CN111158462A - Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model - Google Patents

Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model Download PDF

Info

Publication number
CN111158462A
CN111158462A CN201911193329.3A CN201911193329A CN111158462A CN 111158462 A CN111158462 A CN 111158462A CN 201911193329 A CN201911193329 A CN 201911193329A CN 111158462 A CN111158462 A CN 111158462A
Authority
CN
China
Prior art keywords
electroencephalogram
boundary
task
model
data
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
Application number
CN201911193329.3A
Other languages
Chinese (zh)
Other versions
CN111158462B (en
Inventor
付荣荣
于宝
王世伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yanshan University
Original Assignee
Yanshan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Yanshan University filed Critical Yanshan University
Priority to CN201911193329.3A priority Critical patent/CN111158462B/en
Publication of CN111158462A publication Critical patent/CN111158462A/en
Application granted granted Critical
Publication of CN111158462B publication Critical patent/CN111158462B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
    • 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]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
    • G06F2203/01—Indexing scheme relating to G06F3/01
    • G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
    • 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
    • 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)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Psychiatry (AREA)
  • Psychology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Artificial Intelligence (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Dermatology (AREA)
  • Neurology (AREA)
  • Neurosurgery (AREA)
  • Human Computer Interaction (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The invention provides a method for improving electroencephalogram wakefulness based on implementation of a boundary evasion task, which comprises the steps of establishing a 'cup-ball' dynamic complex model, implementing the boundary evasion task with visual guidance in a virtual environment, collecting electroencephalogram signals of a subject in the process of completing the boundary evasion task, dividing electroencephalogram data into a test set and a training set by taking electroencephalogram classification accuracy as an index for measuring the electroencephalogram wakefulness to be high or low, performing feature optimization on the training data and the test data by using a CSP (chip scale package) algorithm, training a classifier by using the optimized training data to obtain a classification model, and finally verifying the classification performance of the model by using the test data to obtain the classification accuracy. By utilizing the method provided by the invention, the participation degree of the testee is high, the electroencephalogram carrying characteristics are more obvious, the brain level identification precision of the testee is higher than that of a motor imagery task under the condition of less training and testing times, and the electroencephalogram identification effect is still higher under the condition of a small sample.

Description

Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model
Technical Field
The invention relates to the field of biological signal processing, in particular to a method for improving electroencephalogram wakefulness based on a boundary evasion task model.
Background
The electroencephalogram is a graph obtained by amplifying a spontaneous bioelectric potential of the brain from the scalp by a precise electronic instrument and recording the amplified result, and is a spontaneous and rhythmic electrical activity of a brain cell population recorded by an electrode. Has important significance for the evaluation of brain activity and is an important clinical tool for researching the brain functional state and diagnosing and detecting neurological diseases. In the study of the electroencephalogram, a key step is to design a reasonable experimental paradigm to improve the awakening degree of the electroencephalogram.
In the cognitive nerve rehabilitation, a motor imagery paradigm is commonly used for improving the cognitive dysfunction of a stroke patient, and the stroke patient excites the brain electricity by depending on the self imagery in the motor imagery process. However, the simple feedback-free motor imagery paradigm has a large difference in functionality between different subjects, and some potential users have too low brain arousal to achieve feasible control accuracy, which limits its application to some extent.
Disclosure of Invention
The invention aims to provide a method for improving the electroencephalogram arousal level of a subject by adding visual guidance so as to shorten the training time.
In order to solve the problems, the invention provides a method for improving the electroencephalogram wakefulness based on a boundary evasive task model, which comprises the following specific steps:
step 1, establishing a boundary evasion task model:
conceptualizing a mobile water cup scene as a boundary evasion task model, wherein the cup is simplified into a section of arc, water in the cup is simplified into a ball with smaller mass, the radius of the arc is far larger than that of the ball, and the arc and the ball form a dynamic complex system;
step 2, collecting electroencephalogram data, which comprises the following specific steps:
step 21, presenting the boundary avoidance task on a computer by using a function library PsychTolboox;
step 22, in the test process, the left hand and the right hand of the subject respectively knock a left direction key and a right direction key of the computer to control the water cup to do left and right reciprocating motions, the water cup is controlled to convey the ball from the initial position to the target position, if the ball escapes from the water cup in the process, the task is restarted, if the ball does not escape, the task is successful, and electroencephalograms in the subject boundary evasion task are collected in the process;
step 23, preprocessing the acquired electroencephalogram data by a band-pass filter;
and 3, extracting the spatial features of the training set and the test set by using a CSP algorithm, and specifically comprising the following steps:
step 31, grouping the electroencephalogram data of each subject into a test set and a training set, and performing cross validation;
step 32, extracting a group of spatial filters from the training set by using a CSP algorithm, and filtering the training set and the test set by using the spatial filters to obtain spatial features of the training set and the test set;
and 4, deriving a classification model and evaluating the precision, wherein the specific steps are as follows:
step 41, training a classifier by using the spatial features of the training set to obtain a classification model;
step 42, verifying the classification performance of the classification model by using the test set, and obtaining classification precision;
and 43, calculating the average classification precision of the classification precision.
Further, the model equation of motion of the boundary avoidance task model in step 1 is:
Figure BDA0002294120850000021
in the formula, x represents the horizontal position of the water cup, M is the mass of the water cup, M is the mass of the ball, l is the radius of the water cup, F is the external force applied to the model, g is the gravity acceleration, and theta is the included angle between the direction of the radial supporting force of the water cup on the ball and the vertical direction.
Further, in the step 21, the function library psychtools is used to present the boundary avoidance task.
Further, the cut-off frequency of the band-pass filter in the step 23 is 8Hz and 30 Hz.
Further, in step 31, ten-fold cross validation is performed, the electroencephalogram data of each subject is averagely divided into ten groups, the data of each of the ten groups of data is used as the test set, and the data of the remaining 9 groups of the 10 groups is used as the training set.
Further, in step 32, the CSP algorithm extracts the spatial filter by solving the following optimization problem:
Figure BDA0002294120850000031
where, | | · | |, represents the L2-norm, Σ1Sum-sigma2The method comprises the following steps of respectively obtaining spatial covariance matrixes of a first type of electroencephalogram and a second type of electroencephalogram, wherein w is a feature vector to be solved;
extracting eigenvectors corresponding to α maximum eigenvalues and α minimum eigenvalues in the formula to obtain the spatial filter
Figure BDA0002294120850000032
Wherein C is the number of channels for carrying out the electroencephalogram acquisition.
Further, in the step 42, ten-fold cross validation is adopted to obtain 10 classification accuracies.
Compared with the prior art, the invention has the beneficial effects that:
the invention implements the boundary evasion task with visual guidance in a virtual environment by establishing a 'cup-ball' dynamic complex model, and collects electroencephalogram signals of a subject in the process of completing the boundary evasion task. The electroencephalogram classification precision is used as an index for measuring the high or low electroencephalogram arousal level, electroencephalogram data are divided into a test set and a training set, feature optimization is carried out on the training data and the test data through a CSP algorithm, and then a classifier is used for realizing classification of optimized features. By utilizing the method provided by the invention, the participation degree of the testee is high, the electroencephalogram carrying characteristics are more obvious, the brain level identification precision of the testee is higher than that of a motor imagery task under the condition of less training and testing times, and the electroencephalogram identification effect is still higher under the condition of a small sample.
Drawings
FIG. 1 is an overall flow chart in an embodiment of the present invention;
FIG. 2 is a schematic diagram of a water cup and water conceptualized boundary evasive task model employed in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a mechanical model used in an embodiment of the present invention;
FIG. 4 is a force analysis diagram of a model in an embodiment of the invention;
FIG. 5 is a diagram illustrating a boundary avoidance task process in an embodiment of the present invention; and
FIG. 6 is a schematic diagram of an acquisition process of electroencephalogram data according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
The invention discloses a method for improving electroencephalogram wakefulness based on a boundary evasive task model, which has the general flow chart shown in figure 1, and comprises the following steps:
step 1, establishing a boundary evasion task model:
conceptualizing a moving cup scene as a boundary evasive task model, as shown in fig. 2: the cup is simplified into a section of arc, the water in the cup is simplified into a ball with smaller mass, the radius of the arc is far larger than that of the ball, the arc and the ball form a dynamic complex system, the dynamic complex system is called as a boundary evasion task model, and the model is used for simulating the task of actually moving the water cup. Wherein the cup is limited to move linearly along the horizontal direction, when the cup is subjected to a certain force in the horizontal direction, the ball obtains energy to move in the cup, and in a corresponding mechanical model, as shown in fig. 3, x represents the horizontal position of the cup, M and M are the masses of the cup and the ball, respectively, theta is the instantaneous angle of the ball, and theta is the instantaneous angle of the ballESCThen the angle of escape of the ball is represented and l is the radius of the cup. By means of a force analysis diagram of the system, as shown in fig. 4, from whichIt can be seen that when the model is subjected to a certain external force F, the cup and the ball move simultaneously. Analyzing the stress condition of the ball, wherein the water cup has a radial supporting force on the ball except the self gravity, the included angle between the direction and the vertical direction is theta, and the water cup is divided into a horizontal component N and a vertical component P. And (3) establishing a model motion equation through stress analysis of the model:
Figure BDA0002294120850000041
in the formula, x represents the horizontal position of the water cup, M represents the mass of the water cup, M represents the mass of the ball, l represents the radius of the water cup, F represents the external force applied to the model, g represents the gravity acceleration, and theta represents the included angle between the direction of the radial supporting force of the water cup on the ball and the vertical direction.
Step 2, collecting electroencephalogram data:
step 21, virtually presenting the boundary avoidance task on a computer by utilizing a function library PsychTolboox based on a model motion equation;
the computer display interface is as shown in fig. 5, assuming point a as the model initial position and point B as the target position, in the test process, the subject clicks the left and right direction keys with the left and right hands respectively, the cup is controlled to transfer the ball from the position a to the position B, during which the cup moves back and forth, if the ball escapes from the cup in the process, the task is restarted, if no, the task is successful.
As shown in fig. 6, one complete experiment was recorded, one record was completed by 1 subject, and the record started at time 0. Each record comprises an exercise stage (practice) and a plurality of task stages (session), wherein the practice stage is used for training all the subjects related to tasks before the task stage is carried out, so that the subjects can smoothly carry out experiments, and the session is used for controlling the water cup to convey the ball from the position A to the position B. And acquiring electroencephalograms in the boundary evasion task in the process.
And step 22, acquiring electroencephalograms in the boundary avoidance task in the process.
And step 23, preprocessing the acquired electroencephalogram data by a band-pass filter, wherein the cut-off frequency is 8Hz and 30 Hz.
Step 3, CSP extracts the spatial filter:
step 31, executing ten-fold cross validation, averagely dividing the electroencephalogram data of each subject into ten groups, respectively using the data of each group as a test set, and using the data of other groups as a training set;
and 32, extracting a group of spatial filters through the training set by adopting a CSP algorithm, and filtering the training data and the test data by using the group of spatial filters to obtain the spatial characteristics of the training data and the test data.
In this embodiment, the CSP learns the spatial filter that maximizes the variance ratio of the transformed data by solving the following optimization problem:
Figure BDA0002294120850000051
where, | | · | |, represents the L2-norm, Σ1Sum-sigma2The space covariance matrixes of the first type of electroencephalogram and the second type of electroencephalogram respectively, and then the eigenvectors corresponding to α maximum eigenvalues and α minimum eigenvalues in the formula are extracted to form a space filter
Figure BDA0002294120850000052
Is a spatial filter, wherein C is the number of channels for performing the electroencephalogram acquisition. For a given brain electrical sample
Figure BDA0002294120850000053
The spatially filtered signal is:
Figure BDA0002294120850000054
in the formula: w is the spatial filter, E is the given brain electrical sample, and Z is the filtered signal.
In order to prove that the electroencephalogram arousal degree of the boundary avoidance task is higher, 8 tested electroencephalogram data (S1-S8) collected in the boundary avoidance task are compared with the motor imagery data of 4 real tested subjects (Sa, Sb, Sf, Sg) in the BCI competition IV data set 1. In the boundary avoidance task, 120 test electroencephalograms are collected in each test, and 60 times, 14 channels and 128 time points are collected in each type of test. For data set 1 of BCI race IV, 100, 59 channels, 400 time points were collected for each type of trial. And (4) performing feature extraction by adopting a classical CSP (chip size Package). All brain electricity data are preprocessed by a band-pass filter, and the cut-off frequency is 8Hz and 30 Hz. Ten-fold cross validation is performed, electroencephalogram data of each subject are averagely divided into ten groups, data of each group are respectively used as a test set, data of other groups are used as training sets, and then average classification accuracy is calculated. A set of spatial filters is extracted through a training set using the classical CSP algorithm. And filtering the training data and the test data by using the set of spatial filters to obtain the spatial characteristics of the training data and the test data.
And 4, deriving a classification model and evaluating the precision, wherein the specific steps are as follows:
step 41, training a classifier by using the spatial features of the training set to obtain a classification model;
step 42, verifying the classification performance of the classification model by using the test set to obtain classification precision;
and 43, performing cross validation on the ten folds to obtain 10 classification accuracies, and finally calculating the average classification accuracy.
In this embodiment, a supervised algorithm support vector machine is used to classify the electroencephalogram features, so as to obtain the following classification results: the electroencephalogram data set identification precision of the boundary avoidance task is the highest S3, the lowest S7 and the average identification precision of the 8 tested subjects are respectively 98.8% of the tested subjects, 90.5% of the tested subjects and 94.9%. The recognition accuracy of the BCI competition IV data set 1 is 91.1 percent of that of the Sg test, the recognition accuracy of the BCI competition IV data set 1 is 85.1 percent of that of the Sb test, and the average recognition accuracy of the 4 test pieces is 87.6 percent. Compared with the BCI competition IV data set 1, the number of each tested training sample is 90, the number of each tested training sample of the boundary evasion task is 60, and the average identification precision is improved by 7.3%.
The above-mentioned embodiments are merely illustrative of the preferred embodiments of the present invention, and do not limit the scope of the present invention, and various modifications and improvements made to the technical solution of the present invention by those skilled in the art without departing from the spirit of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims (7)

1. A method for improving electroencephalogram wakefulness based on a boundary evasion task model is characterized by comprising the following specific steps:
step 1, establishing a boundary evasion task model:
conceptualizing a mobile water cup scene as a boundary evasion task model, wherein the cup is simplified into a section of arc, water in the cup is simplified into a ball with small mass, the radius of the arc is larger than that of the ball, and the arc and the ball form a dynamic complex system;
step 2, collecting electroencephalogram data, which comprises the following specific steps:
step 21, presenting the boundary avoidance task on a computer by using a function library PsychTolboox;
step 22, in the test process, the left hand and the right hand of the subject respectively knock a left direction key and a right direction key of the computer to control the water cup to do left and right reciprocating motions, the water cup is controlled to convey the ball from the initial position to the target position, if the ball escapes from the water cup in the process, the task is restarted, if the ball does not escape, the task is successful, and the electroencephalogram of the subject in the boundary evasion task is collected in the process;
step 23, preprocessing the acquired electroencephalogram data by a band-pass filter;
step 3, extracting the spatial features of the electroencephalogram data by utilizing a CSP algorithm, and specifically comprising the following steps:
step 31, grouping the electroencephalogram data of each subject into a test set and a training set, and performing cross validation;
step 32, extracting a group of spatial filters from the training set by using a CSP algorithm, and filtering the training set and the test set by using the spatial filters to obtain spatial features of the training set and the test set;
and 4, deriving a classification model and evaluating the precision, wherein the specific steps are as follows:
step 41, training a classifier by using the spatial features of the training set to obtain a classification model;
step 42, verifying the classification performance of the classification model by using the test set, and obtaining classification precision;
and 43, calculating the average classification precision of the classification precision.
2. The method for improving the electroencephalogram wakefulness based on implementation of the boundary evasive task model according to claim 1, wherein the model equation of motion of the boundary evasive task model in the step 1 is as follows:
Figure FDA0002294120840000011
in the formula, x represents the horizontal position of the water cup, M is the mass of the water cup, M is the mass of the ball, l is the radius of the water cup, F is the external force applied to the model, g is the gravity acceleration, and theta is the included angle between the direction of the radial supporting force of the water cup on the ball and the vertical direction.
3. The method for improving the brain wakefulness based on implementation of the boundary avoidance task model according to claim 1, wherein in the step 21, the boundary avoidance task is presented by using a function library psychtools.
4. The method for improving brain electrical arousal level based on implementation of the boundary evasive task model as claimed in claim 1, wherein the cut-off frequency of the band-pass filter in the step 23 is 8Hz and 30 Hz.
5. The method for improving brain electrical arousal level based on implementation of the boundary avoidance task model as claimed in claim 1, wherein the step 31 is implemented by performing ten-fold cross validation, dividing the brain electrical data of each subject into 10 groups on average, using the data of each of the 10 groups as the test set, and using the data of the remaining 9 groups of the 10 groups as the training set.
6. The method for improving brain wave wakefulness based on implementing the boundary evasive task model as claimed in claim 1, wherein in the step 32, the CSP algorithm extracts the spatial filter by solving the following optimization problem:
Figure FDA0002294120840000021
where, | | · | |, represents the L2-norm, Σ1Sum-sigma2The method comprises the following steps of respectively obtaining spatial covariance matrixes of a first type of electroencephalogram and a second type of electroencephalogram, wherein w is a feature vector to be solved;
extracting the eigenvectors corresponding to the α largest and α smallest eigenvalues in the above formula to form the spatial filter
Figure FDA0002294120840000022
Wherein C is the number of channels for carrying out the electroencephalogram acquisition.
7. The method for improving the electroencephalogram wakefulness based on the implementation of the boundary evasive task model according to claim 1, wherein 10 classification accuracies are obtained by adopting ten-fold cross validation in the step 42.
CN201911193329.3A 2019-11-28 2019-11-28 Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model Active CN111158462B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911193329.3A CN111158462B (en) 2019-11-28 2019-11-28 Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911193329.3A CN111158462B (en) 2019-11-28 2019-11-28 Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model

Publications (2)

Publication Number Publication Date
CN111158462A true CN111158462A (en) 2020-05-15
CN111158462B CN111158462B (en) 2021-02-02

Family

ID=70556247

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911193329.3A Active CN111158462B (en) 2019-11-28 2019-11-28 Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model

Country Status (1)

Country Link
CN (1) CN111158462B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104771163A (en) * 2015-01-30 2015-07-15 杭州电子科技大学 Electroencephalogram feature extraction method based on CSP and R-CSP algorithms
CN106362287A (en) * 2016-10-24 2017-02-01 天津大学 Novel MI-SSSEP mixed brain-computer interface method and system thereof
CN108470182A (en) * 2018-01-23 2018-08-31 天津大学 A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification
US10181082B2 (en) * 2017-02-06 2019-01-15 Brown University Method and system for automated behavior classification of test subjects
CN110192874A (en) * 2019-05-24 2019-09-03 中南民族大学 Based on the lie detecting method for more leading the EEG signals nargin factor

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104771163A (en) * 2015-01-30 2015-07-15 杭州电子科技大学 Electroencephalogram feature extraction method based on CSP and R-CSP algorithms
CN106362287A (en) * 2016-10-24 2017-02-01 天津大学 Novel MI-SSSEP mixed brain-computer interface method and system thereof
US10181082B2 (en) * 2017-02-06 2019-01-15 Brown University Method and system for automated behavior classification of test subjects
CN108470182A (en) * 2018-01-23 2018-08-31 天津大学 A kind of brain-computer interface method enhanced for asymmetric brain electrical feature with identification
CN110192874A (en) * 2019-05-24 2019-09-03 中南民族大学 Based on the lie detecting method for more leading the EEG signals nargin factor

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
袁海云: ""基于脑电信号的情绪分类研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Also Published As

Publication number Publication date
CN111158462B (en) 2021-02-02

Similar Documents

Publication Publication Date Title
CN110876626B (en) Depression detection system based on optimal lead selection of multi-lead electroencephalogram
CN107577343B (en) Attention training and evaluation device based on force touch feedback and electroencephalogram signal analysis
Surangsrirat et al. Support vector machine classification of Parkinson's disease and essential tremor subjects based on temporal fluctuation
CN102940490B (en) Method for extracting motor imagery electroencephalogram signal feature based on non-linear dynamics
Pinzón-Arenas et al. Convolutional neural network for hand gesture recognition using 8 different EMG signals
CN105894039A (en) Emotion recognition modeling method, emotion recognition method and apparatus, and intelligent device
CN105184325A (en) Human body action recognition method and mobile intelligent terminal
CN111476158A (en) Multi-channel physiological signal somatosensory gesture recognition method based on PSO-PCA-SVM
CN109009098B (en) Electroencephalogram signal feature identification method under motor imagery state
CN113017645B (en) P300 signal detection method based on void convolutional neural network
CN108985157A (en) A kind of gesture identification method and device
CN107292296A (en) A kind of human emotion wake-up degree classifying identification method of use EEG signals
CN108523883A (en) A kind of continuous Mental imagery identifying system of left and right index finger based on actual act modeling
CN113536882A (en) Multi-class motor imagery electroencephalogram signal feature extraction and classification method
Zhang et al. Upper limb motion capturing and classification for unsupervised stroke rehabilitation
AU2013100576A4 (en) Human Identification with Electroencephalogram (EEG) for the Future Network Security
CN111401435A (en) Human body motion mode identification method based on motion bracelet
CN111259741A (en) Electroencephalogram signal classification method and system
CN112698720B (en) Movement imagery identification method based on mutual information feature extraction and multi-person fusion
CN111158462B (en) Method for improving electroencephalogram wakefulness based on implementation boundary evasion task model
CN108962379B (en) Mobile phone auxiliary detection system for cranial nerve system diseases
CN116541751A (en) Electroencephalogram signal classification method based on brain function connection network characteristics
CN110705656A (en) Facial action recognition method based on EEG sensor
US11937934B2 (en) EEG decoding method based on a non-negative CP decomposition model
CN111297366A (en) Data processing method and diagnosis device for assisting disease diagnosis based on daily necessities

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