kind of psychological condition determines method and device | |
CN109766751B (en) | Steady-state vision-evoked electroencephalogram identity recognition method and system based on frequency domain coding | |
Keshishzadeh et al. | Improved EEG based human authentication system on large dataset | |
CN112603335B (en) | Electroencephalogram emotion recognition method, system, equipment and storage medium | |
CN110786849B (en) | Electrocardiosignal identity recognition method and system based on multi-view discriminant analysis | |
CN109222966A (en) | A kind of EEG signals sensibility classification method based on variation self-encoding encoder | |
CN115211858A (en) | Emotion recognition method and system based on deep learning and storable medium | |
Ma et al. | A classification algorithm of an SSVEP brain-Computer interface based on CCA fusion wavelet coefficients | |
Dzitac et al. | Identification of ERD using fuzzy inference systems for brain-computer interface | |
CN114330422A (en) | Cross-test migration learning method for estimating electroencephalogram emotional characteristics in real time | |
Gnana Rajesh | Analysis of MFCC features for EEG signal classification | |
CN111616680A (en) | Automatic mental load identification method and system | |
CN113907770B (en) | Ratchet composite wave detection and identification method and system based on feature fusion | |
Cheng et al. | Multilevel feature learning method for accurate interictal epileptiform spike detection | |
Wei et al. | Mild cognitive impairment classification convolutional neural network with attention mechanism | |
Kelati et al. | Machine learning for semg facial feature characterization | |
CN113017648A (en) | Electroencephalogram signal identification method and system |
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 |