CN117942076A - Psychological state identification method and device based on single-conduction electroencephalogram signal - Google Patents
Psychological state identification method and device based on single-conduction electroencephalogram signal Download PDFInfo
- Publication number
- CN117942076A CN117942076A CN202410072483.XA CN202410072483A CN117942076A CN 117942076 A CN117942076 A CN 117942076A CN 202410072483 A CN202410072483 A CN 202410072483A CN 117942076 A CN117942076 A CN 117942076A
- Authority
- CN
- China
- Prior art keywords
- electroencephalogram
- target
- signal
- electroencephalogram signal
- psychological state
- 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 65
- 230000006996 mental state Effects 0.000 claims abstract description 14
- 210000004556 brain Anatomy 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 208000019901 Anxiety disease Diseases 0.000 description 5
- 230000036506 anxiety Effects 0.000 description 5
- 230000009466 transformation Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004399 eye closure Effects 0.000 description 1
- 238000005429 filling process Methods 0.000 description 1
- 210000001061 forehead Anatomy 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000012880 independent component analysis Methods 0.000 description 1
- 238000013208 measuring procedure Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000004984 smart glass Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000005654 stationary process Effects 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The embodiment of the specification provides a psychological state identification method and device based on single-conductivity electroencephalogram signals, wherein the psychological state identification method based on the single-conductivity electroencephalogram signals comprises the following steps: acquiring an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; a mental state is determined based on the electroencephalogram features and the target classifier. The method comprises the steps of obtaining an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; the psychological state is determined based on the electroencephalogram characteristics and the target classifier, so that the psychological state identification based on the single-conductivity electroencephalogram signals can be realized, subjective influence is avoided, and accuracy is improved.
Description
Technical Field
The embodiment of the specification relates to the technical field of mental state identification, in particular to a mental state identification method based on single-conduction electroencephalogram signals.
Background
Depression and anxiety are common mental disorders that result in a sustained sadness. Currently, conventional detection of depression and anxiety depends on interviews and scale-based surveys, however, for scale surveys one may intentionally make false expressions to the interview surveys so that detection by conventional methods may be inaccurate and objective.
Traditional depression and anxiety detection means:
Pressure is currently diagnosed mainly by means of a gauge. As a measuring tool, a scale is designed as a series of questions and descriptions, attempting to determine a subjective, quantitative measuring procedure for abstract concepts, assigning numbers to characteristic variables of things according to different rules, and thus forming scales of different measuring levels, also called measuring scales. Common diagnostic scales are the Beck depression test scale, the depression self-evaluation scale, the mental health clinical symptom self-evaluation test (SCL-90), and the like.
As a research tool, the scale requires confidence and efficacy as assurance. Reliability refers to Reliability, which refers to the degree of consistency of results obtained when repeated measurements are performed on the same subject using the same method. Validity refers to the effectiveness, which refers to the degree to which a measurement tool or means can accurately measure what is being measured. Because the scale needs credibility and validity as guarantees, the problems possibly encountered by the object in the filling process are 1, the understanding of the problems is not clear enough, 2, the problem is filled in a mess, and 3, the problem is too subjective and needs to be avoided.
Thus, a better solution is needed.
Disclosure of Invention
In view of this, the present embodiments provide a psychological state recognition method based on a single conductive brain electrical signal. One or more embodiments of the present specification relate to a psychological state recognition device, a computing device, a computer-readable storage medium, and a computer program based on single-lead electroencephalogram signals, which solve the technical drawbacks of the prior art.
According to a first aspect of embodiments of the present disclosure, there is provided a psychological state identification method based on single-conductivity electroencephalogram signals, including:
acquiring an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal;
extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics;
a mental state is determined based on the electroencephalogram features and the target classifier.
In one possible implementation manner, the method for obtaining the original electroencephalogram signal, performing decomposition processing on the original electroencephalogram signal to obtain the target electroencephalogram signal, includes:
decomposing the original electroencephalogram signals to determine wave packet coefficients;
establishing an electroencephalogram reference signal based on the wave packet coefficient;
and decomposing the electroencephalogram reference signal based on the sum wave packet coefficient to obtain the target electroencephalogram signal.
In one possible implementation manner, feature extraction is performed on the target electroencephalogram signal, and electroencephalogram feature determination includes:
extracting linear characteristics of the target electroencephalogram signals, and determining the linear characteristics;
extracting nonlinear characteristics of the target electroencephalogram signals, and determining the nonlinear characteristics;
An electroencephalogram characteristic is determined based on the linear characteristic and the nonlinear characteristic.
In one possible implementation manner, the extracting the linear feature from the target electroencephalogram signal to determine the linear feature includes:
determining band power, center frequency and power ratio based on the target electroencephalogram signal;
the linear characteristic is determined based on the band power, center frequency and power ratio.
In one possible implementation manner, the method for extracting the nonlinear characteristics of the target electroencephalogram signal and determining the nonlinear characteristics includes:
performing entropy calculation based on the target electroencephalogram signals to determine an entropy result;
complexity calculation is carried out based on the target electroencephalogram signals to determine a complexity result;
chaos index calculation is carried out on the basis of the target electroencephalogram signals to determine chaos degree;
The nonlinear characteristics are determined based on the entropy result, the complexity result, and the chaos.
In one possible implementation, the target classifier comprises a KNN classifier;
Correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises:
And inputting the brain electrical characteristics into a KNN classifier to obtain a probability value of the psychological state.
In one possible implementation, the target classifier comprises a naive bayes classifier;
Correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises:
and inputting the electroencephalogram characteristics into a naive Bayes classifier to obtain a probability value of the psychological state.
According to a second aspect of embodiments of the present specification, there is provided a psychological state recognition device based on single-conductivity brain electrical signals, including:
the signal acquisition module is configured to acquire an original electroencephalogram signal, and decompose the original electroencephalogram signal to obtain a target electroencephalogram signal;
the characteristic extraction module is configured to perform characteristic extraction on the target electroencephalogram signals and determine electroencephalogram characteristics;
And a state determination module configured to determine a mental state based on the electroencephalogram features and the target classifier.
According to a third aspect of embodiments of the present specification, there is provided a computing device comprising:
a memory and a processor;
The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, where the computer executable instructions when executed by the processor implement the steps of the method for identifying a psychological state based on single-conductivity electroencephalogram signals.
According to a fourth aspect of embodiments of the present specification, there is provided a computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the above-described method for identifying psychological states based on single-lead electroencephalograms.
According to a fifth aspect of embodiments of the present specification, there is provided a computer program, wherein the computer program, when executed in a computer, causes the computer to perform the steps of the above-described method for identifying a psychological state based on single-lead electroencephalograms.
The embodiment of the specification provides a psychological state identification method and device based on single-conductivity electroencephalogram signals, wherein the psychological state identification method based on the single-conductivity electroencephalogram signals comprises the following steps: acquiring an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; a mental state is determined based on the electroencephalogram features and the target classifier. The method comprises the steps of obtaining an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; the psychological state is determined based on the electroencephalogram characteristics and the target classifier, so that the psychological state identification based on the single-conductivity electroencephalogram signals can be realized, subjective influence is avoided, and accuracy is improved.
Drawings
Fig. 1 is a schematic view of a psychological state recognition method based on a single electroencephalogram signal according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a psychological state recognition method based on a single electroencephalogram signal according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of a psychological state recognition method based on single-conductive electroencephalogram signals according to an embodiment of the present disclosure;
Fig. 4 is a schematic structural diagram of a psychological state recognition device based on single-conductive electroencephalogram signals according to an embodiment of the present disclosure;
FIG. 5 is a block diagram of a computing device provided in one embodiment of the present description.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many other forms than described herein and similarly generalized by those skilled in the art to whom this disclosure pertains without departing from the spirit of the disclosure and, therefore, this disclosure is not limited by the specific implementations disclosed below.
The terminology used in the one or more embodiments of the specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the specification. As used in this specification, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that, although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first may also be referred to as a second, and similarly, a second may also be referred to as a first, without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" depending on the context.
First, terms related to one or more embodiments of the present specification will be explained.
FPz points: midpoint of frontal pole.
In the present specification, a psychological state recognition method based on a single conductive electroencephalogram signal is provided, and the present specification relates to a psychological state recognition apparatus based on a single conductive electroencephalogram signal, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.
Referring to fig. 1, fig. 1 is a schematic view of a psychological state recognition method based on a single electroencephalogram according to an embodiment of the present disclosure.
In the application scenario of fig. 1, the computing device 101 may acquire an original electroencephalogram signal 102, and perform decomposition processing on the original electroencephalogram signal 102 to obtain a target electroencephalogram signal 103. Thereafter, the computing device 101 may perform feature extraction on the target electroencephalogram signal 103, determining the electroencephalogram features 104. Finally, the computing device 101 may determine a mental state based on the electroencephalogram features 104 and the target classifier, as indicated by reference numeral 105.
The computing device 101 may be hardware or software. When the computing device 101 is hardware, it may be implemented as a distributed cluster of multiple servers or terminal devices, or as a single server or single terminal device. When the computing device 101 is embodied as software, it may be installed in the hardware devices listed above. It may be implemented as a plurality of software or software modules, for example, for providing distributed services, or as a single software or software module. The present invention is not particularly limited herein.
Referring to fig. 2, fig. 2 shows a flowchart of a psychological state recognition method based on single-conductivity electroencephalogram signals according to an embodiment of the present disclosure, which specifically includes the following steps.
Step 201: and acquiring an original brain electrical signal, and decomposing the original brain electrical signal to obtain a target brain electrical signal.
In practical application, the original electroencephalogram signals to be tested are collected through a single-conduction electroencephalogram collecting device, and referring to fig. 3, the collecting position is the position of an electroencephalogram electrode which is at the point FPz, and since the point FPz is positioned on the forehead, no hair is covered. The collection needs to be in a clear, quiet room. Quiet eye closure is required during the acquisition process. The collector has a resting brain electricity of 85s and a sampling rate of 260Hz.
In one possible implementation manner, the method for obtaining the original electroencephalogram signal, performing decomposition processing on the original electroencephalogram signal to obtain the target electroencephalogram signal, includes: decomposing the original electroencephalogram signals to determine wave packet coefficients; establishing an electroencephalogram reference signal based on the wave packet coefficient; and decomposing the electroencephalogram reference signal based on the sum wave packet coefficient to obtain the target electroencephalogram signal.
In practical application, the improved denoising algorithm combining Hilbert-Huang transformation and independent variable analysis effectively solves the problem that the electrooculogram interference coincides with the alpha wave band frequency during transformation.
Before the electroencephalogram signal is decomposed, the electroencephalogram signal can be denoised, so that the accuracy of the electroencephalogram signal is improved, and specifically, independent component analysis can be applied, an original electroencephalogram signal and an electrooculogram reference signal are used as input, and electrooculogram interference is removed from the original electroencephalogram signal.
Further, firstly, the Hilbert-Huang transform is applied to decompose the original electroencephalogram signal to form wave packet coefficients representing different frequency domains, and the node coefficients with the high correlation with the electro-oculogram interference of 0-7.5Hz are used for reconstructing an electroencephalogram reference signal.
Step 202: and extracting characteristics of the target electroencephalogram signals, and determining the characteristics of the electroencephalogram signals.
In one possible implementation manner, feature extraction is performed on the target electroencephalogram signal, and electroencephalogram feature determination includes: extracting linear characteristics of the target electroencephalogram signals, and determining the linear characteristics; extracting nonlinear characteristics of the target electroencephalogram signals, and determining the nonlinear characteristics; an initial electroencephalogram characteristic is determined based on the linear characteristic and the nonlinear characteristic.
In practical application, the brain electrical characteristics which are widely applied at present are extracted, and the brain electrical characteristics mainly comprise two major types of linear characteristics and nonlinear characteristics. The linear characteristics include center frequency, alpha, beta, and theta each band power (absolute, relative, and maximum power) and each band power ratio; nonlinear features include Renyi entropy, LZ complexity, CO complexity, maximum Lyapunov index.
In one possible implementation manner, the extracting the linear feature from the target electroencephalogram signal to determine the linear feature includes: determining band power, center frequency and power ratio based on the target electroencephalogram signal; the linear characteristic is determined based on the band power, center frequency and power ratio.
In practical applications, alpha, beta, theta and Delta power in each band are obtained by fast fourier transform. The relative power of each band is the ratio of the power of each band to the total power of all bands, so the relative power value is between 0, 1. The center frequency refers to the frequency at which the maximum power is derived from the fast fourier transform. The power ratios include the ratio of alpha band to beta band power, the ratio of beta band to theta band power, the ratio of alpha band to theta band power, and the ratio of Delta band to other band powers.
In one possible implementation manner, the method for extracting the nonlinear characteristics of the target electroencephalogram signal and determining the nonlinear characteristics includes: performing entropy calculation based on the target electroencephalogram signals to determine an entropy result; complexity calculation is carried out based on the target electroencephalogram signals to determine a complexity result; chaos index calculation is carried out on the basis of the target electroencephalogram signals to determine chaos degree; the nonlinear characteristics are determined based on the entropy result, the complexity result, and the chaos.
In practical use, each nonlinear feature is calculated as follows.
Renyi entropy:
Renyi entropy, which is a representation of the average information content, can be used to analyze time series in non-stationary processes. The smaller the value, the simpler the components making up the sequence, and the larger the value, the more complex the signal. The calculation process is as follows:
when q tends to be 1, there are:
LZ complexity:
LZ complexity can reflect the rate at which new patterns appear in a data sequence as its length increases, and is widely used in the study of nonlinear science. Given one string S (S1, S2 … …, sn) to be solved and another string Q (Q1, Q2 … …, qn), SQ is defined as a concatenation of S and Q, i.e., sq= (S1, S2..sn, Q1, q2...qn). SQ is defined as the string that results when SQ removes the last character. Judging whether Q is a substring of SQv, if Q belongs to a substring of SQv, indicating that the character in Q is copied from S, and cascading the next character of the sequence to be solved after Q. If Q is not a substring of SQv, it means that Q is an insert character. After cascading Q to S, s=sq, a new Q is constructed, and the above process is repeated until Q takes the last bit of the sequence to be solved, and the procedure ends. Each time Q concatenates to S, a new pattern appears, and c represents the number of new patterns in the string. For example, for s= (10101010), applying the above method can result in c (8) =3 new patterns 1,0, 101010.
CO complexity:
the complexity of CO is expressed as a kind of randomness, and its main idea is to decompose a complex time sequence into two parts, regular and random, and calculate the ratio of the square of the random part to the square of the whole sequence. The calculation process is as follows:
given a time sequence { x (t), t=0, 1,2., N-1} of length N, then
For the corresponding sequence of fourier transforms,The worker is an imaginary unit. Record/>Then f (k) can be written as:
Let { f (k), k=0, 1,2., mean square value of N-1 be:
introducing r parameter, reserving frequency spectrum with mean square value exceeding r times, and setting the rest part as zero
Wherein r is a positive integer greater than 1. And (3) performing Fourier transformation to obtain:
The CO complexity is then defined as:
maximum Lyapunov index:
The Lyapunov index is a quantitative index for measuring system dynamics, and the greater the index, the more obvious the chaos characteristic, namely the higher the chaos degree. The step of calculating the maximum Lyapunov index by the small data size method is as follows:
(1) Given the time series { x (,) i=1, 2, … N }, the time delay and embedding dimensions are calculated and the phase space reconstruction is performed.
(2) Calculating a sequence average period P by using Fourier transformation;
(3) Phase space reconstruction according to time delay TAU and embedding dimension m
{Yj，，j=12，…M}， M=N-(m-1)*TAU
(4) Finding the nearest neighbor Y of Y in the phase space and limiting the temporal separation, i.e
(5) Calculating the i discrete time post-distance of each point Y in the phase space
(6) For each i, find the Ind of each j, (1) average, i.e
Where q is a non-zero dj, (i) number and y (i) is the average divergent distance of all pairs of adjacent points lagging by step i.
(7) Slope was determined using least squares curve fitting:
is the maximum Lyapunov index.
Step 203: a mental state is determined based on the electroencephalogram features and the target classifier.
In one possible implementation, the target classifier comprises a KNN classifier; correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises: and inputting the brain electrical characteristics into a KNN classifier to obtain a probability value of the psychological state.
In practice, the k nearest neighbor algorithm (k Nearest Neighbors, kNN) is a commonly used classification algorithm, its work
The mechanism is very simple: the class of the sample is determined by the k neighbors closest to the sample. If in k neighbors
Most belong to a certain class, then the sample also belongs to that class. The Euclidean distances are used herein, two
The euclidean distance of points or elements x1= (X11, X12, … X1 n) and x2= (X21, X22, … X2 n) is:
in order to prevent features from having larger or smaller extremes, resulting in excessive weight, affecting classification results,
And carrying out normalization processing on the characteristic values by using Min-Max, wherein the formula is as follows:
Where min A and max A represent the minimum large value of attribute A for the k nearest neighbor classifier, respectively, defining the most significant class of its k nearest neighbors to which the unknown tuple belongs. For example, when k=1, an unknown tuple is assigned to the class in the pattern space to which the training tuple closest thereto belongs. The value of the neighbor number k can be determined by a number of experiments. From k=1, the test set is used to estimate the error rate of the classification algorithm. This process is repeated each time the k value is increased by 1, i.e. one neighbor at a time. And finally, selecting k corresponding to the minimum error rate.
The KNN algorithm comprises the following steps:
(1) The distance between each sample in the test set and each sample in the training set is calculated.
(2) The samples are ordered in relation to increasing distance.
(3) A minimum k samples are selected and the frequency of each sample class is determined.
(4) The most frequent class of k samples is the final class of test samples.
In one possible implementation, the target classifier comprises a naive bayes classifier; correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises: and inputting the electroencephalogram characteristics into a naive Bayes classifier to obtain a probability value of the psychological state.
In practical application, the influence of different characteristic attributes of the acquired sample on classification of the sample is independent from each other.
The naive bayes working procedure is as follows:
Class m classification problem Bj represents one of m categories. The training sample set is x (1, x 2., [ t ], and the corresponding category is the probability that the current test sample y= (y 1, y 2, y n) belongs to each category.
(1) The probability value P (Bj) of the class Bj in the training sample is:
P (Bj) =class Bj number of samples/total number of samples;
(2) The relative probability value P (A [ i ] Bj) of the feature A [ i ] in the class Bj in the training sample is the number of samples containing the feature A [ i ] and belonging to Bj/the number of samples belonging to Bj;
(3) And calculating according to 1 and 2 to obtain the probability value P (ai) of the feature ai in the sample as follows:
；
(4) If the feature A [ i ] appears in the sample to be classified, the relative probability that the sample belongs to the class B [ j ] is as follows:
P(B[j] | A[i])=P(A[i] | B[j]) P(B[j])/P(A[i])；
(5) The probability P [ j ] that the sample y belongs to B [ j ] is obtained according to naive Bayesian assumption:
P[j]=IIP(B[j]A[i])*y[i]；
(6) The probabilities of the samples y belonging to the respective categories were found to be P1, P2, P m. Normalizing the m probability values, and then sequencing to obtain the probability that the sample y belongs to each category and determining the final classification.
The psychological state obtained after the application of the method is not used as a final diagnosis result, and is only used for auxiliary diagnosis, and the final result needs to be determined manually.
Further, training of the classifier is also required before the above method is performed.
Specifically, in the sample collection stage, according to the normal group, the depression group and the anxiety group, according to the gender and the age, the tested original brain electrical signals are collected through the single-conduction brain electrical collection device, and each group of samples can be 280 cases. The acquisition environment, the acquisition position and the subsequent feature extraction are the same as those described above, and will not be described here again. Sample collection is shown in the following table.
Normal group
Depression group
Anxiety group
The embodiment of the specification provides a psychological state identification method and device based on single-conductivity electroencephalogram signals, wherein the psychological state identification method based on the single-conductivity electroencephalogram signals comprises the following steps: acquiring an original brain electrical signal, and performing interference elimination processing on the original brain electrical signal to obtain a target brain electrical signal; extracting characteristics of the target electroencephalogram signals, and determining initial electroencephalogram characteristics; classifying and screening the initial electroencephalogram characteristics to obtain target electroencephalogram characteristics; and determining a psychological state based on the target brain electrical characteristics and the convolutional neural network model. The method comprises the steps of performing interference elimination processing on an original brain electrical signal by acquiring the original brain electrical signal to obtain a target brain electrical signal; extracting characteristics of the target electroencephalogram signals, and determining initial electroencephalogram characteristics; classifying and screening the initial electroencephalogram characteristics to obtain target electroencephalogram characteristics; the psychological state is determined based on the target brain electrical characteristics and the convolutional neural network model, so that the psychological state identification based on the single-conductivity brain electrical signals can be realized, subjective influence is avoided, and accuracy is improved.
Corresponding to the above method embodiment, the present disclosure further provides an embodiment of a psychological state recognition device based on a single conductive electroencephalogram, and fig. 4 shows a schematic structural diagram of a psychological state recognition device based on a single conductive electroencephalogram provided in an embodiment of the present disclosure. As shown in fig. 4, the apparatus includes:
the signal acquisition module 401 is configured to acquire an original electroencephalogram signal, and decompose the original electroencephalogram signal to obtain a target electroencephalogram signal;
A feature extraction module 402 configured to perform feature extraction on the target electroencephalogram signal, and determine an electroencephalogram feature;
The state determination module 403 is configured to determine a mental state based on the electroencephalogram features and the target classifier.
In one possible implementation, the signal acquisition module 401 is further configured to:
decomposing the original electroencephalogram signals to determine wave packet coefficients;
establishing an electroencephalogram reference signal based on the wave packet coefficient;
and decomposing the electroencephalogram reference signal based on the sum wave packet coefficient to obtain the target electroencephalogram signal.
In one possible implementation, the feature extraction module 402 is further configured to:
extracting linear characteristics of the target electroencephalogram signals, and determining the linear characteristics;
extracting nonlinear characteristics of the target electroencephalogram signals, and determining the nonlinear characteristics;
An electroencephalogram characteristic is determined based on the linear characteristic and the nonlinear characteristic.
In one possible implementation, the feature extraction module 402 is further configured to:
determining band power, center frequency and power ratio based on the target electroencephalogram signal;
the linear characteristic is determined based on the band power, center frequency and power ratio.
In one possible implementation, the feature extraction module 402 is further configured to:
performing entropy calculation based on the target electroencephalogram signals to determine an entropy result;
complexity calculation is carried out based on the target electroencephalogram signals to determine a complexity result;
chaos index calculation is carried out on the basis of the target electroencephalogram signals to determine chaos degree;
The nonlinear characteristics are determined based on the entropy result, the complexity result, and the chaos.
In one possible implementation, the state determination module 403 is further configured to:
the target classifier comprises a KNN classifier;
Correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises:
And inputting the brain electrical characteristics into a KNN classifier to obtain a probability value of the psychological state.
In one possible implementation, the state determination module 403 is further configured to:
The target classifier includes a naive bayes classifier;
Correspondingly, determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises:
and inputting the electroencephalogram characteristics into a naive Bayes classifier to obtain a probability value of the psychological state.
The embodiment of the specification provides a psychological state identification method and device based on single-conductivity electroencephalogram signals, wherein the psychological state identification method based on the single-conductivity electroencephalogram signals comprises the following steps: acquiring an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; a mental state is determined based on the electroencephalogram features and the target classifier. The method comprises the steps of obtaining an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal; extracting characteristics of target electroencephalogram signals and determining electroencephalogram characteristics; the psychological state is determined based on the electroencephalogram characteristics and the target classifier, so that the psychological state identification based on the single-conductivity electroencephalogram signals can be realized, subjective influence is avoided, and accuracy is improved.
The above is a schematic scheme of a psychological state recognition device based on a single brain-conducted electrical signal in this embodiment. It should be noted that, the technical solution of the psychological state recognition device based on the single electroencephalogram signal and the technical solution of the psychological state recognition method based on the single electroencephalogram signal belong to the same concept, and details of the technical solution of the psychological state recognition device based on the single electroencephalogram signal, which are not described in detail, can be referred to the description of the technical solution of the psychological state recognition method based on the single electroencephalogram signal.
Fig. 5 illustrates a block diagram of a computing device 500 provided in accordance with one embodiment of the present description. The components of the computing device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530 and database 550 is used to hold data.
Computing device 500 also includes access device 540, access device 540 enabling computing device 500 to communicate via one or more networks 560. Examples of such networks include public switched telephone networks (PSTN, public Switched Telephone Network), local area networks (LAN, local Area Network), wide area networks (WAN, wide Area Network), personal area networks (PAN, personal Area Network), or combinations of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, wired or wireless, such as a network interface card (NIC, network interface controller), such as an IEEE802.11 wireless local area network (WLAN, wireless Local Area Network) wireless interface, a worldwide interoperability for microwave access (Wi-MAX, worldwide Interoperability for Microwave Access) interface, an ethernet interface, a universal serial bus (USB, universal Serial Bus) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC).
In one embodiment of the present description, the above-described components of computing device 500, as well as other components not shown in FIG. 5, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device shown in FIG. 5 is for exemplary purposes only and is not intended to limit the scope of the present description. Those skilled in the art may add or replace other components as desired.
Computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smart phone), wearable computing device (e.g., smart watch, smart glasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or personal computer (PC, personal Computer). Computing device 500 may also be a mobile or stationary server.
The processor 520 is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the above-described method for identifying a psychological state based on single-conductivity electroencephalogram signals. The foregoing is a schematic illustration of a computing device of this embodiment. It should be noted that, the technical solution of the computing device and the technical solution of the psychological state identification method based on the single electroencephalogram belong to the same concept, and details of the technical solution of the computing device, which are not described in detail, can be referred to the description of the technical solution of the psychological state identification method based on the single electroencephalogram.
An embodiment of the present disclosure further provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described method for identifying a psychological state based on single-lead electroencephalogram signals.
The above is an exemplary version of a computer-readable storage medium of the present embodiment. It should be noted that, the technical solution of the storage medium and the technical solution of the psychological state identification method based on the single electroencephalogram signal belong to the same concept, and details of the technical solution of the storage medium which are not described in detail can be referred to the description of the technical solution of the psychological state identification method based on the single electroencephalogram signal.
An embodiment of the present disclosure further provides a computer program, where the computer program, when executed in a computer, causes the computer to perform the steps of the above mental state identification method based on single-lead electroencephalogram signals.
The above is an exemplary version of a computer program of the present embodiment. It should be noted that, the technical solution of the computer program and the technical solution of the psychological state identification method based on the single electroencephalogram belong to the same conception, and details of the technical solution of the computer program which are not described in detail can be referred to the description of the technical solution of the psychological state identification method based on the single electroencephalogram.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The computer instructions include computer program code that may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of combinations of actions, but it should be understood by those skilled in the art that the embodiments are not limited by the order of actions described, as some steps may be performed in other order or simultaneously according to the embodiments of the present disclosure. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily all required for the embodiments described in the specification.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are merely used to help clarify the present specification. Alternative embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the teaching of the embodiments. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. This specification is to be limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. The psychological state identification method based on the single-conduction electroencephalogram signal is characterized by comprising the following steps of:
Acquiring an original electroencephalogram signal, and decomposing the original electroencephalogram signal to obtain a target electroencephalogram signal;
Extracting characteristics of the target electroencephalogram signals, and determining electroencephalogram characteristics;
And determining a psychological state based on the electroencephalogram characteristics and the target classifier.
2. The method according to claim 1, wherein the obtaining the original electroencephalogram signal, and performing decomposition processing on the original electroencephalogram signal to obtain the target electroencephalogram signal, includes:
Decomposing the original electroencephalogram signals to determine wave packet coefficients;
establishing an electroencephalogram reference signal based on the wave packet coefficient;
And decomposing the electroencephalogram reference signal based on the sum wave packet coefficient to obtain a target electroencephalogram signal.
3. The method of claim 1, wherein the feature extracting the target electroencephalogram signal to determine an electroencephalogram feature comprises:
extracting linear characteristics of the target electroencephalogram signals, and determining the linear characteristics;
Carrying out nonlinear feature extraction on the target electroencephalogram signals to determine nonlinear features;
An electroencephalogram feature is determined based on the linear feature and the nonlinear feature.
4. The method of claim 1, wherein the performing linear feature extraction on the target electroencephalogram signal to determine linear features comprises:
Determining band power, center frequency and power ratio based on the target electroencephalogram signal;
a linear characteristic is determined based on the band power, the center frequency, and the power ratio.
5. The method of claim 1, wherein the performing nonlinear feature extraction on the target electroencephalogram signal to determine nonlinear features comprises:
Performing entropy calculation based on the target electroencephalogram signal to determine an entropy result;
performing complexity calculation based on the target electroencephalogram signals to determine a complexity result;
calculating a chaos index based on the target electroencephalogram signal to determine chaos degree;
And determining a nonlinear characteristic based on the entropy result, the complexity result and the chaos.
6. The method of claim 1, wherein the target classifier comprises a KNN classifier;
correspondingly, the determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises the following steps:
and inputting the electroencephalogram characteristics into the KNN classifier to obtain a probability value of the psychological state.
7. The method of claim 1, wherein the target classifier comprises a naive bayes classifier;
correspondingly, the determining the psychological state based on the electroencephalogram characteristics and the target classifier comprises the following steps:
and inputting the electroencephalogram characteristics into the naive Bayesian classifier to obtain a probability value of the psychological state.
8. A psychological state recognition device based on single-lead brain electrical signals, which is characterized by comprising:
the signal acquisition module is configured to acquire an original electroencephalogram signal, and decompose the original electroencephalogram signal to obtain a target electroencephalogram signal;
the feature extraction module is configured to perform feature extraction on the target electroencephalogram signals and determine electroencephalogram features;
a state determination module configured to determine a mental state based on the electroencephalogram features and a target classifier.
9. A computing device, comprising:
a memory and a processor;
The memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, which when executed by the processor, implement the steps of the single conductivity electroencephalogram signal based mental state identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the single-lead electroencephalogram signal-based mental state recognition method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410072483.XA CN117942076A (en) | 2024-01-18 | 2024-01-18 | Psychological state identification method and device based on single-conduction electroencephalogram signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410072483.XA CN117942076A (en) | 2024-01-18 | 2024-01-18 | Psychological state identification method and device based on single-conduction electroencephalogram signal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117942076A true CN117942076A (en) | 2024-04-30 |
Family
ID=90800502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410072483.XA Pending CN117942076A (en) | 2024-01-18 | 2024-01-18 | Psychological state identification method and device based on single-conduction electroencephalogram signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117942076A (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103690163A (en) * | 2013-12-21 | 2014-04-02 | 哈尔滨工业大学 | ICA (independent component analysis) and HHT (Hilbert-Huang transform) fusion based automatic electrooculogram interference eliminating method |
| US20170238858A1 (en) * | 2015-07-30 | 2017-08-24 | South China University Of Technology | Depression assessment system and depression assessment method based on physiological information |
| CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
| CN110781945A (en) * | 2019-10-22 | 2020-02-11 | 太原理工大学 | Electroencephalogram signal emotion recognition method and system integrating multiple features |
| US20200275873A1 (en) * | 2019-02-28 | 2020-09-03 | Boe Technology Group Co., Ltd. | Emotion analysis method and device and computer readable storage medium |
| CH716863A2 (en) * | 2019-11-22 | 2021-05-31 | Univ Lanzhou | Depression detection system based on channel selection of multi-channel electroencephalography made using training sets. |
| CN113397565A (en) * | 2021-07-22 | 2021-09-17 | 北京脑陆科技有限公司 | Depression identification method, device, terminal and medium based on electroencephalogram signals |
| CN113907768A (en) * | 2021-10-12 | 2022-01-11 | 浙江汉德瑞智能科技有限公司 | Electroencephalogram signal processing device based on matlab |
| CN115349861A (en) * | 2022-08-23 | 2022-11-18 | 山东大学 | Mental stress detection system and method based on single-channel electroencephalogram signal |
| CN116211322A (en) * | 2023-03-31 | 2023-06-06 | 上海外国语大学 | Depression recognition method and system based on machine learning electroencephalogram signals |
| CN116584947A (en) * | 2023-04-03 | 2023-08-15 | 华南理工大学 | Fatigue driving classification method and system for electroencephalogram multi-scale fuzzy entropy features |
-
2024
- 2024-01-18 CN CN202410072483.XA patent/CN117942076A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103690163A (en) * | 2013-12-21 | 2014-04-02 | 哈尔滨工业大学 | ICA (independent component analysis) and HHT (Hilbert-Huang transform) fusion based automatic electrooculogram interference eliminating method |
| US20170238858A1 (en) * | 2015-07-30 | 2017-08-24 | South China University Of Technology | Depression assessment system and depression assessment method based on physiological information |
| CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
| US20200275873A1 (en) * | 2019-02-28 | 2020-09-03 | Boe Technology Group Co., Ltd. | Emotion analysis method and device and computer readable storage medium |
| CN110781945A (en) * | 2019-10-22 | 2020-02-11 | 太原理工大学 | Electroencephalogram signal emotion recognition method and system integrating multiple features |
| CH716863A2 (en) * | 2019-11-22 | 2021-05-31 | Univ Lanzhou | Depression detection system based on channel selection of multi-channel electroencephalography made using training sets. |
| CN113397565A (en) * | 2021-07-22 | 2021-09-17 | 北京脑陆科技有限公司 | Depression identification method, device, terminal and medium based on electroencephalogram signals |
| CN113907768A (en) * | 2021-10-12 | 2022-01-11 | 浙江汉德瑞智能科技有限公司 | Electroencephalogram signal processing device based on matlab |
| CN115349861A (en) * | 2022-08-23 | 2022-11-18 | 山东大学 | Mental stress detection system and method based on single-channel electroencephalogram signal |
| CN116211322A (en) * | 2023-03-31 | 2023-06-06 | 上海外国语大学 | Depression recognition method and system based on machine learning electroencephalogram signals |
| CN116584947A (en) * | 2023-04-03 | 2023-08-15 | 华南理工大学 | Fatigue driving classification method and system for electroencephalogram multi-scale fuzzy entropy features |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xie et al. | Wavelet-based sparse functional linear model with applications to EEGs seizure detection and epilepsy diagnosis | |
| Chakraborty et al. | Epilepsy seizure detection using kurtosis based VMD’s parameters selection and bandwidth features | |
| CN113052113B (en) | Depression identification method and system based on compact convolutional neural network | |
| CN111310570B (en) | Electroencephalogram signal emotion recognition method and system based on VMD and WPD | |
| Al Ghayab et al. | Epileptic EEG signal classification using optimum allocation based power spectral density estimation | |
| Logesparan et al. | The impact of signal normalization on seizure detection using line length features | |
| CN112603335B (en) | Electroencephalogram emotion recognition method, system, equipment and storage medium | |
| Azami et al. | Entropy analysis of univariate biomedical signals: Review and comparison of methods | |
| CN113069117A (en) | Electroencephalogram emotion recognition method and system based on time convolution neural network | |
| CN113229818A (en) | Cross-subject personality prediction system based on electroencephalogram signals and transfer learning | |
| CN115414051A (en) | Emotion classification and recognition method of electroencephalogram signal self-adaptive window | |
| CN114343635A (en) | Variable phase-splitting amplitude coupling-based emotion recognition method and device | |
| CN112380959A (en) | Univariate time series classification method based on graph neural network | |
| CN111312394A (en) | Psychological health condition evaluation system based on combined emotion and processing method thereof | |
| Yedukondalu et al. | Cognitive load detection using Binary salp swarm algorithm for feature selection | |
| Obeidat et al. | EEG based epilepsy diagnosis system using reconstruction phase space and naive Bayes classifier | |
| CN117942076A (en) | Psychological state identification method and device based on single-conduction electroencephalogram signal | |
| See et al. | Heart sound classification based on nonlinear time-frequency features | |
| CN116933119A (en) | Signal data trend removal method based on convolutional neural network | |
| Vimalajeewa et al. | A Method for Detecting Murmurous Heart Sounds based on Self-similar Properties | |
| CN115408891B (en) | Modeling method for user experience percentile measurement containing multiple electroencephalogram cognitive indexes | |
| García-Aquino et al. | Classification of cardiac arrhythmias using machine learning algorithms | |
| CN117708682B (en) | Intelligent brain wave acquisition and analysis system and method | |
| CN114869298B (en) | Depression detection method, system and storable medium based on brain electrical signal | |
| Rahman et al. | Arithmetic Mental Task of EEG Signal Classification Using Statistical Modeling of The DWT Coefficient |
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 |