Method and device for testing brain-computer interface equipment in complex electromagnetic environment

Abstract

The invention discloses a method and a device for testing brain-computer interface equipment in a complex electromagnetic environment. The method comprises the following steps: acquiring a signal parameter information set; the signal parameter information set comprises signal parameter information; the signal parameter information comprises frequency, amplitude and phase; acquiring a standard electroencephalogram signal sequence by using a to-be-tested brain-computer interface device; generating a complex electromagnetic signal according to the signal parameter information set, and measuring to obtain an electroencephalogram signal sequence set in a complex electromagnetic signal environment; and performing evaluation processing on the signal parameter information set, the standard electroencephalogram signal sequence and the electroencephalogram signal sequence set to obtain evaluation result information of the brain-computer interface equipment in the complex electromagnetic environment.

Description

Technical Field

[0001] The present invention relates to the technical field of brain-computer interfaces, and particularly to a test method and device for a brain-computer interface device in a complex electromagnetic environment. Background Art

[0002] With the rapid development of brain-computer interface technology, its applications in the fields of medical treatment, rehabilitation, entertainment, etc. are becoming increasingly widespread. However, in practical applications, brain-computer interfaces are often interfered by complex electromagnetic environments, affecting their performance and reliability. Currently, there is a relative lack of test methods and devices for brain-computer interfaces in complex electromagnetic environments, and it is impossible to effectively evaluate the working conditions of brain-computer interfaces in real electromagnetic environments. Summary of the Invention

[0003] The present invention mainly solves the problem of evaluating the working conditions of brain-computer interfaces in real electromagnetic environments, and discloses a test method and device for a brain-computer interface device in a complex electromagnetic environment.

[0004] In the first aspect of the embodiments of the present invention, a test method for a brain-computer interface device in a complex electromagnetic environment is disclosed, including:

[0005] S1, obtaining a signal parameter information set; the signal parameter information set includes signal parameter information; the signal parameter information includes frequency, amplitude, and phase;

[0006] S2, using the brain-computer interface device to be tested to collect a standard electroencephalogram signal sequence;

[0007] S3, generating a complex electromagnetic signal according to the signal parameter information set, and measuring an electroencephalogram signal sequence set in a complex electromagnetic signal environment;

[0008] S4, performing an evaluation process on the signal parameter information set, the standard electroencephalogram signal sequence, and the electroencephalogram signal sequence set to obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment.

[0009] The generating a complex electromagnetic signal according to the signal parameter information set, and measuring an electroencephalogram signal sequence set in a complex electromagnetic signal environment includes:

[0010] S31, generating a corresponding complex electromagnetic signal according to each signal parameter information in the signal parameter information set;

[0011] S32, setting the brain-computer interface device in the environment of the complex electromagnetic signal, and collecting an electroencephalogram signal sequence;

[0012] S33. For each piece of signal parameter information in the set of signal parameter information, perform S31 to S32, and use all the collected EEG signal sequences to construct a set of EEG signal sequences.

[0013] The evaluation processing of the set of signal parameter information, the standard EEG signal sequence, and the set of EEG signal sequences to obtain the evaluation result information of the brain-computer interface device under complex electromagnetic environments includes:

[0014] S41. Perform modeling processing on the set of signal parameter information, the standard EEG signal sequence, and the set of EEG signal sequences to obtain an EEG signal integrity prediction model;

[0015] S42. Perform feature extraction processing on the set of signal parameter information to obtain feature signal parameters;

[0016] S43. Use the EEG signal integrity prediction model to perform calculation processing on the feature signal parameters to obtain integrity evaluation information;

[0017] S44. Perform volatility evaluation processing on the standard EEG signal sequence and the set of EEG signal sequences to obtain volatility evaluation information;

[0018] S45. Use the integrity evaluation information and the volatility evaluation information to construct the evaluation result information of the brain-computer interface device under complex electromagnetic environments.

[0019] The performing modeling processing on the set of signal parameter information, the standard EEG signal sequence, and the set of EEG signal sequences to obtain an EEG signal integrity prediction model includes:

[0020] S411. Subtract each EEG signal sequence in the set of EEG signal sequences from the standard EEG signal sequence to obtain a corresponding difference sequence;

[0021] S412. Use all the difference sequences to construct a difference matrix; the row vectors of the difference matrix are the difference sequences;

[0022] S413. Use the set of signal parameter information to construct a signal parameter matrix; the row vectors of the signal parameter matrix are the signal parameter information;

[0023] S414. Use the difference matrix and the signal parameter matrix to construct an integrity optimization model;

[0024] S415. Solve the integrity optimization model to obtain the calculation result of the evaluation matrix;

[0025] S416. Use the calculation result of the evaluation matrix to construct an EEG signal integrity prediction model.

[0026] Performing volatility evaluation processing on the standard EEG signal sequence and the EEG signal sequence set to obtain volatility evaluation information, including:

[0027] S441. Subtracting each EEG signal sequence in the EEG signal sequence set from the standard EEG signal sequence to obtain a corresponding difference sequence;

[0028] S442. Using all the difference sequences to construct a difference matrix;

[0029] S443. Performing deviation calculation processing on the difference matrix to obtain a deviation vector;

[0030] S444. Performing correlation calculation processing on the difference matrix to obtain a correlation matrix; the element in the i-th row and j-th column of the correlation matrix is obtained by multiplying the i-th row vector and the j-th row vector in the difference matrix;

[0031] S445. Performing eigenvalue decomposition processing on the correlation matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector obtained by arranging all the eigenvalues of the correlation matrix in descending order of their values;

[0032] S446. Performing a dot product of the deviation vector and the eigenvalue vector to obtain volatility evaluation information.

[0033] The deviation calculation processing has the following expression:

[0034] t = (P T V + aI) -1 P T y,

[0035] V = QR -1 ,

[0036] where t is the calculated deviation vector, Q and R are the Q matrix and R matrix obtained by performing QR decomposition on the difference matrix P respectively, V is an intermediate matrix, a is the largest eigenvalue of the difference matrix P, and y is the eigenvector of the difference matrix P.

[0037] In the second aspect of the implementation of the present invention, a test device for a brain-computer interface device in a complex electromagnetic environment is disclosed, which is used to implement the test method for the brain-computer interface device in the complex electromagnetic environment, including:

[0038] A complex signal generation module and an evaluation module;

[0039] The complex signal generation module is connected to the evaluation model and is used to obtain a signal parameter information set and generate a complex electromagnetic signal according to the signal parameter information set;

[0040] The evaluation module is configured to collect an electroencephalogram (EEG) signal sequence set, and perform evaluation processing on the signal parameter information set, the standard EEG signal sequence, and the EEG signal sequence set to obtain evaluation result information of the brain-computer interface device under a complex electromagnetic environment.

[0041] In a third aspect of the implementation of the present invention, a test device for a brain-computer interface device under a complex electromagnetic environment is disclosed. The device includes:

[0042] A memory storing executable program code;

[0043] A processor coupled to the memory;

[0044] The processor calls the executable program code stored in the memory to execute the test method for the brain-computer interface device under the complex electromagnetic environment.

[0045] In a fourth aspect of the implementation of the present invention, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, which are used to execute the test method for the brain-computer interface device under the complex electromagnetic environment when called by a computer.

[0046] In a fifth aspect of the implementation of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the test method for the brain-computer interface device under the complex electromagnetic environment.

[0047] The beneficial effects of the present invention are as follows:

[0048] The present invention can truly simulate a complex electromagnetic environment, conduct comprehensive and accurate performance tests on the brain-computer interface, and provide reliable technical support for the research and application of the brain-computer interface. The present invention helps to discover potential problems of the brain-computer interface under electromagnetic interference, take measures in advance for optimization and improvement, and improve the anti-interference ability and reliability of the brain-computer interface. The present invention can provide data basis for the formulation of relevant standards and promote the standardized development of brain-computer interface technology.

[0049] When evaluating the brain-computer interface device under a complex electromagnetic environment, the present invention proposes to evaluate from two aspects: integrity evaluation information and volatility evaluation information for the EEG signal characteristics, and specifically establishes corresponding evaluation algorithms. Using the evaluation algorithms, efficient and accurate evaluation of the above two indicators can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a flowchart of the implementation of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] To better understand the content of the present invention, an embodiment is given here.

[0052] Figure 1 This is the implementation flowchart of the method of the present invention.

[0053] In the first aspect of the embodiments of the present invention, a test method for a brain-computer interface device in a complex electromagnetic environment is disclosed, including:

[0054] S1, obtaining a signal parameter information set; the signal parameter information set includes signal parameter information; the signal parameter information includes frequency, amplitude, and phase;

[0055] S2, using the brain-computer interface device to be tested to collect a standard electroencephalogram signal sequence;

[0056] S3, generating a complex electromagnetic signal according to the signal parameter information set, and measuring an electroencephalogram signal sequence set in a complex electromagnetic signal environment;

[0057] S4, performing an evaluation process on the signal parameter information set, the standard electroencephalogram signal sequence, and the electroencephalogram signal sequence set to obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment;

[0058] The generating a complex electromagnetic signal according to the signal parameter information set and measuring an electroencephalogram signal sequence set in a complex electromagnetic signal environment includes:

[0059] S31, generating a corresponding complex electromagnetic signal according to each signal parameter information in the signal parameter information set;

[0060] S32, setting the brain-computer interface device in the environment of the complex electromagnetic signal, and collecting an electroencephalogram signal sequence;

[0061] S33, for each signal parameter information in the signal parameter information set, performing S31 to S32, and using all the collected electroencephalogram signal sequences to construct an electroencephalogram signal sequence set;

[0062] The performing an evaluation process on the signal parameter information set, the standard electroencephalogram signal sequence, and the electroencephalogram signal sequence set to obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment includes:

[0063] S41, performing a modeling process on the signal parameter information set, the standard electroencephalogram signal sequence, and the electroencephalogram signal sequence set to obtain an electroencephalogram signal integrity prediction model;

[0064] S42, performing a feature extraction process on the signal parameter information set to obtain a feature signal parameter;

[0065] S43. Using the EEG signal integrity prediction model, calculate and process the feature signal parameters to obtain integrity evaluation information;

[0066] S44. Perform a volatility evaluation process on the standard EEG signal sequence and the EEG signal sequence set to obtain volatility evaluation information;

[0067] S45. Using the integrity evaluation information and the volatility evaluation information, construct the evaluation result information of the brain-computer interface device under complex electromagnetic environments.

[0068] The process of performing a modeling process on the signal parameter information set, the standard EEG signal sequence, and the EEG signal sequence set to obtain an EEG signal integrity prediction model includes:

[0069] For each EEG signal sequence in the EEG signal sequence set, subtract it from the standard EEG signal sequence to obtain a corresponding difference sequence;

[0070] Using all the difference sequences, construct a difference matrix; the row vectors of the difference matrix are the difference sequences;

[0071] Using the signal parameter information set, construct a signal parameter matrix; the row vectors of the signal parameter matrix are the signal parameter information;

[0072] Using the difference matrix and the signal parameter matrix, construct an integrity optimization model;

[0073] Solve the integrity optimization model to obtain the calculation result A of the evaluation matrix;

[0074] Using the calculation result of the evaluation matrix, construct an EEG signal integrity prediction model;

[0075] The process of performing a volatility evaluation process on the standard EEG signal sequence and the EEG signal sequence set to obtain volatility evaluation information includes:

[0076] S441. For each EEG signal sequence in the EEG signal sequence set, subtract it from the standard EEG signal sequence to obtain a corresponding difference sequence;

[0077] S442. Using all the difference sequences, construct a difference matrix;

[0078] S443. Perform a deviation calculation process on the difference matrix to obtain a deviation vector;

[0079] S444. Perform a correlation calculation process on the difference matrix to obtain a correlation matrix; the element in the i-th row and j-th column of the correlation matrix is obtained by multiplying the i-th row vector and the j-th row vector in the difference matrix;

[0080] S445. Perform eigenvalue decomposition on the correlation matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector obtained by arranging all the eigenvalues of the correlation matrix in descending order of their values.

[0081] S446. Perform a dot product of the deviation vector and the eigenvalue vector to obtain volatility evaluation information.

[0082] The deviation calculation process has the following expression:

[0083] g = (P T V + aI) -1 P T z,

[0084] V = QR -1 ,

[0085] where g is the calculated deviation vector, Q and R are the Q matrix and the R matrix obtained by performing QR decomposition on the difference matrix P respectively, V is an intermediate matrix, a is the largest eigenvalue of the difference matrix P, and z is the eigenvector of the difference matrix P.

[0086] The eigenvalue decomposition process can be implemented using the eigenvalue decomposition algorithm of the matrix.

[0087] The integrity optimization model has the following expression:

[0088]

[0089] subject to AA T = I A ,

[0090] where I A represents the identity matrix with the row dimension of matrix A, E is the integrity difference matrix, E ij represents the element in the i-th row and j-th column of the integrity difference matrix, and the expression of E is:

[0091] E = W(KA - P),

[0092] where W is the weighted transformation matrix, K is the signal parameter matrix. Considering the influence on each item in the corresponding sequence of the signal parameter information set, it can be in the form of a two-dimensional angular discrete matrix with a dimension of Hr×Hs. The element in its i-th row and j-th column is expressed as W ij = cos(2πi / Hr + θ 1 )sin(2πj / Hs + θ 2 ), where θ 1 and θ 2 are the starting angles of the weighted transformation matrix.

[0093] Solve the integrity optimization model to obtain the calculation result A of the evaluation matrix, including:

[0094] S101. Use the initialized evaluation matrix A 0 as the initial solution to determine the increment matrix ΔA;

[0095] S102. Express the objective function as a function f(A) of matrix A;

[0096] S103. With the elements of matrix A as independent variables, obtain the first-order partial derivative matrix of f(A) with respect to the independent variables at the value A 0 ;

[0097] S104. Construct the first solution equation for the iterative increment matrix ΔA 0 ;

[0098]

[0099] S105. Solve the first solution equation to obtain the value of the iterative increment matrix ΔA 0 ; Judge whether |ΔA 0 | is less than the set discrimination threshold. If it is less than the set discrimination threshold, determine A 0 +ΔA 0 as the calculation result A; otherwise, replace A 0 +ΔA 0 for A 0 and execute S103;

[0100] The feature extraction process for the signal parameter information set to obtain the feature signal parameters includes:

[0101] Use the signal parameter information set to construct a signal parameter matrix; the row vectors of the signal parameter matrix are signal parameter information;

[0102] Perform decomposition processing on the signal parameter matrix to obtain a feature matrix;

[0103] Extract the diagonal elements of the feature matrix to obtain a feature vector;

[0104] Confirm the feature vector as the feature signal parameter;

[0105] The vector corresponding to the feature signal parameter is the feature vector.

[0106] The calculation expression of the decomposition processing is:

[0107] Y = UAV,

[0108] Among them, U is the left decomposition matrix, Y is the signal parameter matrix, A is the feature matrix, V is the right decomposition matrix, both U and V are orthogonal matrices, and A is a diagonal matrix;

[0109] The electroencephalogram signal integrity prediction model includes:

[0110] Using the calculation result A of the evaluation matrix, a complete deviation vector estimation sub-model is constructed; the expression of the complete deviation vector estimation sub-model is:

[0111] χ = ρA,

[0112] Among them, ρ is the vector corresponding to the characteristic signal parameter, and χ is the fusion deviation vector;

[0113] Performing deviation fusion calculation processing on the fusion deviation vector and the standard electroencephalogram signal sequence to obtain integrity evaluation information;

[0114] The expression of the deviation fusion calculation processing is:

[0115]

[0116] Among them, qa is the integrity evaluation information, T i () represents the i-th order polynomial of the first kind of Chebyshev polynomial, N1 represents the length of the standard electroencephalogram signal sequence, ρ i represents the i-th element of the vector corresponding to the characteristic signal parameter, μ i represents the i-th element of the standard electroencephalogram signal sequence.

[0117] In the second aspect of the present invention, a test device for a brain-computer interface device in a complex electromagnetic environment is disclosed. The device includes:

[0118] A memory storing executable program code;

[0119] A processor coupled to the memory;

[0120] The processor calls the executable program code stored in the memory and executes the test method for the brain-computer interface device in the complex electromagnetic environment.

[0121] In the third aspect of the present invention, a computer-readable storage medium is disclosed. The computer-readable storage medium stores computer instructions, and when the computer instructions are called by the computer, they are used to execute the test method for the brain-computer interface device in the complex electromagnetic environment.

[0122] In the fourth aspect of the present invention, an information data processing terminal is disclosed. The information data processing terminal is used to implement the test method for the brain-computer interface device in the complex electromagnetic environment.

[0123] In the fifth aspect of the implementation of the present invention, a test device for a brain-computer interface device in a complex electromagnetic environment is disclosed, which is used to implement the test method for the brain-computer interface device in the complex electromagnetic environment, and includes:

[0124] A complex signal generation module and an evaluation module;

[0125] The complex signal generation module is connected to the evaluation model, and is used to obtain a set of signal parameter information, and generate a complex electromagnetic signal according to the set of signal parameter information;

[0126] The evaluation module is used to collect a set of electroencephalogram signal sequences, and perform evaluation processing on the set of signal parameter information, the standard electroencephalogram signal sequence, and the set of electroencephalogram signal sequences to obtain the evaluation result information of the brain-computer interface device in the complex electromagnetic environment.

[0127] The above are only the embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A method for testing a brain-computer interface device in a complex electromagnetic environment, characterized in that: include: S1, obtaining a signal parameter information set; the signal parameter information set includes signal parameter information; The signal parameter information includes frequency, amplitude and phase; S2, using the brain-computer interface device to be tested, collect and obtain a standard EEG signal sequence; S3, generating a complex electromagnetic signal according to the signal parameter information set, and measuring a set of brain electrical signal sequences in a complex electromagnetic signal environment; S4, evaluating and processing the signal parameter information set, the standard EEG signal sequence and the EEG signal sequence set to obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment.

2. The method for testing a brain-computer interface device in a complex electromagnetic environment as claimed in claim 1, characterized in that: The method of generating a complex electromagnetic signal according to the signal parameter information set and measuring a set of brain electrical signal sequences in a complex electromagnetic signal environment includes: S31, generating a corresponding complex electromagnetic signal according to each signal parameter information in the signal parameter information set; S32, placing the brain-computer interface device in the complex electromagnetic signal environment to collect and obtain an electroencephalogram signal sequence; S33, executing S31 to S32 for each signal parameter information in the signal parameter information set, and constructing an EEG signal sequence set using all acquired EEG signal sequences.

3. The method for testing a brain-computer interface device in a complex electromagnetic environment as claimed in claim 1, characterized in that: The signal parameter information set, the standard EEG signal sequence and the EEG signal sequence set are evaluated and processed to obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment, including: S41, modeling the signal parameter information set, the standard EEG signal sequence and the EEG signal sequence set to obtain an EEG signal integrity prediction model; S42, performing feature extraction processing on the signal parameter information set to obtain characteristic signal parameters; S43, using the EEG signal integrity prediction model, calculating and processing the characteristic signal parameters to obtain integrity assessment information; S44, performing a volatility assessment process on the standard EEG signal sequence and the EEG signal sequence set to obtain volatility assessment information; S45, using the integrity assessment information and volatility assessment information, construct assessment result information of the brain-computer interface device in a complex electromagnetic environment.

4. The method for testing a brain-computer interface device in a complex electromagnetic environment as claimed in claim 3, characterized in that: The signal parameter information set, the standard EEG signal sequence and the EEG signal sequence set are modeled to obtain an EEG signal integrity prediction model, including: S411, subtracting each EEG signal sequence in the EEG signal sequence set from the standard EEG signal sequence to obtain a corresponding difference sequence; S412, constructing a difference matrix using all the difference sequences; the row vector of the difference matrix is ​​the difference sequence; S413, constructing a signal parameter matrix using the signal parameter information set; the row vector of the signal parameter matrix is ​​the signal parameter information; S414, constructing an integrity optimization model using the difference matrix and the signal parameter matrix; S415, solving the integrity optimization model to obtain a calculation result of an evaluation matrix; S416, constructing an EEG signal integrity prediction model using the calculation result of the evaluation matrix.

5. The method for testing a brain-computer interface device in a complex electromagnetic environment as claimed in claim 3, characterized in that: The performing of volatility assessment processing on the standard EEG signal sequence and the EEG signal sequence set to obtain volatility assessment information includes: S441, subtracting each EEG signal sequence in the EEG signal sequence set from the standard EEG signal sequence to obtain a corresponding difference sequence; S442, constructing a difference matrix using all the difference sequences; S443, performing deviation calculation processing on the difference matrix to obtain a deviation vector; S444, performing correlation calculation processing on the difference matrix to obtain a correlation matrix; the element of the i-th row and j-th column of the correlation matrix is ​​obtained by multiplying the i-th row vector and the j-th row vector in the difference matrix; S445, performing eigendecomposition processing on the correlation matrix to obtain an eigenvalue vector; the eigenvalue vector is a vector obtained by arranging all eigenvalues ​​of the correlation matrix from large to small; S446, performing vector dot multiplication on the deviation vector and the eigenvalue vector to obtain volatility assessment information.

6. The method for testing a brain-computer interface device in a complex electromagnetic environment as claimed in claim 5, characterized in that: The deviation calculation process is expressed as follows: t=(P T V+aI) -1 P T yes, V=QR -1 , Wherein, t is the calculated deviation vector, Q and R are the Q matrix and R matrix obtained by QR decomposition of the difference matrix P, V is the intermediate matrix, a is the maximum eigenvalue of the difference matrix P, and y is the eigenvector of the difference matrix P.

7. A testing device for a brain-computer interface device in a complex electromagnetic environment, characterized in that: A method for testing a brain-computer interface device in a complex electromagnetic environment according to any one of claims 1 to 6, comprising: Complex signal generation module and evaluation module; The complex signal generating module is connected to the evaluation model and is used to obtain a signal parameter information set and generate a complex electromagnetic signal according to the signal parameter information set; The evaluation module is used to collect and obtain a set of EEG signal sequences, evaluate and process the signal parameter information set, the standard EEG signal sequence and the EEG signal sequence set, and obtain evaluation result information of the brain-computer interface device in a complex electromagnetic environment.

8. A testing device for a brain-computer interface device in a complex electromagnetic environment, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the testing method of the brain-computer interface device in a complex electromagnetic environment as described in any one of claims 1 to 6.

9. A computer storable medium, characterized in that: The computer storable medium stores computer instructions, which, when called by a computer, are used to execute the method for testing a brain-computer interface device in a complex electromagnetic environment as described in any one of claims 1 to 6.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the testing method of the brain-computer interface device in a complex electromagnetic environment as described in any one of claims 1 to 6.

Images