CN116910625A - Accurate brain-computer signal monitoring and identifying method - Google Patents
Accurate brain-computer signal monitoring and identifying method Download PDFInfo
- Publication number
- CN116910625A CN116910625A CN202310925209.8A CN202310925209A CN116910625A CN 116910625 A CN116910625 A CN 116910625A CN 202310925209 A CN202310925209 A CN 202310925209A CN 116910625 A CN116910625 A CN 116910625A
- Authority
- CN
- China
- Prior art keywords
- brain
- computer
- signal
- decomposition
- signals
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 166
- 239000011159 matrix material Substances 0.000 claims abstract description 122
- 238000012545 processing Methods 0.000 claims abstract description 48
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 239000013598 vector Substances 0.000 claims description 24
- 230000009471 action Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 20
- 238000013507 mapping Methods 0.000 claims description 20
- 238000005070 sampling Methods 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 15
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000002087 whitening effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 210000004556 brain Anatomy 0.000 abstract description 17
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 210000004237 neck muscle Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
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
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Psychology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The application relates to the technical field of brain-computer signal monitoring and recognition, and discloses a precise brain-computer signal monitoring and recognition method, which comprises the following steps: carrying out eigenmode decomposition on the pretreated brain-computer signal, and reconstructing the eigenmode decomposition signal to obtain a reconstructed brain-computer signal; performing maximum variance processing on the reconstructed brain-computer signals to obtain a brain-computer signal projection matrix; and extracting features of the brain-computer signal projection matrix to obtain brain-computer signal features, identifying brain-computer signals based on the brain-computer signal features, and marking the brain-computer signals identified by the brain-computer signals as effective brain-computer signals. According to the application, the brain-computer signals are subjected to eigenmode decomposition to obtain decomposition results of different modal decomposition scales, the identification of non-brain-electrical-signal information in the acquired brain-computer signals is realized based on the distribution degree of the decomposition results, the non-brain-electrical-signal information is weakened in the reconstruction process, the enhancement of brain electrical signals is realized, and the accuracy of monitoring and identifying the brain-computer signals is improved.
Description
Technical Field
The application relates to the technical field of brain-computer signal monitoring and recognition, in particular to a precise brain-computer signal monitoring and recognition method.
Background
The brain-computer interface is a man-machine interaction mode for directly carrying out information transmission between the human brain and the computer equipment, and does not need participation of human muscles, so that man-machine interaction is simpler and faster. The motor imagery brain-computer interface can realize the control of equipment only by depending on virtual motor imagery, and is widely applied to a plurality of fields such as brain cognitive science, medical rehabilitation, life entertainment and the like. However, the current motor imagery brain-computer signal has the problems of low brain-electrical signal induction quality, partial dimension characteristic loss during the extraction of brain-electrical signal characteristics, difficult characteristic selection and the like. Aiming at the problem, the application provides a brain-computer signal monitoring and identifying method for accurately identifying brain-computer signals.
Disclosure of Invention
In view of the above, the application provides a precise brain-computer signal monitoring and identifying method, which aims at: 1) The method comprises the steps of carrying out eigenmode decomposition on a preprocessed brain-computer signal to obtain decomposition results of different mode decomposition scales, comparing the distribution degree of each decomposition result, judging the decomposition result with sharp information as a mixed brain-computer signal decomposition result with other physiological action signals, realizing signal information identification of non-brain-electrical signals in the acquired brain-computer signals, carrying out feature decomposition and feature mapping processing on the mixed brain-computer signals, and realizing mapping of other physiological action signal information in the mixed signal decomposition result to brain-electrical signal information, so as to weaken other physiological action signals in the mixed brain-computer signal to obtain a purer brain-computer signal, realize signal enhancement of the brain-electrical signals in the brain-computer signal and improve the accuracy of monitoring and identification of the brain-computer signal; 2) The brain-computer signal projection matrix which enables the signal value variance in the brain-computer signal to be maximum is obtained by utilizing a matrix diagonalization method, the brain-computer signal is projected based on the brain-computer signal projection matrix, the projection matrix which enables different sampling signal positions to have high distinction is obtained, feature extraction is carried out on the projection matrix, the brain-computer signal feature which represents the sampling signal position feature and the signal value size feature is obtained, and more accurate brain-computer signal identification is realized based on the brain-computer signal feature.
The application provides a precise brain-computer signal monitoring and identifying method, which comprises the following steps:
s1: collecting brain-computer signals and preprocessing the brain-computer signals to obtain preprocessed brain-computer signals;
s2: carrying out eigenmode decomposition on the pretreated brain-computer signal to obtain an eigen decomposition signal of the pretreated brain-computer signal, and reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal;
s3: performing maximum variance processing on the reconstructed brain-computer signals to obtain a brain-computer signal projection matrix;
s4: and extracting features of the brain-computer signal projection matrix to obtain brain-computer signal features, identifying brain-computer signals based on the brain-computer signal features, and marking the brain-computer signals identified by the brain-computer signals as effective brain-computer signals.
As a further improvement of the present application:
optionally, the step S1 of collecting brain-computer signals and preprocessing the brain-computer signals includes:
the brain-computer signal acquisition instrument is used for acquiring brain-computer signals and marking the acquired brain-computer signals as brain-computer signals, wherein the brain-computer signals are expressed in the following form:
X＝(x(1),x(2),...,x(n),...,x(N))
wherein:
x represents brain-computer signals acquired by an electroencephalogram signal acquisition instrument;
x (N) represents the signal value of the nth sampling signal point in the brain-computer signal X, the sampling time interval of two adjacent sampling signal points is deltat, and N represents the total number of sampling signal points of the acquired brain-computer signal;
preprocessing the acquired brain-computer signals, wherein the preprocessing formula is as follows:
y(n)＝ax(n)+(1-a)y(n-1)
a＝ωΔt
wherein:
a is a filter processing coefficient, ω represents a preset cut-off frequency, and ω is set to 1 hz;
y (n) represents the result of the filtering process of the signal value x (n), y (0) =0;
the brain-computer signals after pretreatment are:
Y＝(y(1),y(2),...,y(n),...,y(N))
wherein:
y represents the brain-computer signal after preprocessing.
Optionally, in the step S2, the performing eigenmode decomposition on the preprocessed brain-computer signal includes:
carrying out eigenmode decomposition on the pretreated brain-computer signals, wherein the eigenmode decomposition flow is as follows:
s21: adding a white noise sequence into the pretreated brain-computer signal to obtain a brain-computer signal Y' to be subjected to eigenmode decomposition:
Y′＝Y+σ Y m
wherein:
σ Y the standard deviation of signal values of brain-computer signals Y is represented, and m represents a white noise sequence;
s22: taking the brain-computer signal Y' as an original signal, setting the current modal decomposition scale as J and setting the maximum modal decomposition scale as J;
s23: acquiring all local extremum points of an original signal, and distinguishing a minimum value point and a maximum value point;
s24: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, wherein the interpolation processing result of the minimum value point set is a lower envelope curve, and the interpolation processing result of the maximum value point set is an upper envelope curve;
s25: calculating the average value of the upper envelope line and the lower envelope line, and calculating the difference value between the original signal and the average value; in the embodiment of the application, the average value of the upper envelope line and the lower envelope line and the difference value between the original signal and the average value are all in the signal form of N position points;
if the difference between the zero point number and the local extreme point number of the difference is less than or equal to 1, and the average value of the upper envelope and the lower envelope of the difference is0, the difference value is taken as a decomposition result Y of the brain-computer signal in the modal decomposition scale j j Let j=j+1, decompose result Y j As an original signal, return to step S23 until j=j, where the initial value of J is 1;
otherwise, the difference value is made to be the original signal, and the step S23 is returned;
s26: obtaining decomposition results of J modal decomposition scales, wherein the decomposition results are assembled as follows:
{Y j ＝(y j (1),y j (2),...,y j (n),...,y j (N))|j∈[1,J]}
wherein:
y j (n) represents the decomposition result Y j Signal value of n-th position in the (b);
calculating the distribution degree of each decomposition result, and then decomposing the result Y j Distribution degree B of (2) j The method comprises the following steps:
wherein:
representing the decomposition result Y j Signal value average values of N positions in the middle;
s27: marking the decomposition result with the distribution degree lower than a preset distribution threshold value as a pure brain-computer signal decomposition result, and marking the decomposition result with the distribution degree higher than or equal to the preset distribution threshold value as a mixed brain-computer signal decomposition result with other physiological action signals; in the embodiment of the application, the decomposition results under J modal decomposition scales are intrinsic decomposition signals;
s28: constitute pure brain-machine signal:
wherein:
Y 1 representing clean brain-machine signals, num 1 Representing the number of the decomposition results of the pure brain-computer signals;
Y i 1 and (5) representing the marked i-th pure brain-computer signal decomposition result.
Optionally, reconstructing the eigen decomposition signal in the step S2 to obtain a reconstructed brain-computer signal, including:
reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal, wherein the reconstruction process of the brain-computer signal comprises the following steps:
acquiring a mixed brain-computer signal decomposition result set:
wherein:
representing the labeled result of decomposition of the s-th mixed brain-computer signal, num 2 Representing the number of mixed brain-computer signal decomposition results;
the mixed brain-computer signal Y is formed by the combination of the decomposition results of the mixed brain-computer signals 2 ：
Wherein:
y 2 (n) represents the hybrid brain-computer signal Y 2 Signal value of n-th position in the (b);
construction of Mixed brain-computer Signal Y 2 Is a conversion matrix a of (a):
wherein:
t represents the transpose, trace (&) represents the trace of the computation matrix;
conversion toPerforming feature decomposition on the matrix A to obtain the maximum num of the conversion matrix A 2 Feature vectors corresponding to the feature values:
wherein:
α s representing a feature vector corresponding to the s-th large feature value of the conversion matrix A;
for num in order of distribution degree from low to high 2 The mixed brain-computer signal decomposition results are sequenced, and the mapping processing is carried out on each mixed brain-computer signal decomposition result by combining the feature vector, wherein the mapping processing formula is as follows:
Y 2 (s)′＝α s ·Y 2 (s)
wherein:
representing a matrix dot product;
Y 2 (s) represents the decomposition result of the s-th mixed brain-computer signal after sequencing, Y 2 (s)' represents Y 2 Mapping the result of(s);
calculation of Y 2 Degree of distribution of(s)' if Y 2 The distribution degree of(s)' is less than 1.5, Y is reserved 2 (s)', otherwise delete Y 2 (s)′；
Accumulating the reserved mapping processing results to obtain a mixed brain-computer signal Y without other physiological action signals 3 And obtaining a reconstruction result of brain-computer signals:
Y″＝Y 1 +Y 3
wherein:
y' represents the reconstruction result of brain-computer signals. In the embodiment of the application, Y' represents a pure brain electrical signal from which other physiological action signals except brain electrical signals are removed, wherein the other physiological action signals comprise head and neck muscle action signals, eye electrical signals, heartbeat signals and the like.
Optionally, the performing the maximum variance processing on the reconstructed brain-computer signal in the step S3 includes:
performing maximum variance processing on the reconstructed brain-computer signal Y '', wherein the maximum variance processing flow is as follows:
s31: constructing a conversion matrix C of Y':
s32: performing feature decomposition on the conversion matrix C, and arranging feature values and feature vectors corresponding to the feature values according to the descending order of the feature values:
(λ 1 ,λ 2 ,...,λ k ,...,λ K )
β＝(β 1 ,β 2 ,...,β k ,...,β K )
wherein:
λ k represents the kth largest eigenvalue, beta, obtained by eigenvalue decomposition of the transformation matrix C k As a characteristic value lambda k The corresponding feature vector, K represents the total number of decomposition of the preset feature value;
beta represents a eigenvector matrix obtained by performing eigenvalue decomposition on the conversion matrix C;
will (lambda) 1 ,λ 2 ,...,λ k ,...,λ K ) As the diagonal value, constructing and obtaining a diagonal matrix lambda;
s33: calculating to obtain a whitening matrix D of the brain-computer signal Y':
s34: let matrix z=dcd T ；
S35: performing feature decomposition processing on the matrix Z, and sequencing K feature values according to the descending order of the feature values to obtain a feature vector matrix beta of the matrix Z Z ；
S36: and constructing and obtaining a brain-computer signal projection matrix:
W＝(β Z ) T D
wherein:
w represents the brain-computer signal projection matrix. In the embodiment of the application, a brain-computer signal projection matrix which enables the signal value variance in the brain-computer signal to be maximum is obtained through a matrix diagonalization method, the brain-computer signal is projected based on the brain-computer signal projection matrix, the projection matrix which enables different sampling signal positions to have high distinction degree is obtained, and the feature extraction is carried out on the projection matrix, so that the brain-computer signal feature which represents the sampling signal position feature and the signal value size feature is obtained.
Optionally, in the step S4, feature extraction is performed on the brain-computer signal projection matrix to obtain brain-computer signal features, including:
performing feature extraction on the brain-computer signal projection matrix W to obtain brain-computer signal features F, wherein the feature extraction flow is as follows:
s41: using brain-computer signal projection matrix to project brain-computer signal Y':
G＝W*Y″
wherein:
g represents a projection matrix, x represents a convolution operation;
s42: calculating to obtain a g-th value F (g) in the brain-computer signal characteristic F:
wherein:
var (G, G) represents the variance of the G-th row in the projection matrix G, G ε [1, row (G) ], row (G) represents the total number of rows of the projection matrix G;
s43: the brain-machine signal characteristics f= (F (1), F (2), F (G), F (row (G)) are constituted.
Optionally, in the step S4, brain-computer signal identification is performed based on brain-computer signal characteristics, and the brain-computer signal identified by the brain-computer signal is marked as an effective brain-computer signal, which includes:
and calculating cosine similarity between the brain electrical signal characteristics F and the real brain electrical signal characteristics, and marking Y' as an effective brain-computer signal if the similarity is higher than a preset threshold value, so as to realize monitoring and identification of the brain-computer signal, wherein the real brain electrical signal characteristics are preset brain electrical signal characteristics from the real brain electrical signal. In the embodiment of the application, the extraction flow of the real electroencephalogram signal characteristics is the characteristic extraction flow of the steps S3-S4.
In order to solve the above-described problems, the present application provides an electronic apparatus including:
a memory storing at least one instruction;
the communication interface is used for realizing the communication of the electronic equipment; a kind of electronic device with high-pressure air-conditioning system
And the processor executes the instructions stored in the memory to realize the accurate brain-computer signal monitoring and identifying method.
In order to solve the above-mentioned problems, the present application further provides a computer readable storage medium, in which at least one instruction is stored, the at least one instruction being executed by a processor in an electronic device to implement the above-mentioned accurate brain-computer signal monitoring and identifying method.
Compared with the prior art, the application provides a precise brain-computer signal monitoring and identifying method, which has the following advantages:
firstly, the scheme provides a decomposition and reconstruction method of brain-computer signals, wherein the distribution degree of each decomposition result is calculated by carrying out eigenmode decomposition on the brain-computer signals, and then the decomposition result Y i Distribution degree B of (2) i The method comprises the following steps:
wherein:representing the decomposition result Y j Signal value average values of N positions in the middle; marking the decomposition result with the distribution degree lower than a preset distribution threshold value as a pure brain-computer signal decomposition result, and marking the decomposition result with the distribution degree higher than or equal to the preset distribution threshold value as a mixed brain-computer signal decomposition result with other physiological action signals; constitute pure brain-machine signal:
wherein: y is Y 1 Representing clean brain-machine signals, num 1 Representing the number of the decomposition results of the pure brain-computer signals; y is Y i 1 And (5) representing the marked i-th pure brain-computer signal decomposition result. Reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal, wherein the reconstruction process of the brain-computer signal comprises the following steps: acquiring a mixed brain-computer signal decomposition result set:
wherein:representing the labeled result of decomposition of the s-th mixed brain-computer signal, num 2 Representing the number of mixed brain-computer signal decomposition results; the mixed brain-computer signal Y is formed by the combination of the decomposition results of the mixed brain-computer signals 2 ：
Wherein: y is 2 (n) represents the hybrid brain-computer signal Y 2 Signal value of n-th position in the (b); construction of Mixed brain-computer Signal Y 2 Is a conversion matrix a of (a):
wherein: t represents the transpose, trace (&) represents the trace of the computation matrix; performing feature decomposition on the conversion matrix A to obtain the maximum num of the conversion matrix A 2 Feature vectors corresponding to the feature values:
wherein: alpha s Representing a feature vector corresponding to the s-th large feature value of the conversion matrix A; for num in order of distribution degree from low to high 2 The mixed brain-computer signal decomposition results are sequenced, and the mapping processing is carried out on each mixed brain-computer signal decomposition result by combining the feature vector, wherein the mapping processing formula is as follows:
Y 2 (s)′＝α s ·Y 2 (s)
wherein: representing a matrix dot product; y is Y 2 (s) represents the decomposition result of the s-th mixed brain-computer signal after sequencing, Y 2 (s)' represents Y 2 Mapping the result of(s); calculation of Y 2 Degree of distribution of(s)' if Y 2 The distribution degree of(s)' is less than 1.5, Y is reserved 2 (s)', otherwise delete Y 2 (s)'; accumulating the reserved mapping processing results to obtain a mixed brain-computer signal Y without other physiological action signals 3 And obtaining a reconstruction result of brain-computer signals:
Y″＝Y 1 +Y 3
wherein: y' represents the reconstruction result of brain-computer signals. According to the scheme, according to decomposition results of different modal decomposition scales, the distribution degree of each decomposition result is compared, the decomposition result with sharp information is judged to be a mixed brain-computer signal decomposition result with other physiological action signals, signal information identification of non-brain-computer signals in the acquired brain-computer signals is realized, characteristic decomposition and characteristic mapping processing are carried out on the mixed brain-computer signals, mapping from other physiological action signal information in the mixed signal decomposition result to brain-computer signal information is realized, weakening processing is carried out on other physiological action signals in the mixed brain-computer signals, a purer brain-computer signal is obtained, signal enhancement of brain-computer signals in the brain-computer signals is realized, and accuracy of brain-computer signal monitoring identification is improved
Meanwhile, the scheme provides a brain-computer signal characteristic extraction method, which constructs a transformation matrix C of brain-computer signals Y':
performing feature decomposition on the conversion matrix C, and arranging feature values and feature vectors corresponding to the feature values according to the descending order of the feature values:
(λ 1 ,λ 2 ,...,λ k ,...,λ K )
β＝(β 1 ,β 2 ,...,β k ,...,β K )
wherein: lambda (lambda) k Represents the kth largest eigenvalue, beta, obtained by eigenvalue decomposition of the transformation matrix C k As a characteristic value lambda k Corresponding feature vectors; beta represents a eigenvector matrix obtained by performing eigenvalue decomposition on the conversion matrix C; will (lambda) 1 ,λ 2 ,...,λ k ,...,λ K ) As the diagonal value, constructing and obtaining a diagonal matrix lambda; calculating to obtain a whitening matrix D of the brain-computer signal Y':
let matrix z=dcd T The method comprises the steps of carrying out a first treatment on the surface of the Performing feature decomposition processing on the matrix Z, and sequencing K feature values according to the descending order of the feature values to obtain a feature vector matrix beta of the matrix Z Z The method comprises the steps of carrying out a first treatment on the surface of the And constructing and obtaining a brain-computer signal projection matrix:
W＝(β Z ) T D
wherein: w represents the brain-computer signal projection matrix. Performing feature extraction on the brain-computer signal projection matrix W to obtain brain-computer signal features F, wherein the feature extraction flow is as follows: using brain-computer signal projection matrix to project brain-computer signal Y':
G＝W*Y″
wherein: g represents a projection matrix, x represents a convolution operation; calculating to obtain a g-th value F (g) in the brain-computer signal characteristic F:
wherein: var (G, G) represents the variance of the G-th row in the projection matrix G, G ε [1, row (G) ], row (G) represents the total number of rows of the projection matrix G; the brain-machine signal characteristics f= (F (1), F (2), F (G), F (row (G)) are constituted. According to the scheme, a brain-computer signal projection matrix which enables signal value variance in brain-computer signals to be maximum is obtained by solving a matrix diagonalization method, brain-computer signals are projected based on the brain-computer signal projection matrix, projection matrixes which enable different sampling signal positions to have high distinction degree are obtained, feature extraction is carried out on the projection matrixes, brain-computer signal features which represent sampling signal position features and signal value size features are obtained, and more accurate brain-computer signal identification is achieved based on the brain-computer signal features.
Drawings
FIG. 1 is a flow chart of a method for monitoring and identifying brain-computer signals according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an electronic device for implementing a method for monitoring and identifying accurate brain-computer signals according to an embodiment of the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application provides a precise brain-computer signal monitoring and identifying method. The execution subject of the accurate brain-computer signal monitoring and identifying method includes, but is not limited to, at least one of a server, a terminal and the like capable of being configured to execute the method provided by the embodiment of the application. In other words, the accurate brain-computer signal monitoring and identifying method may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Example 1:
s1: and acquiring brain-computer signals and preprocessing the brain-computer signals to obtain preprocessed brain-computer signals.
And in the step S1, brain-computer signals are collected and preprocessed, and the method comprises the following steps:
the brain-computer signal acquisition instrument is used for acquiring brain-computer signals and marking the acquired brain-computer signals as brain-computer signals, wherein the brain-computer signals are expressed in the following form:
X＝(x(1),x(2),...,x(n),...,x(N))
wherein:
x represents brain-computer signals acquired by an electroencephalogram signal acquisition instrument;
x (N) represents the signal value of the nth sampling signal point in the brain-computer signal X, the sampling time interval of two adjacent sampling signal points is deltat, and N represents the total number of sampling signal points of the acquired brain-computer signal;
preprocessing the acquired brain-computer signals, wherein the preprocessing formula is as follows:
y(n)＝ax(n)+(1-a)y(n-1)
a＝ωΔt
wherein:
a is a filter processing coefficient, ω represents a preset cut-off frequency, and ω is set to 1 hz;
y (n) represents the result of the filtering process of the signal value x (n), y (0) =0;
the brain-computer signals after pretreatment are:
Y＝(y(1),y(2),...,y(n),...,y(N))
wherein:
y represents the brain-computer signal after preprocessing.
S2: and carrying out eigenmode decomposition on the preprocessed brain-computer signals to obtain eigen decomposition signals of the preprocessed brain-computer signals, and reconstructing the eigen decomposition signals to obtain reconstructed brain-computer signals.
And in the step S2, carrying out eigenmode decomposition on the preprocessed brain-computer signals, wherein the eigenmode decomposition comprises the following steps:
carrying out eigenmode decomposition on the pretreated brain-computer signals, wherein the eigenmode decomposition flow is as follows:
s21: adding a white noise sequence into the pretreated brain-computer signal to obtain a brain-computer signal Y' to be subjected to eigenmode decomposition:
Y′＝Y+σ Y m
wherein:
σ Y the standard deviation of signal values of brain-computer signals Y is represented, and m represents a white noise sequence;
s22: taking the brain-computer signal Y' as an original signal, setting the current modal decomposition scale as J and setting the maximum modal decomposition scale as J;
s23: acquiring all local extremum points of an original signal, and distinguishing a minimum value point and a maximum value point;
s24: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, wherein the interpolation processing result of the minimum value point set is a lower envelope curve, and the interpolation processing result of the maximum value point set is an upper envelope curve;
s25: calculating the average value of the upper envelope line and the lower envelope line, and calculating the difference value between the original signal and the average value; in the embodiment of the application, the average value of the upper envelope line and the lower envelope line and the difference value between the original signal and the average value are all in the signal form of N position points;
if the difference between the zero point number and the local extreme point number of the difference is less than or equal to 1 and the average value of the upper envelope and the lower envelope of the difference is 0, the difference is taken as a decomposition result Y of the brain-computer signal in the modal decomposition scale j j Let j=j+1, decompose result Y j As an original signal, return to step S23 until j=j, where the initial value of J is 1;
otherwise, the difference value is made to be the original signal, and the step S23 is returned;
s26: obtaining decomposition results of J modal decomposition scales, wherein the decomposition results are assembled as follows:
{Y j ＝(y j (1),y j (2),...,y j (n),...,y j (N))|j∈[1,J]}
wherein:
y j (n) represents the decomposition result Y j Signal value of n-th position in the (b);
calculating the distribution degree of each decomposition result, and then decomposing the result Y j Distribution degree B of (2) j The method comprises the following steps:
wherein:
representing the decomposition result Y j Signal value average values of N positions in the middle;
s27: marking the decomposition result with the distribution degree lower than a preset distribution threshold value as a pure brain-computer signal decomposition result, and marking the decomposition result with the distribution degree higher than or equal to the preset distribution threshold value as a mixed brain-computer signal decomposition result with other physiological action signals;
s28: constitute pure brain-machine signal:
wherein:
Y 1 representing clean brain-machine signals, num 1 Representing the number of the decomposition results of the pure brain-computer signals;
Y i 1 and (5) representing the marked i-th pure brain-computer signal decomposition result.
And in the step S2, the eigen decomposition signal is reconstructed to obtain a reconstructed brain-computer signal, which comprises the following steps:
reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal, wherein the reconstruction process of the brain-computer signal comprises the following steps:
acquiring a mixed brain-computer signal decomposition result set:
wherein:
representing the labeled result of decomposition of the s-th mixed brain-computer signal, num 2 Representing the number of mixed brain-computer signal decomposition results;
the mixed brain-computer signal Y is formed by the combination of the decomposition results of the mixed brain-computer signals 2 ：
Wherein:
y 2 (n) represents the hybrid brain-computer signal Y 2 Signal value of n-th position in the (b);
construction of Mixed brain-computer Signal Y 2 Is a conversion matrix a of (a):
wherein:
t represents the transpose, trace (&) represents the trace of the computation matrix;
performing feature decomposition on the conversion matrix A to obtain the maximum num of the conversion matrix A 2 Feature vectors corresponding to the feature values:
wherein:
α s representing a feature vector corresponding to the s-th large feature value of the conversion matrix A;
for num in order of distribution degree from low to high 2 The mixed brain-computer signal decomposition results are sequenced, and the mapping processing is carried out on each mixed brain-computer signal decomposition result by combining the feature vector, wherein the mapping processing formula is as follows:
Y 2 (s)′＝α s ·Y 2 (s)
wherein:
representing a matrix dot product;
Y 2 (s) represents the decomposition result of the s-th mixed brain-computer signal after sequencing, Y 2 (s)' represents Y 2 Mapping the result of(s);
calculation of Y 2 Degree of distribution of(s)' if Y 2 The distribution degree of(s)' is less than 1.5, Y is reserved 2 (s)', otherwise delete Y 2 (s)′；
Accumulating the reserved mapping processing results to obtain a mixed brain-computer signal Y without other physiological action signals 3 And obtaining a reconstruction result of brain-computer signals:
Y″＝Y 1 +Y 3
wherein:
y' represents the reconstruction result of brain-computer signals. In the embodiment of the application, Y' represents a pure brain electrical signal from which other physiological action signals except brain electrical signals are removed, wherein the other physiological action signals comprise head and neck muscle action signals, eye electrical signals, heartbeat signals and the like.
S3: and performing maximum variance processing on the reconstructed brain-computer signals to obtain a brain-computer signal projection matrix.
And (3) performing maximum variance processing on the reconstructed brain-computer signal in the step (S3), wherein the method comprises the following steps:
performing maximum variance processing on the reconstructed brain-computer signal Y', wherein the maximum variance processing flow is as follows:
s31: constructing a conversion matrix C of Y':
s32: performing feature decomposition on the conversion matrix C, and arranging feature values and feature vectors corresponding to the feature values according to the descending order of the feature values:
(λ 1 ,λ 2 ,...,λ k ,...,λ K )
β＝(β 1 ,β 2 ,...,β k ,...,β K )
wherein:
λ k representing counter-rotationThe matrix C is changed to obtain the kth largest eigenvalue, beta by eigenvalue decomposition k As a characteristic value lambda k The corresponding feature vector, K represents the total number of decomposition of the preset feature value;
beta represents a eigenvector matrix obtained by performing eigenvalue decomposition on the conversion matrix C;
will (lambda) 1 ,λ 2 ,...,λ k ,...,λ K ) As the diagonal value, constructing and obtaining a diagonal matrix lambda;
s33: calculating to obtain a whitening matrix D of a brain-computer signal Y '':
s34: let matrix z=dcd T ；
S35: performing feature decomposition processing on the matrix Z, and sequencing K feature values according to the descending order of the feature values to obtain a feature vector matrix beta of the matrix Z Z ；
S36: and constructing and obtaining a brain-computer signal projection matrix:
W＝(β z ) T D
wherein:
w represents the brain-computer signal projection matrix.
S4: and extracting features of the brain-computer signal projection matrix to obtain brain-computer signal features, identifying brain-computer signals based on the brain-computer signal features, and marking the brain-computer signals identified by the brain-computer signals as effective brain-computer signals.
And in the step S4, feature extraction is carried out on the brain-computer signal projection matrix to obtain brain-computer signal features, which comprises the following steps:
performing feature extraction on the brain-computer signal projection matrix W to obtain brain-computer signal features F, wherein the feature extraction flow is as follows:
s41: using brain-computer signal projection matrix to project brain-computer signal Y':
G＝W*Y′′
wherein:
g represents a projection matrix, x represents a convolution operation;
s42: calculating to obtain a g-th value F (g) in the brain-computer signal characteristic F:
wherein:
var (G, G) represents the variance of the G-th row in the projection matrix G, G ε [1, row (G) ], row (G) represents the total number of rows of the projection matrix G;
s43: the brain-machine signal characteristics f= (F (1), F (2), F (G), F (row (G)) are constituted.
And step S4, performing brain-computer signal identification based on brain-computer signal characteristics, marking the brain-computer signal identified by the brain-computer signal as an effective brain-computer signal, and comprising the following steps:
and calculating cosine similarity between the brain electrical signal characteristics F and the real brain electrical signal characteristics, and marking Y' as an effective brain-computer signal if the similarity is higher than a preset threshold value, so as to realize monitoring and identification of the brain-computer signal, wherein the real brain electrical signal characteristics are preset brain electrical signal characteristics from the real brain electrical signal. In the embodiment of the application, the extraction flow of the real electroencephalogram signal characteristics is the characteristic extraction flow of the steps S3-S4.
Example 2:
fig. 2 is a schematic structural diagram of an electronic device for implementing a method for monitoring and identifying accurate brain-computer signals according to an embodiment of the present application.
The electronic device 1 may comprise a processor 10, a memory 11, a communication interface 13 and a bus, and may further comprise a computer program, such as program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of the program 12, but also for temporarily storing data that has been output or is to be output.
The processor 10 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, and the like. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects respective parts of the entire electronic device using various interfaces and lines, executes or executes programs or modules (a program 12 for realizing accurate brain-computer signal monitoring and recognition, etc.) stored in the memory 11, and invokes data stored in the memory 11 to perform various functions of the electronic device 1 and process the data.
The communication interface 13 may comprise a wired interface and/or a wireless interface (e.g. WI-FI interface, bluetooth interface, etc.), typically used to establish a communication connection between the electronic device 1 and other electronic devices and to enable connection communication between internal components of the electronic device.
The bus may be a peripheral component interconnect standard (peripheral component interconnect, PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. The bus is arranged to enable a connection communication between the memory 11 and at least one processor 10 etc.
Fig. 2 shows only an electronic device with components, it being understood by a person skilled in the art that the structure shown in fig. 2 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or may be arranged in different components.
For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for supplying power to each component, and preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that functions of charge management, discharge management, power consumption management, and the like are implemented through the power management device. The power supply may also include one or more of any of a direct current or alternating current power supply, recharging device, power failure detection circuit, power converter or inverter, power status indicator, etc. The electronic device 1 may further include various sensors, bluetooth modules, wi-Fi modules, etc., which will not be described herein.
The electronic device 1 may optionally further comprise a user interface, which may be a Display, an input unit, such as a Keyboard (Keyboard), or a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The program 12 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
collecting brain-computer signals and preprocessing the brain-computer signals to obtain preprocessed brain-computer signals;
carrying out eigenmode decomposition on the pretreated brain-computer signal to obtain an eigen decomposition signal of the pretreated brain-computer signal, and reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal;
performing maximum variance processing on the reconstructed brain-computer signals to obtain a brain-computer signal projection matrix;
and extracting features of the brain-computer signal projection matrix to obtain brain-computer signal features, identifying brain-computer signals based on the brain-computer signal features, and marking the brain-computer signals identified by the brain-computer signals as effective brain-computer signals.
Specifically, the specific implementation method of the above instruction by the processor 10 may refer to descriptions of related steps in the corresponding embodiments of fig. 1 to 2, which are not repeated herein.
It should be noted that, the foregoing reference numerals of the embodiments of the present application are merely for describing the embodiments, and do not represent the advantages and disadvantages of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. The accurate brain-computer signal monitoring and identifying method is characterized by comprising the following steps:
s1: collecting brain-computer signals and preprocessing the brain-computer signals to obtain preprocessed brain-computer signals;
s2: carrying out eigenmode decomposition on the pretreated brain-computer signal to obtain an eigen decomposition signal of the pretreated brain-computer signal, and reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal;
s3: performing maximum variance processing on the reconstructed brain-computer signals to obtain a brain-computer signal projection matrix;
s4: and extracting features of the brain-computer signal projection matrix to obtain brain-computer signal features, identifying brain-computer signals based on the brain-computer signal features, and marking the brain-computer signals identified by the brain-computer signals as effective brain-computer signals.
2. The method for monitoring and identifying accurate brain-computer signals according to claim 1, wherein the step S1 of acquiring and preprocessing brain-computer signals comprises the steps of:
the brain-computer signal acquisition instrument is used for acquiring brain-computer signals and marking the acquired brain-computer signals as brain-computer signals, wherein the brain-computer signals are expressed in the following form:
X＝(x(1),x(2),...,x(n),...,x(N))
wherein:
x represents brain-computer signals acquired by an electroencephalogram signal acquisition instrument;
x (N) represents the signal value of the nth sampling signal point in the brain-computer signal X, the sampling time interval of two adjacent sampling signal points is deltat, and N represents the total number of sampling signal points of the acquired brain-computer signal;
preprocessing the acquired brain-computer signals, wherein the preprocessing formula is as follows:
y(n)＝ax(n)+(1-a)y(n-1)
a＝ωΔt
wherein:
a is a filter processing coefficient, ω represents a preset cut-off frequency, and ω is set to 1 hz;
y (n) represents the result of the filtering process of the signal value x (n), y (0) =0;
the brain-computer signals after pretreatment are:
Y＝(y(1),y(2),...,y(n),...,y(N))
wherein:
y represents the brain-computer signal after preprocessing.
3. The method for monitoring and identifying accurate brain-computer signals according to claim 2, wherein the step S2 of performing eigenmode decomposition on the preprocessed brain-computer signals comprises:
carrying out eigenmode decomposition on the pretreated brain-computer signals, wherein the eigenmode decomposition flow is as follows:
s21: adding a white noise sequence into the pretreated brain-computer signal to obtain a brain-computer signal Y' to be subjected to eigenmode decomposition:
Y′＝Y+σ Y m
wherein:
σ Y the standard deviation of signal values of brain-computer signals Y is represented, and m represents a white noise sequence;
s22: taking the brain-computer signal Y' as an original signal, setting the current modal decomposition scale as J and setting the maximum modal decomposition scale as J;
s23: acquiring all local extremum points of an original signal, and distinguishing a minimum value point and a maximum value point;
s24: respectively carrying out interpolation processing on the minimum value point set and the maximum value point set by using a cubic spline interpolation method, wherein the interpolation processing result of the minimum value point set is a lower envelope curve, and the interpolation processing result of the maximum value point set is an upper envelope curve;
s25: calculating the average value of the upper envelope line and the lower envelope line, and calculating the difference value between the original signal and the average value;
if the difference isThe difference between the zero point number and the local extreme point number is less than or equal to 1, and the average value of the upper envelope and the lower envelope of the difference is 0, the difference is taken as a decomposition result Y of the brain-computer signal in the modal decomposition scale j j Let j=j+1, decompose result Y j As an original signal, return to step S23 until j=j, where the initial value of J is 1;
otherwise, the difference value is made to be the original signal, and the step S23 is returned;
s26: obtaining decomposition results of J modal decomposition scales, wherein the decomposition results are assembled as follows:
{Y j ＝(y j (1),y j (2),...,y j (n),...,y j (N))|j∈[1,J]}
wherein:
y j (n) represents the decomposition result Y j Signal value of n-th position in the (b);
calculating the distribution degree of each decomposition result, and then decomposing the result Y j Distribution degree B of (2) j The method comprises the following steps:
wherein:
representing the decomposition result Y j Signal value average values of N positions in the middle;
s27: marking the decomposition result with the distribution degree lower than a preset distribution threshold value as a pure brain-computer signal decomposition result, and marking the decomposition result with the distribution degree higher than or equal to the preset distribution threshold value as a mixed brain-computer signal decomposition result with other physiological action signals;
s28: constitute pure brain-machine signal:
wherein:
Y 1 representing clean brain-machine signals, num 1 Representing the number of the decomposition results of the pure brain-computer signals;
Y i 1 and (5) representing the marked i-th pure brain-computer signal decomposition result.
4. The method for monitoring and identifying accurate brain-computer signals according to claim 3, wherein the reconstructing the eigen-decomposition signal in step S2 to obtain the reconstructed brain-computer signal comprises:
reconstructing the eigen decomposition signal to obtain a reconstructed brain-computer signal, wherein the reconstruction process of the brain-computer signal comprises the following steps:
acquiring a mixed brain-computer signal decomposition result set:
wherein:
representing the labeled result of decomposition of the s-th mixed brain-computer signal, num 2 Representing the number of mixed brain-computer signal decomposition results;
the mixed brain-computer signal Y is formed by the combination of the decomposition results of the mixed brain-computer signals 2 ：
Wherein:
y 2 (n) represents the hybrid brain-computer signal Y 2 Signal value of n-th position in the (b);
construction of Mixed brain-computer Signal Y 2 Is a conversion matrix a of (a):
wherein:
t represents the transpose, trace (&) represents the trace of the computation matrix;
performing feature decomposition on the conversion matrix A to obtain the maximum num of the conversion matrix A 2 Feature vectors corresponding to the feature values:
wherein:
α s representing a feature vector corresponding to the s-th large feature value of the conversion matrix A;
for num in order of distribution degree from low to high 2 The mixed brain-computer signal decomposition results are sequenced, and the mapping processing is carried out on each mixed brain-computer signal decomposition result by combining the feature vector, wherein the mapping processing formula is as follows:
Y 2 (s)′＝α s ·Y 2 (s)
wherein:
representing a matrix dot product;
Y 2 (s) represents the decomposition result of the s-th mixed brain-computer signal after sequencing, Y 2 (s)' represents Y 2 Mapping the result of(s);
calculation of Y 2 Degree of distribution of(s)' if Y 2 The distribution degree of(s)' is less than 1.5, Y is reserved 2 (s)', otherwise delete Y 2 (s)′；
Accumulating the reserved mapping processing results to obtain a mixed brain-computer signal Y without other physiological action signals 3 And obtaining a reconstruction result of brain-computer signals:
Y″＝Y 1 +Y 3
wherein:
y' represents the reconstruction result of brain-computer signals.
5. The method for monitoring and identifying accurate brain-computer signals according to claim 1, wherein the step S3 of performing maximum variance processing on the reconstructed brain-computer signals comprises the following steps:
performing maximum variance processing on the reconstructed brain-computer signal Y', wherein the maximum variance processing flow is as follows:
s31: constructing a conversion matrix C of Y':
s32: performing feature decomposition on the conversion matrix C, and arranging feature values and feature vectors corresponding to the feature values according to the descending order of the feature values:
(λ 1 ,λ 2 ,...,λ k ,...,λ K )
β＝(β 1 ,β 2 ,...,β k ,...,β K )
wherein:
λ k represents the kth largest eigenvalue, beta, obtained by eigenvalue decomposition of the transformation matrix C k As a characteristic value lambda k The corresponding feature vector, K represents the total number of decomposition of the preset feature value;
beta represents a eigenvector matrix obtained by performing eigenvalue decomposition on the conversion matrix C;
will (lambda) 1 ,λ 2 ,...,λ k ,...,λ K ) As the diagonal value, constructing and obtaining a diagonal matrix lambda;
s33: calculating to obtain a whitening matrix D of the brain-computer signal Y':
s34: let matrix z=dcd T ；
S35: performing feature decomposition processing on the matrix Z, and sequencing K feature values according to the descending order of the feature values to obtain a feature vector matrix beta of the matrix Z Z ；
S36: and constructing and obtaining a brain-computer signal projection matrix:
W＝(β Z ) T D
wherein:
w represents the brain-computer signal projection matrix.
6. The method for accurately monitoring and identifying brain-computer signals according to claim 5, wherein in the step S4, feature extraction is performed on a brain-computer signal projection matrix to obtain brain-computer signal features, and the method comprises the following steps:
performing feature extraction on the brain-computer signal projection matrix W to obtain brain-computer signal features F, wherein the feature extraction flow is as follows:
s41: using brain-computer signal projection matrix to project brain-computer signal Y':
G＝W*Y″
wherein:
g represents a projection matrix, x represents a convolution operation;
s42: calculating to obtain a g-th value F (g) in the brain-computer signal characteristic F:
wherein:
var (G, G) represents the variance of the G-th row in the projection matrix G, G ε [1, row (G) ], row (G) represents the total number of rows of the projection matrix G;
s43: the brain-machine signal characteristics f= (F (1), F (2), F (G), F (row (G)) are constituted.
7. The method for monitoring and identifying accurate brain-computer signals according to claim 6, wherein in the step S4, brain-computer signal identification is performed based on brain-computer signal characteristics, and the brain-computer signal identified by the brain-computer signal is marked as an effective brain-computer signal, including:
and calculating cosine similarity between the electroencephalogram signal characteristics F and the real electroencephalogram signal characteristics, and if the similarity is higher than a preset threshold value, marking Y' as an effective brain-computer signal, wherein the real electroencephalogram signal characteristics are preset electroencephalogram signal characteristics from the real electroencephalogram signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925209.8A CN116910625A (en) | 2023-07-26 | 2023-07-26 | Accurate brain-computer signal monitoring and identifying method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310925209.8A CN116910625A (en) | 2023-07-26 | 2023-07-26 | Accurate brain-computer signal monitoring and identifying method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116910625A true CN116910625A (en) | 2023-10-20 |
Family
ID=88366548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310925209.8A Pending CN116910625A (en) | 2023-07-26 | 2023-07-26 | Accurate brain-computer signal monitoring and identifying method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116910625A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743810A (en) * | 2024-02-21 | 2024-03-22 | 莱凯医疗器械(北京)有限公司 | Intended understanding analysis method for electroencephalogram signal monitoring |
-
2023
- 2023-07-26 CN CN202310925209.8A patent/CN116910625A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743810A (en) * | 2024-02-21 | 2024-03-22 | 莱凯医疗器械(北京)有限公司 | Intended understanding analysis method for electroencephalogram signal monitoring |
| CN117743810B (en) * | 2024-02-21 | 2024-04-30 | 莱凯医疗器械(北京)有限公司 | Intended understanding analysis method for electroencephalogram signal monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tuncer et al. | A dynamic center and multi threshold point based stable feature extraction network for driver fatigue detection utilizing EEG signals | |
| CN116910625A (en) | Accurate brain-computer signal monitoring and identifying method | |
| US20230334893A1 (en) | Method for optimizing human body posture recognition model, device and computer-readable storage medium | |
| CN111274937A (en) | Fall detection method and device, electronic equipment and computer-readable storage medium | |
| CN117524427B (en) | Intelligent medical image analysis method | |
| CN117055726A (en) | Micro-motion control method for brain-computer interaction | |
| CN115796231B (en) | Temporal analysis ultra-short term wind speed prediction method | |
| CN111402068B (en) | Premium data analysis method and device based on big data and storage medium | |
| CN116720101A (en) | On-line intelligent monitoring method and device for propeller faults of underwater propeller | |
| CN110889836A (en) | Image data analysis method and device, terminal equipment and storage medium | |
| CN117743810B (en) | Intended understanding analysis method for electroencephalogram signal monitoring | |
| CN118021323A (en) | Electroencephalogram signal identification method based on multi-domain feature fusion | |
| CN114842254B (en) | Image classification method, device, equipment and medium for multi-index fusion of brain function network by taking amygdala as core | |
| CN116522105B (en) | Method, device, equipment and medium for integrally constructing data based on cloud computing | |
| CN116740221B (en) | Method, device, computer equipment and medium for generating real-time brain function activation graph | |
| CN116578864A (en) | Rapid processing method for continuously controlling brain-computer signals | |
| CN113139590B (en) | Dimension reduction method and device for time series data, computer equipment and storage medium | |
| CN115399738B (en) | Rapid ICU false alarm identification method | |
| CN117290806A (en) | Multi-path parallel medical knowledge integration method | |
| CN116486097B (en) | Remote automatic feeding method and system applied to rodent feeding scene | |
| CN116434955A (en) | Staff health state evaluation method and device | |
| CN116701937A (en) | Rapid generation method of brain-computer model training sample | |
| CN115624330A (en) | Electroencephalogram analysis mental stress quantification method | |
| CN117598710A (en) | Remote electrocardiosignal monitoring method and system | |
| CN116822205A (en) | Rapid fault early warning method for multi-dimensional ring main unit |
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 |