CN114869299A - Mental health testing device and testing method based on electroencephalogram data - Google Patents
Mental health testing device and testing method based on electroencephalogram data Download PDFInfo
- Publication number
- CN114869299A CN114869299A CN202210703996.7A CN202210703996A CN114869299A CN 114869299 A CN114869299 A CN 114869299A CN 202210703996 A CN202210703996 A CN 202210703996A CN 114869299 A CN114869299 A CN 114869299A
- Authority
- CN
- China
- Prior art keywords
- brain wave
- data
- matrix
- mental health
- mental
- 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
- 230000004630 mental health Effects 0.000 title claims abstract description 46
- 238000012360 testing method Methods 0.000 title claims abstract description 38
- 210000004556 brain Anatomy 0.000 claims abstract description 89
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 230000003068 static effect Effects 0.000 claims abstract description 10
- 230000005611 electricity Effects 0.000 claims abstract description 3
- 239000011159 matrix material Substances 0.000 claims description 55
- 238000012549 training Methods 0.000 claims description 28
- 230000003340 mental effect Effects 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 14
- 239000013598 vector Substances 0.000 claims description 14
- 230000003542 behavioural effect Effects 0.000 claims description 10
- 230000009323 psychological health Effects 0.000 claims description 9
- 230000002087 whitening effect Effects 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 230000006399 behavior Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000036541 health Effects 0.000 claims description 7
- 208000019901 Anxiety disease Diseases 0.000 claims description 6
- 206010010219 Compulsions Diseases 0.000 claims description 6
- 206010012335 Dependence Diseases 0.000 claims description 6
- 230000036506 anxiety Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000354 decomposition reaction Methods 0.000 claims description 6
- 230000002996 emotional effect Effects 0.000 claims description 6
- 230000000763 evoking effect Effects 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 208000036119 Frailty Diseases 0.000 claims description 3
- 206010022998 Irritability Diseases 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 206010003549 asthenia Diseases 0.000 claims description 3
- 238000005311 autocorrelation function Methods 0.000 claims description 3
- 238000005314 correlation function Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 229940074869 marquis Drugs 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 claims description 3
- VBUNOIXRZNJNAD-UHFFFAOYSA-N ponazuril Chemical compound CC1=CC(N2C(N(C)C(=O)NC2=O)=O)=CC=C1OC1=CC=C(S(=O)(=O)C(F)(F)F)C=C1 VBUNOIXRZNJNAD-UHFFFAOYSA-N 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 238000000844 transformation Methods 0.000 claims description 3
- 230000007177 brain activity Effects 0.000 abstract description 3
- 230000008451 emotion Effects 0.000 description 4
- 238000010998 test method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000009223 counseling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
- A61B5/374—Detecting the frequency distribution of signals, e.g. detecting delta, theta, alpha, beta or gamma waves
-
- 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]
- A61B5/386—Accessories or supplementary instruments therefor
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Psychiatry (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Psychology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- Educational Technology (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Fuzzy Systems (AREA)
- Hospice & Palliative Care (AREA)
- Evolutionary Computation (AREA)
- Social Psychology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a mental health testing device and a testing method based on electroencephalogram data, which comprises the following steps: the main machine is connected with a brain wave acquisition electrode and an electrostatic bracelet, and the brain wave acquisition electrode is used for acquiring brain wave data; the static bracelet is used for absorbing static electricity; the host computer is used for extracting mental health related electroencephalogram characteristics from electroencephalogram data, outputting concentration degree, relaxation degree parameters and electroencephalogram parameters, establishing a normal range, and reflecting the mental health condition of a tested person from a plurality of dimensions. The invention can accurately analyze and output the brain wave parameters based on the brain wave signals generated by brain activity acquisition, and simultaneously analyze and calculate the mental health state of the tested person by depending on the brain wave algorithm and the brain wave big data.
Description
Technical Field
The invention belongs to the technical field of mental health testing, and particularly relates to a mental health testing device and a testing method based on brain wave data.
Background
The mental health refers to that all aspects and the activity process of the psychology are in a good or normal state, the ideal state of the mental health is the state of perfect maintenance, normal intelligence, correct cognition, proper emotion, reasonable mind, positive attitude, proper behavior and good adaptation, the mental health is influenced by both heredity and environment, especially the teaching and maintenance mode of primary families in the young period has great influence on the development of the mental health, the mental health is prominent in social interaction, production and life, and the mental health can be well communicated or matched with other people, so that various conditions occurring in life can be well treated. With the progress of society, psychological tests and psychological counseling are more and more accepted by the public, and psychological health conditions are obtained through a psychological test method.
Psychological tests refer to the general term of mental activities of a person, including the psychological phenomena of feeling, perception, memory, thinking, imagination, attention, emotion, intelligence, temperament, character, etc. of a person. Psychological tests are widely applied in psychological research and clinical consultation, but the existing psychological test method generally adopts a mode of performing questionnaire survey by using a scale, and the mode is greatly influenced by individual subjectivity, so that the estimation of the psychological health degree is inaccurate.
Disclosure of Invention
In order to solve the problems in the prior art, a mental health testing device and a testing method based on electroencephalogram data are provided.
The technical scheme adopted by the invention for solving the technical problems is as follows:
this technical scheme has provided mental health testing arrangement based on brain wave data, includes: a main machine connected with a brain wave collecting electrode and an electrostatic hand ring,
the brain wave acquisition electrode is used for acquiring brain wave data;
the static bracelet is used for absorbing static electricity;
the main machine is used for extracting mental health related electroencephalogram characteristics from electroencephalogram data, outputting concentration degree, relaxation degree parameters and electroencephalogram parameters, establishing a normal range, and reflecting the mental health condition of a tested person from a plurality of dimensions.
Preferably, the dimension comprises basic psychological data, health psychological data, safety psychological data, interpersonal psychological data and behavior psychological data;
the basic psychological data includes sense of security, emotional acceptance, mental elasticity, and emotional output;
the health psychological data includes exogenous anxiety, endogenous anxiety, pleasure addiction and discharge addiction;
safety psychological data include right-brain depression, left-brain depression, frailty index, and marquis index;
the social psychological data comprises thought self-closing, thought compulsion, entanglement indexes and irritability indexes;
behavioral psychology data packet behavioral self-closure, behavioral compulsion, fear index and behavioral response.
A test method of a mental health test device based on brain wave data comprises the following steps:
extracting brain wave features related to mental health according to the brain wave data to obtain a mental database;
creating a standard normal mode range according to the mental database;
according to the brain wave signal of the tested person, converting the brain wave signal into a digital signal through analog-to-digital conversion, and transmitting the digital signal to a host computer, wherein the host computer adopts spectral analysis, wavelet, pattern recognition and nonlinear complexity algorithm to obtain a cluster of multi-dimensional quantitative marking numerical values related to each calculation window of the brain wave, then obtains a plurality of dimensions related to the mental health condition through multivariate linear regression and fuzzy recognition calculation, and analyzes to obtain a normal mode value related to the mental health of the tested person;
and comparing the normal value related to the psychological health of the tested person with the standard normal range to obtain the psychological health condition of the tested person, and automatically generating an evaluation report according to the data result.
Preferably, the host stores basic information of the testee, and the host collects brain wave information of the testee through the brain wave collecting electrodes by playing a picture with sound to the testee;
selecting a certain stress training task, wherein the stress training task comprises a plurality of stress pictures, and the testee wears the brain wave acquisition electrode and the electrostatic wristband to finish so as to start stress training;
after a stress training task starts, acquiring brain wave information in real time through a brain wave acquisition electrode in a stress picture flow, judging whether to adjust the playing sequence of the stress picture according to the brain wave information acquired in real time, analyzing by a host according to the acquired brain wave signals to obtain a constant modulus value related to the psychological health of a tested person after the stress picture flow is finished, and then generating a stress training file and reporting and outputting an evaluation report.
Preferably, the brain wave information reading method includes:
suppose X 1 And X 2 The multi-channel evoked response space-time signal matrixes are respectively under two stress training tasks, the dimensionalities of the multi-channel evoked response space-time signal matrixes are N x T, wherein N is the number of electroencephalogram channels, T is the number of samples collected by each channel, and N is assumed to be less than T;
wherein S is 1 And S 2 Respectively represent two stress training tasks, S 1 Is formed by m 1 Constituted by individual sources, S 2 Is formed by m 2 A source is composed of 1 And C 2 From S 1 And S 2 M of correlation 1 And m 2 A common spatial pattern, each spatial pattern being an N x 1-dimensional vector, which is now used to represent the distributed weights of the signals on the N leads caused by the signals of the individual signal sources, C M Is represented by the formula M A respective common spatial pattern;
(11) solving a mixed space covariance matrix:
X 1 and X 2 Normalized covariance matrix R 1 And R 2 Respectively as follows:
wherein, X T Represents the transpose of the X matrix, trace (X) represents the sum of the elements on the diagonal of the matrix, and then the mixture spatial covariance matrix R:
wherein,
respectively is an average covariance matrix of two stress training task experiments;
(12) solving a whitening eigenvalue matrix P:
and (3) carrying out eigenvalue decomposition on the mixed spatial covariance matrix R according to the formula:
R＝UλU T (4)
wherein, U is an eigenvector matrix of matrix lambda, lambda is a diagonal matrix formed by corresponding eigenvalues, the eigenvalues are arranged in descending order, and a whitening value matrix P is
(13) Constructing a spatial filter:
to R 1 And R 2 The following transformations are performed:
S 1 ＝PR 1 P T ,S 2 ＝PR 2 P T (6)
then to S 1 And S 2 And performing principal component decomposition to obtain:
the matrix S is proved by the above formula 1 The eigenvector sum matrix S 2 Is characterized byThe vector matrices are equal, i.e.:
B 1 ＝B 2 ＝V (8)
at the same time, a diagonal matrix λ of two eigenvalues 1 And λ 2 The sum is the identity matrix, i.e.:
λ 1 +λ 2 ＝I (9)
since the sum of the eigenvalues of the two types of matrices is always 1, S is 1 The feature vector corresponding to the maximum feature value of (1) makes S 2 Has the smallest characteristic value;
lambda is measured 1 The eigenvalues in (1) are arranged in descending order, then λ 2 In ascending order, to infer lambda 1 And λ 2 Having the form:
λ 1 ＝diag(I 1 σ M 0),λ 2 ＝diag(0σ M I 2 ) (10)
whitening brain wave to lambda 1 And λ 2 The transformation of the eigenvector corresponding to the largest eigenvalue in (a) is optimal for separating the variances in the two signal matrices, the projection matrix W is the corresponding spatial filter:
W＝B T P (11)
(14) feature extraction:
the motor imagery matrix X of the training set L 、X R The characteristic Z can be obtained by filtering through the corresponding constructed filter W L 、Z R Comprises the following steps:
Z L ＝W×X L ,Z R ＝W×X R (12)
according to the definition of the extraction of the characteristics of the multi-electrode acquired electroencephalogram signals, f is selected L And f R To imagine the left and right feature vectors, the following is defined:
for test data X i In the case of a composite material, for example,its feature vector f i The extraction method is as follows, and L and f R Comparing to determine the ith imagine as imagined left and imagined right;
finding f of the test i And (5) performing corresponding classification.
Preferably, the wavelet algorithm comprises:
j ═ 0,1,2, …; k belongs to Z and is called cj, and k is a discrete wavelet transform coefficient, which is called wavelet coefficient for short;
get a 0 ＝1，b 0 When a is equal to 1, the value of a is 20,21, …,2j, and the basis function ψ ab (t) in the continuous wavelet transform is denoted as ψ jk (t);
accordingly, the discrete wavelet transform is represented as
Preferably, the distribution of the brain wave signal power at each frequency point is represented by a concept of density, which is a measure of a mean square value of a random variable, and the method specifically comprises the following steps:
s1: x (N) is an infinite length random sequence, and the truncated length N is changed into a finite length sequence which is called XN (N);
s2: calculating an autocorrelation function RX (m) of XN (n) at the point (2 m-1);
s3: and solving Fourier transform of the correlation function to obtain a power spectrum:
wherein M is- (M-1) …, -1, 0,1, …, M-1, and M is less than or equal to N.
Compared with the prior art, the invention has the following advantages:
according to the invention, based on the brain wave signals generated by brain activity acquisition, concentration degree, relaxation parameters, delta, theta, alpha, beta, gamma and other brain wave parameters are accurately analyzed and output, and training is carried out by adopting various brain wave feedback modes such as games, music, images and the like, so that the goals of improving attention, emotion management, relieving psychological stress, easy learning and high-efficiency work are realized, meanwhile, the mental health state of a tested person is analyzed and calculated by depending on a brain wave algorithm and brain wave big data, and compared with the form of question and answer of a scale, the method does not need to answer the question and scale, can effectively eliminate subjective interference, and thus improves the accuracy of psychological test; according to the method, the electroencephalogram characteristics related to mental health are extracted from electroencephalogram data, a normal range is established, and the mental health condition of a tested person is reflected by 5 dimensions of basic mental data, health mental data, safety mental data, interpersonal mental data and behavior mental data.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is an overall flow chart of the present invention;
fig. 2 is a schematic illustration of an electroencephalogram reading of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
The embodiment provides a testing method of a mental health testing device based on brain wave data, and the mental health testing device based on the brain wave data comprises the following steps:
a main machine which is connected with a brain wave collecting electrode and an electrostatic hand ring,
when the brain wave acquisition device is used, the brain wave acquisition motor is worn on the head of a tested person, and the brain wave acquisition electrode is used for acquiring brain wave data.
The static bracelet can be worn on the wrist, and the static bracelet is used for absorbing static to prevent static interference brain wave.
The host computer is used for extracting mental health related electroencephalogram characteristics from electroencephalogram data, outputting concentration degree, relaxation degree parameters and electroencephalogram parameters, establishing a normal range, and reflecting the mental health condition of a tested person from a plurality of dimensions.
The brain wave collecting electrode collects brain wave signals generated by brain activities, accurately analyzes and outputs concentration degree Attention and relaxation degree position parameters and brain wave EEG parameters such as delta, theta, alpha, beta and gamma, and the like, and adopts various brain wave feedback modes such as games, music, images and the like to train so as to achieve the aims of improving Attention, managing emotion, relieving psychological pressure, easily learning and efficiently working.
The brain wave acquisition positions are as follows: left brain (guide electrode Fp1Z, reference electrode a1), right brain (guide electrode Fp2, reference electrode a2, zero electrode Ppz).
The dimensionality comprises basic psychological data, health psychological data, safety psychological data, interpersonal psychological data and behavior psychological data;
the basic psychological data includes sense of security, emotional acceptance, mental elasticity, and emotional output;
the health psychological data includes exogenous anxiety, endogenous anxiety, pleasure addiction and discharge addiction;
safety psychological data include right-brain depression, left-brain depression, frailty index, and marquis index;
the social psychological data comprises thought self-closing, thought compulsion, entanglement indexes and irritability indexes;
behavioral psychology data packet behavioral self-closure, behavioral compulsion, fear index and behavioral response.
The test method comprises the following steps:
extracting brain wave features related to mental health according to the brain wave data to obtain a mental database;
creating a standard normal range according to the mental database;
according to the brain wave signal of the tested person, converting the brain wave signal into a digital signal through analog-to-digital conversion, and transmitting the digital signal to a host computer, wherein the host computer adopts spectral analysis, wavelet, pattern recognition and nonlinear complexity algorithm to obtain a cluster of multi-dimensional quantitative marking numerical values related to each calculation window of the brain wave, then obtains a plurality of dimensions related to the mental health condition through multivariate linear regression and fuzzy recognition calculation, and analyzes to obtain a normal mode value related to the mental health of the tested person;
and comparing the normal value related to the psychological health of the tested person with the standard normal range to obtain the psychological health condition of the tested person, and automatically generating an evaluation report according to the data result.
The main machine is used for collecting the brain wave information of the testee through the brain wave collecting electrodes by playing a picture with sound to the testee.
The host machine also comprises a display screen and an operable keyboard and mouse, the information of the testee can be input through the keyboard and mouse, the information of the testee can be displayed on the display screen, and an evaluation report can be automatically generated according to the tested result.
Selecting a certain stress training task, wherein the stress training task comprises a plurality of stress pictures, and the testee wears the brain wave acquisition electrode and the electrostatic wristband to finish so as to start stress training;
after a stress training task starts, acquiring brain wave information in real time through brain wave acquisition electrodes in a stress picture flow, judging whether to adjust the playing sequence of the stress picture according to the brain wave information acquired in real time, analyzing by a host according to the acquired brain wave signals to obtain a constant modulus value related to the mental health of a tested person after the stress picture flow is finished, and then generating a stress training file and reporting to output an evaluation report.
The brain wave collecting electrode specifically comprises a bioelectricity sensor which can convert physiological information of a human body into electric information with a determined functional relation with the physiological information.
The brain electrical signals are finally converted into original data of brain waves by a series of means such as differential amplification, filtering, digital-to-analog conversion and the like, and the data are in scattered wave shapes.
The biggest difficulty in brain wave reading is reading precision. In addition to channel enhancement and precision improvement on the device, the problems of solving the precision need to be solved by using an electroencephalogram algorithm.
The brain wave information reading method comprises the following steps:
suppose X 1 And X 2 The multi-channel evoked response space-time signal matrixes are respectively under two stress training tasks, the dimensionalities of the multi-channel evoked response space-time signal matrixes are N x T, wherein N is the number of electroencephalogram channels, T is the number of samples collected by each channel, and N is assumed to be less than T;
wherein S is 1 And S 2 Respectively represent two stress training tasks, S 1 Is formed by m 1 Constituted by individual sources, S 2 Is formed by m 2 A source is composed of 1 And C 2 From S 1 And S 2 M of correlation 1 And m 2 A common spatial pattern, each spatial pattern being an N x 1-dimensional vector, which is now used to represent the distributed weights of the signals on the N leads caused by the signals of the individual signal sources, C M Is represented by the formula M A respective common spatial pattern;
the objective of the algorithm is to design spatial filteringDevice F 1 And F 2 A spatial factor W is obtained.
(11) Solving a mixed space covariance matrix:
X 1 and X 2 Normalized covariance matrix R 1 And R 2 Respectively as follows:
wherein, X T Represents the transpose of the X matrix, trace (X) represents the sum of the elements on the diagonal of the matrix, and then the mixture spatial covariance matrix R:
wherein,
respectively is an average covariance matrix of two stress training task experiments;
(12) and (3) applying a principal component analysis method to obtain a whitening eigenvalue matrix P:
and carrying out eigenvalue decomposition on the mixed spatial covariance matrix R according to the formula:
R＝UλU T (4)
wherein, U is an eigenvector matrix of matrix lambda, lambda is a diagonal matrix formed by corresponding eigenvalues, the eigenvalues are arranged in descending order, and a whitening value matrix P is
(13) Constructing a spatial filter:
to R 1 And R 2 The following transformations are performed:
S 1 ＝PR 1 P T ,S 2 ＝PR 2 P T (6)
then to S 1 And S 2 And performing principal component decomposition to obtain:
the matrix S is proved by the above formula 1 The eigenvector sum matrix S 2 Are equal, i.e.:
B 1 ＝B 2 ＝V (8)
at the same time, a diagonal matrix λ of two eigenvalues 1 And λ 2 The sum is the identity matrix, i.e.:
λ 1 +λ 2 ＝I (9)
since the sum of the eigenvalues of the two types of matrices is always 1, S is 1 The feature vector corresponding to the maximum feature value of (1) makes S 2 Has the smallest characteristic value;
lambda of handle 1 The eigenvalues in (1) are arranged in descending order, then λ 2 In ascending order, to infer lambda 1 And λ 2 Having the form:
λ 1 ＝diag(I 1 σ M 0),λ 2 ＝diag(0σ M I 2 ) (10)
whitening brain wave to lambda 1 And λ 2 The transformation of the eigenvector corresponding to the largest eigenvalue in (a) is optimal for separating the variances in the two signal matrices, the projection matrix W is the corresponding spatial filter:
W＝B T P (11)
(14) feature extraction:
the motor imagery matrix X of the training set L 、X R The characteristic Z can be obtained by filtering through the corresponding constructed filter W L 、Z R Comprises the following steps:
Z L ＝W×X L ,Z R ＝W×X R (12)
extracted according to the characteristics of the electroencephalogram signal collected at multiple electrodesDefinition, selection of f L And f R To imagine the left and right feature vectors, the following is defined:
for test data X i In other words, its feature vector f i The extraction method is as follows, and L and f R Comparing to determine the ith imagine as imagined left and imagined right;
finding f of the test i And (5) performing corresponding classification.
The algorithm is an algorithm for extracting spatial filtering characteristics under two classification tasks, and spatial distribution components of each type can be extracted from multi-channel brain-computer interface data. The basic principle of the public space mode algorithm is to find a group of optimal space filters for projection by utilizing the diagonalization of a matrix, so that the variance difference of two types of signals is maximized, and the feature vector with higher discrimination is obtained.
The wavelet algorithm comprises the following steps:
j ═ 0,1,2, …; k belongs to Z and is called cj, and k is a discrete wavelet transform coefficient, which is called wavelet coefficient for short;
get a 0 ＝1，b 0 When a is equal to 1, the value of a is 20,21, …,2j, and the basis function ψ ab (t) in the continuous wavelet transform is denoted as ψ jk (t);
accordingly, the discrete wavelet transform is represented as
The method is characterized in that the distribution of brain wave signal power at each frequency point is represented by a density concept, the distribution is a measure of a mean square value of a random variable and is a measure of unit frequency average power, and the method specifically comprises the following steps:
s1: x (N) is an infinite length random sequence, and the truncated length N is changed into a finite length sequence which is called XN (N);
s2: calculating an autocorrelation function RX (m) of XN (n) at the point (2 m-1);
s3: taking the Fourier transform of the correlation function to obtain a power spectrum:
wherein M is- (M-1) …, -1, 0,1, …, M-1, and M is less than or equal to N.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (7)
1. Mental health testing arrangement based on brain wave data, its characterized in that includes: a main machine connected with a brain wave collecting electrode and an electrostatic hand ring,
the brain wave acquisition electrode is used for acquiring brain wave data;
the static bracelet is used for absorbing static electricity;
the main machine is used for extracting mental health related electroencephalogram characteristics from electroencephalogram data, outputting concentration degree, relaxation degree parameters and electroencephalogram parameters, establishing a normal range, and reflecting the mental health condition of a tested person from a plurality of dimensions.
2. The brain wave data-based mental health test apparatus according to claim 1, wherein the dimensions include basic mental data, health mental data, safety mental data, interpersonal mental data, and behavioral mental data;
the basic psychological data includes sense of security, emotional acceptance, mental elasticity, and emotional output;
the health psychological data includes exogenous anxiety, endogenous anxiety, pleasure addiction and discharge addiction;
safety psychological data include right-brain depression, left-brain depression, frailty index, and marquis index;
the social psychological data comprises thought self-closing, thought compulsion, entanglement indexes and irritability indexes;
behavioral psychology data packet behavioral self-closure, behavioral compulsion, fear index and behavioral response.
3. A testing method of a mental health testing device based on brain wave data is characterized by comprising the following steps:
extracting brain wave features related to mental health according to the brain wave data to obtain a mental database;
creating a standard normal range according to the mental database;
according to the brain wave signal of the tested person, converting the brain wave signal into a digital signal through analog-to-digital conversion, and transmitting the digital signal to a host computer, wherein the host computer adopts spectral analysis, wavelet, pattern recognition and nonlinear complexity algorithm to obtain a cluster of multi-dimensional quantitative marking numerical values related to each calculation window of the brain wave, then obtains a plurality of dimensions related to the mental health condition through multivariate linear regression and fuzzy recognition calculation, and analyzes to obtain a normal mode value related to the mental health of the tested person;
and comparing the normal value related to the psychological health of the tested person with the standard normal range to obtain the psychological health condition of the tested person, and automatically generating an evaluation report according to the data result.
4. The method for testing the mental health test device based on electroencephalogram data according to claim 3, wherein basic information of the subject is stored in a host, the host collects the information of the electroencephalogram of the subject through an electroencephalogram collecting electrode by playing a picture with sound to the subject;
selecting a certain stress training task, wherein the stress training task comprises a plurality of stress pictures, and the testee wears the brain wave acquisition electrode and the electrostatic wristband to finish so as to start stress training;
after a stress training task starts, acquiring brain wave information in real time through brain wave acquisition electrodes in a stress picture flow, judging whether to adjust the playing sequence of the stress picture according to the brain wave information acquired in real time, analyzing by a host according to the acquired brain wave signals to obtain a constant modulus value related to the mental health of a tested person after the stress picture flow is finished, and then generating a stress training file and reporting to output an evaluation report.
5. The method for testing the mental health test apparatus based on brain wave data according to claim 4, wherein the brain wave information reading method comprises:
suppose X 1 And X 2 The multi-channel evoked response space-time signal matrixes are respectively under two stress training tasks, the dimensionalities of the multi-channel evoked response space-time signal matrixes are N x T, wherein N is the number of electroencephalogram channels, T is the number of samples collected by each channel, and N is assumed to be less than T;
wherein S is 1 And S 2 Respectively represent two stress training tasks, S 1 Is formed by m 1 Constituted by individual sources, S 2 Is formed by m 2 A source is composed of 1 And C 2 From S 1 And S 2 CorrelationM of 1 And m 2 A common spatial pattern, each spatial pattern being an N x 1-dimensional vector, which is now used to represent the distributed weights of the signals on the N leads caused by the signals of the individual signal sources, C M Is represented by the formula M A respective common spatial pattern;
(11) solving a mixed space covariance matrix:
X 1 and X 2 Normalized covariance matrix R 1 And R 2 Respectively as follows:
wherein, X T Represents the transpose of the X matrix, trace (X) represents the sum of the elements on the diagonal of the matrix, and then the mixture spatial covariance matrix R:
wherein,
respectively is an average covariance matrix of two stress training task experiments;
(12) solving a whitening eigenvalue matrix P:
and (3) carrying out eigenvalue decomposition on the mixed spatial covariance matrix R according to the formula:
R＝UλU T (4)
wherein, U is an eigenvector matrix of matrix lambda, lambda is a diagonal matrix formed by corresponding eigenvalues, the eigenvalues are arranged in descending order, and a whitening value matrix P is
(13) Constructing a spatial filter:
to R 1 And R 2 The following transformations are performed:
S 1 ＝PR 1 P T ,S 2 ＝PR 2 P T (6)
then to S 1 And S 2 And performing principal component decomposition to obtain:
the matrix S is proved by the above formula 1 The eigenvector sum matrix S 2 Are equal, i.e.:
B 1 ＝B 2 ＝V (8)
at the same time, a diagonal matrix λ of two eigenvalues 1 And λ 2 The sum is the identity matrix, i.e.:
λ 1 +λ 2 ＝I (9)
since the sum of the eigenvalues of the two types of matrices is always 1, S is 1 The feature vector corresponding to the maximum feature value of (1) makes S 2 Has the smallest characteristic value;
lambda is measured 1 The eigenvalues in (1) are arranged in descending order, then λ 2 In ascending order, to infer lambda 1 And λ 2 Having the form:
λ 1 ＝diag(I 1 σ M 0),λ 2 ＝diag(0σ M I 2 ) (10)
whitening brain wave to lambda 1 And λ 2 The transformation of the eigenvector corresponding to the largest eigenvalue in (a) is optimal for separating the variances in the two signal matrices, the projection matrix W is the corresponding spatial filter:
W＝B T P (11)
(14) feature extraction:
the motor imagery matrix X of the training set L 、X R The characteristic Z can be obtained by filtering through the corresponding constructed filter W L 、Z R Comprises the following steps:
Z L ＝W×X L ,Z R ＝W×X R (12)
according to the definition of the extraction of the characteristics of the multi-electrode acquired electroencephalogram signals, f is selected L And f R To imagine the left and right feature vectors, the following is defined:
for test data X i In other words, its feature vector f i The extraction method is as follows, and L and f R Comparing to determine the ith imagine as imagined left and imagined right;
finding f of the test i And (5) performing corresponding classification.
6. The method for testing the mental health test device based on brain wave data according to claim 4, wherein the wavelet algorithm comprises:
j ═ 0,1,2, …; k belongs to Z and is called cj, and k is a discrete wavelet transform coefficient, which is called wavelet coefficient for short;
get a 0 ＝1，b 0 When a is equal to 1, the value of a is 20,21, …,2j, and the basis function ψ ab (t) in the continuous wavelet transform is denoted as ψ jk (t);
accordingly, the discrete wavelet transform is represented as
7. The method for testing the mental health test device based on brain wave data of claim 4, wherein the distribution of the brain wave signal power at each frequency point is represented by a concept of density, which is a measure of a mean square value of a random variable, and the method comprises the following steps:
s1: x (N) is an infinite length random sequence, and the truncated length N is changed into a finite length sequence which is called XN (N);
s2: calculating an autocorrelation function RX (m) of XN (n) at the point (2 m-1);
s3: and solving Fourier transform of the correlation function to obtain a power spectrum:
wherein M is- (M-1) …, -1, 0,1, …, M-1, and M is less than or equal to N.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210703996.7A CN114869299A (en) | 2022-06-21 | 2022-06-21 | Mental health testing device and testing method based on electroencephalogram data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210703996.7A CN114869299A (en) | 2022-06-21 | 2022-06-21 | Mental health testing device and testing method based on electroencephalogram data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114869299A true CN114869299A (en) | 2022-08-09 |
Family
ID=82681869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210703996.7A Pending CN114869299A (en) | 2022-06-21 | 2022-06-21 | Mental health testing device and testing method based on electroencephalogram data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114869299A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115624329A (en) * | 2022-10-28 | 2023-01-20 | 上海觉觉健康科技有限公司 | Method and system for identifying non-strength based on electroencephalogram signals |
| CN115886812A (en) * | 2022-09-30 | 2023-04-04 | 中国安全生产科学研究院 | An assessment and guidance system for employees' mental health |
| CN117116489A (en) * | 2023-10-25 | 2023-11-24 | 光大宏远(天津)技术有限公司 | Psychological assessment data management method and system |
| CN117312836A (en) * | 2023-10-30 | 2023-12-29 | 厚德明心(北京)科技有限公司 | User meditation state processing method and system based on artificial intelligence |
| CN118319330A (en) * | 2024-06-14 | 2024-07-12 | 东北电力大学 | A brain wave analysis method for diagnosing depression |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108888264A (en) * | 2018-05-03 | 2018-11-27 | 南京邮电大学 | EMD and CSP merges power spectral density brain electrical feature extracting method |
| CN112232207A (en) * | 2020-10-16 | 2021-01-15 | 江苏田域科技有限公司 | Mental evaluation system and brain data cloud application system |
| CN112515685A (en) * | 2020-11-10 | 2021-03-19 | 上海大学 | Multi-channel electroencephalogram signal channel selection method based on time-frequency co-fusion |
| US11311220B1 (en) * | 2021-10-11 | 2022-04-26 | King Abdulaziz University | Deep learning model-based identification of stress resilience using electroencephalograph (EEG) |
-
2022
- 2022-06-21 CN CN202210703996.7A patent/CN114869299A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108888264A (en) * | 2018-05-03 | 2018-11-27 | 南京邮电大学 | EMD and CSP merges power spectral density brain electrical feature extracting method |
| CN112232207A (en) * | 2020-10-16 | 2021-01-15 | 江苏田域科技有限公司 | Mental evaluation system and brain data cloud application system |
| CN112515685A (en) * | 2020-11-10 | 2021-03-19 | 上海大学 | Multi-channel electroencephalogram signal channel selection method based on time-frequency co-fusion |
| US11311220B1 (en) * | 2021-10-11 | 2022-04-26 | King Abdulaziz University | Deep learning model-based identification of stress resilience using electroencephalograph (EEG) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115886812A (en) * | 2022-09-30 | 2023-04-04 | 中国安全生产科学研究院 | An assessment and guidance system for employees' mental health |
| CN115624329A (en) * | 2022-10-28 | 2023-01-20 | 上海觉觉健康科技有限公司 | Method and system for identifying non-strength based on electroencephalogram signals |
| CN117116489A (en) * | 2023-10-25 | 2023-11-24 | 光大宏远(天津)技术有限公司 | Psychological assessment data management method and system |
| CN117312836A (en) * | 2023-10-30 | 2023-12-29 | 厚德明心(北京)科技有限公司 | User meditation state processing method and system based on artificial intelligence |
| CN117312836B (en) * | 2023-10-30 | 2024-04-05 | 厚德明心(北京)科技有限公司 | User meditation state processing method and system based on artificial intelligence |
| CN118319330A (en) * | 2024-06-14 | 2024-07-12 | 东北电力大学 | A brain wave analysis method for diagnosing depression |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khare et al. | SPWVD-CNN for automated detection of schizophrenia patients using EEG signals | |
| CN114869299A (en) | Mental health testing device and testing method based on electroencephalogram data | |
| Khare et al. | PDCNNet: An automatic framework for the detection of Parkinson’s disease using EEG signals | |
| US6129681A (en) | Apparatus and method for analyzing information relating to physical and mental condition | |
| Bastos-Filho et al. | Evaluation of feature extraction techniques in emotional state recognition | |
| Wagh et al. | Performance evaluation of multi-channel electroencephalogram signal (EEG) based time frequency analysis for human emotion recognition | |
| KR101842750B1 (en) | Realtime simulator for brainwaves training and interface device using realtime simulator | |
| CN113143208A (en) | Pain sensitivity assessment system and method based on multi-dimensional measurement | |
| CN112806994A (en) | System and method for predicting individual stress coping mode based on physiological signal | |
| CN112185493A (en) | Personality preference diagnosis device and project recommendation system based on same | |
| Baravalle et al. | Discriminating imagined and non-imagined tasks in the motor cortex area: Entropy-complexity plane with a wavelet decomposition | |
| Greco et al. | A Morlet wavelet classification technique for ICA filtered sEMG experimental data | |
| CN109271894A (en) | A kind of product image recognition methods based on EEG signals and fuzzy reasoning | |
| Hurtado-Rincon et al. | Motor imagery classification using feature relevance analysis: An Emotiv-based BCI system | |
| Dzitac et al. | Identification of ERD using fuzzy inference systems for brain-computer interface | |
| Heinisch et al. | The Impact of Physical Activities on the Physiological Response to Emotions | |
| Srinivas et al. | Wavelet based emotion recognition using RBF algorithm | |
| JP3933568B2 (en) | Brain function measuring device | |
| Raman et al. | Electroencephalogram (EEG), its processing and feature extraction | |
| Chandel et al. | Computer based detection of alcoholism using eeg signals | |
| Kidwai et al. | A new perspective of detecting and classifying neurological disorders through recurrence and machine learning classifiers | |
| Apicella et al. | Metrological foundations of emotional valence measurement through an EEG-based system | |
| Rahman et al. | Arithmetic Mental Task of EEG Signal Classification Using Statistical Modeling of The Dwt Coefficient | |
| Manekar et al. | Wavelet Decomposition based Automated Alcoholism Classification using EEG Signal | |
| Chandra et al. | Classification of Electroencephalography for Neurobiological Spectrum Disorder Diagnosis |
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 |