CN108209909A - Bimodulus spy's nerve signal feature selection approach based on action intention task - Google Patents
Bimodulus spy's nerve signal feature selection approach based on action intention task Download PDFInfo
- Publication number
- CN108209909A CN108209909A CN201711395683.5A CN201711395683A CN108209909A CN 108209909 A CN108209909 A CN 108209909A CN 201711395683 A CN201711395683 A CN 201711395683A CN 108209909 A CN108209909 A CN 108209909A
- Authority
- CN
- China
- Prior art keywords
- feature
- eeg signals
- selection approach
- action intention
- blood oxygen
- 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.)
- Pending
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]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
- A61B5/14553—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases specially adapted for cerebral tissue
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Neurology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Optics & Photonics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of feature extracting methods of bimodal (EEG signals/near infrared signal) brain machine interface system based on action intention task.For EEG signals, frequency domain character, temporal signatures, spatial model feature are considered respectively, based on linear discriminant analysis, choose the highest spatial model feature of discrimination.For near infrared signal, Variance feature, amplitude average absolute value tag, sharp peaks characteristic are considered respectively, based on linear discriminant analysis, choose the highest amplitude average absolute value tag of discrimination.The present invention provides beneficial feature for the bimodal brain machine interface system based on action intention task.
Description
Technical field
The invention belongs to brain-computer interface (brain-computer interfaces, BCI) field, it particularly relates to
It acts and EEG signals and the validity feature of near infrared signal is chosen in intention task.
Background technology
Brain is the material base of all advanced behaviors of the mankind, is made of a large amount of nerve cells, cynapse and spongiocyte, this
A little nerve cells are not carrying out spontaneous, rhythmicity, comprehensive electrical activity all the time, and the electric field of generation is led through volume
Potential distribution is formed after body conduction on scalp, this electric potential signal using the time as axis is brain electricity
(electroencephalograph, EEG) signal.During brain carries out cognitive activities, activate contained by the blood flow of brain area
Some oxygen can be significantly increased, and the transmission of oxygen is using the hemoglobin in blood, so oxygenated haemoglobin
(oxygenated hemoglobin, HbO) concentration improves, deoxyhemoglobin (deoxygenated hemoglobin, HbR)
Concentration reduces.Near infrared spectrum is imaged (near-infrared spectroscopy, NIRS) based on oxygenated haemoglobin with taking off
Oxygen hemoglobin is sent out using past brain for the difference of the absorbability feature of near infrared spectrum wave band and absorbs several classes of wavelength
Infrared light the activity of brain is presented indirectly.
Among social interactions, when people are when others' behavior is observed, the physical motion of this behavior can be not only perceived,
And can independently understand the intention of behavior behind according to the environment and being associated with for behavioral agent and target of surrounding, it is such
Behavior is generally termed as being intended to read (intention reading) or action is intended to understand (intention
understanding).Using certain machine learning method, can by complicated EEG signals and near infrared signal with it is specific
The action relevant feature extraction of intention task comes out, and then relevant action is intended to be differentiated and be applied.
Existing most of bimodal feature extracting methods mainly for language learning, Mental imagery, audiovisual stimulation,
The feature extraction of psychological levels did not accounted for the bimodal feature extraction based on action intention task.In view of the above problems, this
Invention proposes bimodulus spy's nerve signal feature selection approach based on action intention task, the feature choosing including EEG signals
It selects, the feature selecting of near infrared signal.
Invention content
The technical problem to be solved by the present invention is to：In order to realize sentencing for the bimodal nerve signal based on action intention task
It does not apply, the present invention provides EEG signals and the feature selection approach of near infrared signal, and the spatial model for extracting EEG signals is special
The amplitude average absolute value tag near infrared signal of seeking peace, the action intent classifier for being conducive to obtain higher discrimination differentiate.
The present invention solve its technical problem solution be：EEG signals feature selecting side based on action intention task
Method, it is characterised in that：Include the following steps：Step 1: EEG signals are pre-processed；Step 2: extraction EEG signals
Frequency domain character；Step 3: the temporal signatures of extraction EEG signals；Step 4: the spatial model feature of extraction EEG signals；Step
5th, the feature selecting of EEG signals.
Specifically, the specific method of the step 1 is：Utilize independent component analysis (independent component
Analysis, ICA) method, what EEG signals were carried out with artefact filters out processing.
Specifically, the specific method of the step 2 is：Event-related desynchronization/event the phase for being intended to have according to action
Synchronous (event-related desynchronization/synchronization, ERD/ERS) phenomenon is closed, different is dynamic
Make intention task and embody difference on Evoked ptential, calculate the power spectrum of 8~30Hz frequency bands, the frequency domain for extracting EEG signals is special
Sign.
Specifically, the specific method of the step 3 is：EEG signals are done with Short Time Fourier Transform (short time
Fouriertransform, STFT), the spectrum distribution under different moments is obtained, and then the time-frequency collection of illustrative plates for obtaining EEG signals is special
Sign.
Specifically, the specific method of the step 4 is：Utilize common space pattern (common spatial
Patterns, CSP) algorithm extraction EEG signals spatial model feature.
Specifically, the specific method of the step 5 is：Utilize linear discriminant analysis (linear discriminant
Analysis, LDA) method respectively classifies to the frequency domain character of said extracted, temporal signatures, spatial model feature.According to
Experimental result chooses the highest spatial model feature of discrimination as the feature used in bimodal brain machine interface system.
Based on the near infrared signal feature selection approach of action intention task, include the following steps：Step 1: blood oxygen is believed
It number is pre-processed；Step 2: calculate the Variance feature of blood oxygen variation；Step 3: the amplitude for calculating blood oxygen variation is average exhausted
To being worth (mean absolute value, MAV) feature；Step 4: calculate the sharp peaks characteristic of blood oxygen variation；Step 5: near-infrared
The feature selecting of signal.
Specifically, the specific method of the step 1 is：Baseline drift and bandpass filtering (0.02 are carried out near infrared signal
~0.1Hz) processing.
Specifically, the specific method of the step 2 is：Calculate the Variance feature of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
Specifically, the specific method of the step 3 is：Calculate the MAV features of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
Specifically, the specific method of the step 4 is：The sharp peaks characteristic of blood oxygen variation is calculated, the amplitude of variation is considering
The maximum instantaneous value reached in time interval, as peak value.
Specifically, the specific method of the step 5 is：Using LDA methods respectively to the Variance feature of said extracted, MAV
Feature, sharp peaks characteristic are classified.According to experimental result, the highest MAV features of discrimination are chosen as bimodal brain-computer interface
The feature used in system.
The beneficial effects of the invention are as follows：The present invention consider based on action intention task EEG signals time space frequency feature and
The blood oxygen variation characteristic of near infrared signal chooses optimal differentiation feature, is connect for the bimodal brain machine based on action intention task
Port system provides beneficial feature.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described.Obviously, described attached drawing is the part of the embodiment of the present invention rather than all implements
Example, those skilled in the art without creative efforts, can also be obtained according to these attached drawings other designs
Scheme and attached drawing.
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the access diagram used when near-infrared data acquire in the embodiment of the present invention；
Fig. 3 is the discrimination of three kinds of different characteristics of EEG signals；
Fig. 4 is the discrimination of three kinds of different characteristics of near infrared signal.
Specific embodiment
The technique effect of the design of the present invention, concrete structure and generation is carried out below with reference to embodiment and attached drawing clear
Chu is fully described by, to be completely understood by the purpose of the present invention, feature and effect.Obviously, described embodiment is this hair
Bright part of the embodiment rather than whole embodiments.Based on the embodiment of the present invention, those skilled in the art is not paying
The other embodiment obtained under the premise of creative work, belongs to the scope of protection of the invention.In addition, be previously mentioned in text
All connection/connection relations not singly refer to component and directly connect, and refer to be added deduct by adding according to specific implementation situation
Few couple auxiliary, to form more preferably coupling structure.Each technical characteristic in the invention, in not conflicting conflict
Under the premise of can be with combination of interactions.
The present invention will be described in detail with example below in conjunction with the accompanying drawings, and flow chart is as shown in Figure 1.In the present embodiment altogether
Include the eeg data and near-infrared data 10 subjects about the action intention of " hand drinks water by cup " and " hand movement cup ".
For the harvester of data set as shown in Fig. 2, wherein EEG signals use 64 channels, near infrared signal uses 48 channels.It is real
The task of testing is to understand action to be intended to " hand drinks water by cup " or " hand movement cup ".When the sound for sending out " drop " reminds subject real
Starting is tested, occurs symbol "+" among computer screen, it is for 6 seconds, then occur a cup picture among screen, continue 0.5
Second, then the stimulation picture of " hand drinks water by cup " or " hand movement cup " is presented in screen at random, continues 3.5 seconds, by the 10th second,
Picture is stimulated to disappear, a single experiment terminates.Experiment (understands " hand drinks water by cup " meaning 28 times comprising 56 single experiments altogether
Figure understands " hand movement cup " intention for 28 times).Each single experiment moderate stimulation picture occurs at random, and the cup color of appearance is total to
There are seven kinds, the influence for being intended to understand to action to avoid cup color.Single experiment signal can be by the matrix table of N × C dimension
Show, wherein N represents sampled point number in single experiment, and C represents number of active lanes.
Based on the EEG signals feature selection approach of action intention task, follow the steps below.
EEG signals are pre-processed：Using independent component analysis (independent component analysis,
ICA) method, what EEG signals were carried out with artefact filters out processing.ICA algorithm makees EEG signals independent component analysis, obtains more
A independent derived components artefact ingredient zero setting, and then carry out ICA inverse transformations, obtain the EEG signals rebuild.
Extract the frequency domain character of EEG signals：Event-related desynchronization/the event-related design for being intended to have according to action
(event-related desynchronization/synchronization, ERD/ERS) phenomenon, different actions are intended to
Task embodies the difference on Evoked ptential, and occurrence frequency concentrates on μ rhythm (8-14Hz) and beta response (14-30Hz).If xN
(n) it is the EEG signals containing N number of sampled point, Fourier is done to it and converts to obtain XN(ejw), the square value for calculating its amplitude removes
With N, the power spectrum P (e of 8~30Hz frequency bands are calculatedjw), extract the frequency domain characters of EEG signals.
Extract the temporal signatures of EEG signals：EEG signals are done with Short Time Fourier Transform (short time
Fouriertransform, STFT), the spectrum distribution under different moments is obtained, and then the time-frequency collection of illustrative plates for obtaining EEG signals is special
Sign.
Extract the spatial model feature of EEG signals：Using common space pattern (common spatial patterns,
CSP) the spatial model feature of algorithm extraction EEG signals.CSP is the extracting method of effective, classical spatial model feature, it
The quotient of two class signal variances reaches maximum or minimum after being projected by space projection EEG signals, and then portrays multichannel
The difference of the strength fluctuation of EEG signals.In solution, simultaneous diagonalization sample variance matrix or generalized eigen decomposition can be passed through
It carries out.
The feature selecting of EEG signals：Using linear discriminant analysis (linear discriminant analysis,
LDA) method respectively classifies to the frequency domain character of said extracted, temporal signatures, spatial model feature.LDA is a kind of
Common grader, it seeks a projective transformation so that scattering reaches maximum and scattered in class reach minimum simultaneously between class.If
SBAnd SWCollision matrix in collision matrix and class is represented between class respectively, then i.e. seek projection matrix W meets formula to LDALDA graders are trained using the feature of training data extraction, are classified
Face, and then classify, and export class label to the feature of test data, record discrimination.Fig. 3 is shown based on LDA points
Class device is classified obtained discrimination respectively using frequency domain character, temporal signatures, spatial model feature.It can from experimental result
See, spatial model feature contains best discriminant information.So as to choose the highest spatial model feature of discrimination as bimodal
The feature used in brain machine interface system.
Based on the near infrared signal feature selection approach of action intention task, follow the steps below.
Blood oxygen signal is pre-processed：Baseline drift and bandpass filtering (0.02~0.1Hz) are carried out near infrared signal
Processing.
Calculate the Variance feature of blood oxygen variation：Calculate the Variance feature of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
Calculate amplitude average absolute value (mean absolute value, MAV) feature of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
Calculate the sharp peaks characteristic of blood oxygen variation：The sharp peaks characteristic of blood oxygen variation is calculated, the amplitude of variation is between the time is considered
Every the interior maximum instantaneous value reached, as peak value.
The feature selecting of near infrared signal：Using LDA methods respectively to the Variance feature of said extracted, MAV features, peak value
Feature is classified.Fig. 4 is shown to be classified based on LDA graders using Variance feature, MAV features, sharp peaks characteristic respectively
The discrimination obtained.From experimental result as it can be seen that MAV features contain best discriminant information.It is highest so as to choose discrimination
MAV features are as the feature used in bimodal brain machine interface system.
The better embodiment of the present invention is illustrated, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent modifications under the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent modifications or replacement are all contained in the application claim limited range.
Claims (10)
1. the EEG signals feature selection approach based on action intention task, it is characterised in that：Include the following steps：
Step 1: EEG signals are pre-processed；
Step 2: the frequency domain character of extraction EEG signals；
Step 3: the temporal signatures of extraction EEG signals；
Step 4: the spatial model feature of extraction EEG signals；
Step 5: the feature selecting of EEG signals.
2. the EEG signals feature selection approach according to claim 1 based on action intention task, it is characterised in that：Institute
Stating the specific method of step 1 is：Utilize independent component analysis (independent component analysis, ICA) side
Method, what EEG signals were carried out with artefact filters out processing.
3. the EEG signals feature selection approach according to claim 1 based on action intention task, it is characterised in that：Institute
Stating the specific method of step 2 is：Event-related desynchronization/event-related design (the event- for being intended to have according to action
Related desynchronization/synchronization, ERD/ERS) phenomenon, the power of calculating 8~30Hz frequency bands
Spectrum extracts the frequency domain character of EEG signals.
4. the EEG signals feature selection approach according to claim 1 based on action intention task, it is characterised in that：Institute
Stating the specific method of step 3 is：EEG signals are done Short Time Fourier Transform (short time fourier transform,
STFT), the spectrum distribution under different moments is obtained, and then obtains the time-frequency TuPu method of EEG signals.
5. the EEG signals feature selection approach according to claim 1 based on action intention task, it is characterised in that：Institute
Stating the specific method of step 4 is：Brain is extracted using common space pattern (common spatial patterns, CSP) algorithm
The spatial model feature of electric signal.
6. the EEG signals feature selection approach according to claim 1 based on action intention task, it is characterised in that：Institute
Stating the specific method of step 5 is：Utilize linear discriminant analysis (linear discriminant analysis, LDA) method point
It is other to classify to the frequency domain character of said extracted, temporal signatures, spatial model feature, choose the highest spatial model of discrimination
Feature is as the feature used in bimodal brain machine interface system.
7. the near infrared signal feature selection approach based on action intention task, it is characterised in that：Include the following steps：
Step 1: blood oxygen signal is pre-processed；
Step 2: calculate the Variance feature of blood oxygen variation；
Step 3: calculate amplitude average absolute value (mean absolute value, MAV) feature of blood oxygen variation；
Step 4: calculate the sharp peaks characteristic of blood oxygen variation；
Step 5: the feature selecting of near infrared signal.
8. the near infrared signal feature selection approach according to claim 7 based on action intention task, it is characterised in that：
The specific method of the step 1 is：Baseline drift and bandpass filtering (0.02~0.1Hz) processing are carried out near infrared signal.
9. the near infrared signal feature selection approach according to claim 7 based on action intention task, it is characterised in that：
The specific method of the step 2 is：Calculate the Variance feature of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
10. the near infrared signal feature selection approach according to claim 7 based on action intention task, feature exist
In：The specific method of the step 3 is：Calculate the MAV features of blood oxygen variation：
Wherein x is the blood oxygen signal of some channel, and N is sampled point number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711395683.5A CN108209909A (en) | 2017-12-21 | 2017-12-21 | Bimodulus spy's nerve signal feature selection approach based on action intention task |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711395683.5A CN108209909A (en) | 2017-12-21 | 2017-12-21 | Bimodulus spy's nerve signal feature selection approach based on action intention task |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108209909A true CN108209909A (en) | 2018-06-29 |
Family
ID=62647633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711395683.5A Pending CN108209909A (en) | 2017-12-21 | 2017-12-21 | Bimodulus spy's nerve signal feature selection approach based on action intention task |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108209909A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109730648A (en) * | 2019-02-14 | 2019-05-10 | 深兰科技（上海）有限公司 | A kind of movement execution method and device |
| CN110135357A (en) * | 2019-05-17 | 2019-08-16 | 西南大学 | A kind of happiness real-time detection method based on long-range remote sensing |
| CN110569727A (en) * | 2019-08-06 | 2019-12-13 | 华南理工大学 | Transfer learning method combining intra-class distance and inter-class distance based on motor imagery classification |
| CN110955330A (en) * | 2019-11-22 | 2020-04-03 | 燕山大学 | Complex object control-based high-arousal-degree electroencephalogram intention distinguishing method |
| CN113712574A (en) * | 2021-09-03 | 2021-11-30 | 上海诺诚电气股份有限公司 | Electroencephalogram biofeedback rehabilitation method and system |
-
2017
- 2017-12-21 CN CN201711395683.5A patent/CN108209909A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109730648A (en) * | 2019-02-14 | 2019-05-10 | 深兰科技（上海）有限公司 | A kind of movement execution method and device |
| CN110135357A (en) * | 2019-05-17 | 2019-08-16 | 西南大学 | A kind of happiness real-time detection method based on long-range remote sensing |
| CN110569727A (en) * | 2019-08-06 | 2019-12-13 | 华南理工大学 | Transfer learning method combining intra-class distance and inter-class distance based on motor imagery classification |
| CN110569727B (en) * | 2019-08-06 | 2022-03-29 | 华南理工大学 | Transfer learning method combining intra-class distance and inter-class distance for motor imagery classification |
| CN110955330A (en) * | 2019-11-22 | 2020-04-03 | 燕山大学 | Complex object control-based high-arousal-degree electroencephalogram intention distinguishing method |
| CN113712574A (en) * | 2021-09-03 | 2021-11-30 | 上海诺诚电气股份有限公司 | Electroencephalogram biofeedback rehabilitation method and system |
| CN113712574B (en) * | 2021-09-03 | 2022-06-21 | 上海诺诚电气股份有限公司 | Brain electrical biofeedback rehabilitation method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Nakanishi et al. | Enhancing detection of SSVEPs for a high-speed brain speller using task-related component analysis | |
| CN108209909A (en) | Bimodulus spy's nerve signal feature selection approach based on action intention task | |
| Wang et al. | Analysis and classification of speech imagery EEG for BCI | |
| Tong et al. | Quantitative EEG analysis methods and clinical applications | |
| Ramadan et al. | Basics of brain computer interface | |
| Schaaff et al. | Towards emotion recognition from electroencephalographic signals | |
| Li et al. | Emotion recognition using physiological signals | |
| Makeig et al. | A natural basis for efficient brain-actuated control | |
| Li et al. | Classification of single-trial electroencephalogram during finger movement | |
| Kong et al. | EEG fingerprints: phase synchronization of EEG signals as biomarker for subject identification | |
| Alyasseri et al. | The effects of EEG feature extraction using multi-wavelet decomposition for mental tasks classification | |
| CN103019382B (en) | A kind of brain-machine interface method utilizing Evoked ptential to reflect brain subjective motivation signal | |
| Calibo et al. | Cognitive stress recognition | |
| Revett | Cognitive biometrics: A novel approach to person authentication | |
| US11016567B1 (en) | Letter and number recognition system using EEG-fNIRS for speech impaired people | |
| CN106502410A (en) | Improve the transcranial electrical stimulation device of Mental imagery ability and method in brain-computer interface | |
| Wang et al. | Improvement of mental tasks with relevant speech imagery for brain-computer interfaces | |
| Wang et al. | Practical designs of brain–computer interfaces based on the modulation of EEG rhythms | |
| Singh et al. | Emotion recognition using electroencephalography (EEG): a review | |
| Rivet et al. | “P300 speller” Brain-Computer Interface: Enhancement of P300 evoked potential by spatial filters | |
| Hu et al. | Multi-feature fusion method based on WOSF and MSE for four-class MI EEG identification | |
| Smith | Electroencephalograph based brain computer interfaces | |
| Ren et al. | Affective assessment of computer users based on processing the pupil diameter signal | |
| Touyama et al. | Non-target photo images in oddball paradigm improve EEG-based personal identification rates | |
| Jiang et al. | Single-trial ERP detecting for emotion recognition |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180629 |
|
| RJ01 | Rejection of invention patent application after publication |