Fatigue monitoring method and device based on near-infrared brain imaging and brain-computer interface

Abstract

The invention discloses a fatigue monitoring method and device based on near-infrared brain imaging and a brain-computer interface. The method comprises the steps that a brain blood oxygen content data set and an electroencephalogram signal set of a user are acquired; the electroencephalogram signal set comprises an alpha-wave signal, a beta-wave signal, a theta-wave signal and a delta-wave signal which are acquired at a plurality of moments; the brain blood oxygen content data set comprises brain blood oxygen content sequences acquired at a plurality of moments; performing fatigue feature extraction on the brain blood oxygen content data set and the electroencephalogram signal set to obtain a fatigue feature set; performing fatigue monitoring evaluation on the fatigue feature set to obtain a fatigue evaluation value; the value of the fatigue evaluation value is mild fatigue, moderate fatigue or severe fatigue.

Description

Technical Field

[0001] The present invention relates to the fields of physiological signal data processing and brain-computer interface technology, and specifically to a fatigue monitoring method and device based on near-infrared brain imaging and brain-computer interface. Background Art

[0002] With the accelerating pace of modern life and increasing work pressure, fatigue has become a significant factor affecting people's work efficiency and quality of life. Especially in work environments that require high concentration and rapid response, such as driving, aerospace, and medical fields, timely and accurate monitoring of fatigue status is crucial for ensuring personnel safety and work quality.

[0003] Currently, commonly used fatigue monitoring methods mainly include those based on physiological indicators (such as heart rate, blood pressure, and electroencephalogram) and those based on behavioral characteristics (such as eye movements, facial expressions, and driving behavior). However, these methods have some limitations, such as the possibility that the measurement of physiological indicators may be interfered with by external factors, and the lack of accuracy and real-time monitoring of behavioral characteristics.

[0004] Near-infrared neuroradiography (fNIRS) is an emerging non-invasive brain function monitoring technology that can monitor changes in blood oxygenation levels in the cerebral cortex in real time, reflecting brain activity. Brain-computer interface (BCI) technology can enable direct communication between the brain and external devices, converting the brain's intentions and states into controllable signals. Summary of the Invention

[0005] The present invention mainly solves the problem of how to achieve fast and accurate fatigue detection of users based on near-infrared brain imaging and brain-computer interface. The present invention discloses a fatigue monitoring method and device based on near-infrared brain imaging and brain-computer interface.

[0006] In a first aspect of an embodiment of the present invention, a fatigue monitoring method based on near-infrared brain imaging and a brain-computer interface is disclosed, comprising:

[0007] S1, collecting a user's brain blood oxygen content dataset and an EEG signal set; the EEG signal set includes alpha wave signals, beta wave signals, theta wave signals, and delta wave signals collected at several moments; the brain blood oxygen content dataset includes brain blood oxygen content sequences collected at several moments;

[0008] S2, performing fatigue feature extraction on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set;

[0009] S3, performing fatigue monitoring and evaluation on the fatigue feature set to obtain a fatigue evaluation value; the fatigue evaluation value can be light fatigue, moderate fatigue or severe fatigue.

[0010] The fatigue feature extraction is performed on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set, including:

[0011] S21, performing EEG fatigue calculation on the α wave signal, β wave signal, θ wave signal, and δ wave signal of the EEG signal set at each moment to obtain an EEG fatigue characteristic value at each moment;

[0012] S22, performing brain fatigue calculation on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain a brain fatigue characteristic value at each moment;

[0013] S23, constructing a fatigue feature set using the EEG fatigue feature values and brain fatigue feature values at all times.

[0014] The EEG fatigue calculation is performed on the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment to obtain the EEG fatigue characteristic value at each moment, including:

[0015] Using the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment, constructing an EEG signal matrix at the moment; the row vector of the EEG signal matrix is a type of signal;

[0016] Performing symplectic geometric modal decomposition on each row vector of the EEG signal matrix to obtain a corresponding decomposition vector;

[0017] Using all decomposition vectors, construct the decomposition matrix;

[0018] Performing normalized modal calculation on the decomposition matrix to obtain a normalized modal matrix;

[0019] Performing singular value calculation and norm calculation on the decomposition matrix to obtain a singular value set and a norm value H respectively;

[0020] Perform a first eigenvalue calculation on the normalized modal matrix to obtain the EEG fatigue eigenvalue at the moment.

[0021] The expression of the normalized modal matrix is:

[0022]

[0023] Among them, sg0 represents the mean of the decomposition matrix, sg ij and ij Represent the elements of the i-th row and j-th column of the decomposition matrix and the EEG signal matrix, respectively, mt ijrepresents the element of the i-th row and j-th column of the normalized modal matrix, m and n represent the row dimension and column dimension of the decomposition matrix respectively, sg i and i denote the mean of the i-th row of the decomposition matrix and the EEG signal matrix respectively;

[0024] The expression for calculating the first feature is:

[0025]

[0026] Among them, ndp is the EEG fatigue characteristic value at the moment, δ i represents the i-th singular value of the singular value set, and represent the minimum and maximum values of the i-th row of the normalized modal matrix, respectively.

[0027] The brain fatigue calculation is performed on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain the brain fatigue characteristic value at each moment, including:

[0028] Obtaining the standard value of brain blood oxygen content;

[0029] subtracting the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set from the brain blood oxygen content standard value to obtain a corresponding difference sequence;

[0030] The cross-correlation calculation is performed on the brain blood oxygen content sequence at each moment and the corresponding difference sequence to obtain the cross-correlation matrix R;

[0031] Performing matrix feature transformation on the cross-correlation matrix to obtain a brain blood oxygen transformation matrix V;

[0032] Calculating the rank value and row vector variance value of the brain blood oxygen conversion matrix;

[0033] Perform a second characteristic calculation on the rank value and the row vector variance value to obtain the brain fatigue characteristic value at the moment.

[0034] The expression of the matrix feature transformation is:

[0035] R=SΛS T ,

[0036]

[0037] Where R = SΛS T Indicates the eigenvalue decomposition of matrix R, S represents the eigenvalue decomposition matrix, Λ represents the intermediate characteristic matrix, Λ * Represents the conjugate matrix of the intermediate characteristic matrix, S *represents the conjugate matrix of the eigendecomposition matrix;

[0038] The expression for calculating the second feature is:

[0039]

[0040] Among them, nbp is the brain fatigue characteristic value at a moment, N1 is the row dimension of the brain blood oxygen conversion matrix, μ and γ i are the rank value of the brain blood oxygen conversion matrix and the variance value of the row vector of the i-th row, γ i is the mean of the variance values of all row vectors.

[0041] In a second aspect of an embodiment of the present invention, a fatigue monitoring device based on near-infrared brain imaging and brain-computer interface is disclosed, which is used to implement the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface, including: a signal acquisition module, a feature extraction module and a fatigue assessment module;

[0042] The signal acquisition module is used to acquire a user's brain blood oxygen content data set and an EEG signal set;

[0043] The feature extraction module is connected to the signal acquisition module and the fatigue assessment module respectively, and is used to extract fatigue features from the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set;

[0044] The fatigue assessment module is used to perform fatigue monitoring and assessment on the fatigue feature set to obtain a fatigue assessment value.

[0045] In a third aspect of an embodiment of the present invention, a fatigue monitoring device based on near-infrared brain imaging and a brain-computer interface is disclosed, the device comprising:

[0046] a memory storing executable program code;

[0047] a processor coupled to the memory;

[0048] The processor calls the executable program code stored in the memory to execute the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0049] In a fourth aspect of an embodiment of the present invention, a computer-storable medium is disclosed, which stores computer instructions. When the computer instructions are called by a computer, they are used to execute the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0050] In a fifth aspect of the embodiments of the present invention, an information data processing terminal is disclosed, which is used to implement the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0051] The beneficial effects of the present invention are:

[0052] This invention combines near-infrared brain imaging with brain-computer interface technology to more comprehensively and accurately monitor brain fatigue, improving the reliability and accuracy of fatigue monitoring. By monitoring fatigue in real time and issuing timely warnings, it helps prevent accidents and errors caused by fatigue, ensuring personnel safety and work quality. This invention provides new technical means and data support for fatigue research, contributing to a deeper understanding of the mechanisms and development patterns of fatigue.

[0053] The present invention integrates multi-dimensional brain-related information by simultaneously collecting the user's brain blood oxygen content data set and EEG signal set. From the perspective of EEG signals, it covers signals of different frequency bands such as α waves, β waves, θ waves and δ waves. These signals will show their own unique change patterns when fatigue occurs. Through a series of processing and feature extraction such as special EEG fatigue calculation, it is possible to comprehensively and meticulously capture signs of fatigue at the level of brain electrical activity. At the same time, combined with the brain blood oxygen content data, considering that changes in brain metabolism during fatigue will be reflected in changes in blood oxygen supply, corresponding brain fatigue calculations are performed to extract features, further assisting in judging the fatigue state from a physiological metabolic perspective, making the overall monitoring of fatigue more accurate, effectively avoiding the misjudgment caused by single indicator monitoring, and accurately distinguishing different degrees of fatigue such as mild fatigue, moderate fatigue and severe fatigue. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Flow chart for the implementation of the method of the present invention;

[0055] Figure 2 It is a composition diagram of the device of the present invention. DETAILED DESCRIPTION

[0056] In order to better understand the content of the present invention, an embodiment is given here.

[0057] Figure 1 4 is an implementation flow chart of the method of the present invention. Figure 2 It is a composition diagram of the device of the present invention.

[0058] In a first aspect of an embodiment of the present invention, a fatigue monitoring method based on near-infrared brain imaging and a brain-computer interface is disclosed, comprising:

[0059] S1, collecting a user's brain blood oxygen content dataset and an EEG signal set; the EEG signal set includes alpha wave signals, beta wave signals, theta wave signals, and delta wave signals collected at several moments; the brain blood oxygen content dataset includes brain blood oxygen content sequences collected at several moments;

[0060] S2, performing fatigue feature extraction on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set;

[0061] S3, performing fatigue monitoring and evaluation on the fatigue feature set to obtain a fatigue evaluation value; the fatigue evaluation value can be light fatigue, moderate fatigue or severe fatigue.

[0062] Unlike traditional fatigue assessment methods based on subjective feelings, this invention analyzes objective brain physiological data. Both EEG signals and brain blood oxygen content data are collected through professional equipment. After scientific and rigorous calculation, feature extraction and evaluation processes, the fatigue assessment value is finally obtained. This greatly reduces the interference of human factors and provides objective and reliable assessment results for fatigue monitoring. It can be applied to multiple fields with high requirements for fatigue monitoring accuracy, such as transportation (long-distance driving fatigue monitoring), aerospace (pilot fatigue status control) and fatigue monitoring of personnel operating complex equipment in industrial production.

[0063] The fatigue feature extraction is performed on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set, including:

[0064] S21, performing EEG fatigue calculation on the α wave signal, β wave signal, θ wave signal, and δ wave signal of the EEG signal set at each moment to obtain an EEG fatigue characteristic value at each moment;

[0065] S22, performing brain fatigue calculation on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain a brain fatigue characteristic value at each moment;

[0066] S23, constructing a fatigue feature set using the EEG fatigue feature values and brain fatigue feature values at all times.

[0067] The EEG fatigue calculation is performed on the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment to obtain the EEG fatigue characteristic value at each moment, including:

[0068] Using the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment, constructing an EEG signal matrix at the moment; the row vector of the EEG signal matrix is a type of signal;

[0069] Performing symplectic geometric modal decomposition on each row vector of the EEG signal matrix to obtain a corresponding decomposition vector;

[0070] Using all decomposition vectors, construct the decomposition matrix;

[0071] Performing normalized modal calculation on the decomposition matrix to obtain a normalized modal matrix;

[0072] The expression of the normalized modal matrix is:

[0073]

[0074] Among them, sg0 represents the mean of the decomposition matrix, sg ij and ij Represent the elements of the i-th row and j-th column of the decomposition matrix and the EEG signal matrix, respectively, mt ij represents the element of the i-th row and j-th column of the normalized modal matrix, m and n represent the row dimension and column dimension of the decomposition matrix respectively, sg i and i denote the mean of the i-th row of the decomposition matrix and the EEG signal matrix respectively;

[0075] Performing singular value calculation and norm calculation on the decomposition matrix to obtain a singular value set and a norm value H respectively;

[0076] Performing a first eigenvalue calculation on the normalized modal matrix to obtain an EEG fatigue eigenvalue at the moment;

[0077] The expression for calculating the first feature is:

[0078]

[0079] Among them, ndp is the EEG fatigue characteristic value at the moment, δ i represents the i-th singular value of the singular value set, and represent the minimum and maximum values of the i-th row of the normalized modal matrix, respectively.

[0080] The brain fatigue calculation is performed on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain the brain fatigue characteristic value at each moment, including:

[0081] Obtaining the standard value of brain blood oxygen content;

[0082] subtracting the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set from the brain blood oxygen content standard value to obtain a corresponding difference sequence;

[0083] The cross-correlation calculation is performed on the brain blood oxygen content sequence at each moment and the corresponding difference sequence to obtain the cross-correlation matrix R;

[0084] Performing matrix feature transformation on the cross-correlation matrix to obtain a brain blood oxygen transformation matrix V;

[0085] Calculating the rank value and row vector variance value of the brain blood oxygen conversion matrix;

[0086] Performing a second characteristic calculation on the rank value and the row vector variance value to obtain a brain fatigue characteristic value at the moment;

[0087] The expression of the matrix feature transformation is:

[0088] R=SΛS T ,

[0089]

[0090] Where R = SΛS T Indicates the eigenvalue decomposition of matrix R, S represents the eigenvalue decomposition matrix, Λ represents the intermediate characteristic matrix, Λ * Represents the conjugate matrix of the intermediate characteristic matrix, S * represents the conjugate matrix of the eigendecomposition matrix;

[0091] The expression for calculating the second feature is:

[0092]

[0093] Among them, nbp is the brain fatigue characteristic value at a moment, N1 is the row dimension of the brain blood oxygen conversion matrix, μ and γ i are the rank value of the brain blood oxygen conversion matrix and the variance value of the row vector of the i-th row, respectively, and γ0 is the mean of all row vector variance values.

[0094] The element in the i-th row and j-th column of the cross-correlation matrix is the cross-correlation value between the brain blood oxygen content sequence and the corresponding difference sequence when the relative sequence delay is (ij);

[0095] The performing fatigue monitoring and evaluation on the fatigue feature set to obtain a fatigue evaluation value includes:

[0096] Using the EEG fatigue feature values at all moments in the fatigue feature set to form a first feature value sequence;

[0097] Using brain fatigue feature values at all moments in the fatigue feature set to form a second feature value sequence;

[0098] Performing a joint evaluation calculation on the first eigenvalue sequence and the second eigenvalue sequence to obtain a fatigue evaluation value;

[0099] Using a preset value interval set, determining the value interval to which the fatigue assessment value belongs, and determining the fatigue degree corresponding to the value interval as the fatigue assessment value;

[0100] The value interval set includes value intervals corresponding to three types of fatigue: mild fatigue, moderate fatigue and severe fatigue.

[0101] The expression for the joint evaluation calculation is:

[0102]

[0103]

[0104] Wherein, RX1 and RX2 are the first intermediate quantity and the second intermediate quantity, respectively, N is the length of the first eigenvalue sequence, PLP is the fatigue assessment value, FFT represents fast Fourier transform, and x(i) and y(i) represent the i-th item of the first eigenvalue sequence and the second eigenvalue sequence, respectively.

[0105] In a second aspect of an embodiment of the present invention, a fatigue monitoring device based on near-infrared brain imaging and brain-computer interface is disclosed, which is used to implement the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface, including: a signal acquisition module, a feature extraction module and a fatigue assessment module;

[0106] The signal acquisition module is used to acquire a user's brain blood oxygen content data set and an EEG signal set;

[0107] The feature extraction module is connected to the signal acquisition module and the fatigue assessment module respectively, and is used to extract fatigue features from the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set;

[0108] The fatigue assessment module is used to perform fatigue monitoring and assessment on the fatigue feature set to obtain a fatigue assessment value.

[0109] The signal acquisition module includes an EEG acquisition submodule and a near-infrared detector; the EEG acquisition submodule is used to acquire an EEG signal set

[0110] The brain blood oxygen content dataset can be realized by using a near-infrared detector;

[0111] The near-infrared detector can be implemented using Artinis' PortaLite MKII.

[0112] In a third aspect of an embodiment of the present invention, a fatigue monitoring device based on near-infrared brain imaging and a brain-computer interface is disclosed, the device comprising:

[0113] a memory storing executable program code;

[0114] a processor coupled to the memory;

[0115] The processor calls the executable program code stored in the memory to execute the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0116] In a fourth aspect of an embodiment of the present invention, a computer-storable medium is disclosed, which stores computer instructions. When the computer instructions are called by a computer, they are used to execute the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0117] In a fifth aspect of the embodiments of the present invention, an information data processing terminal is disclosed, which is used to implement the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface.

[0118] A sixth aspect of the embodiments of the present invention discloses a fatigue monitoring method based on near-infrared brain imaging and brain-computer interface, comprising:

[0119] Step 1: Data Collection

[0120] Near-infrared brain imaging equipment was used to collect blood oxygenation level data from the subjects' cerebral cortex, including changes in the concentrations of oxyhemoglobin (HbO) and deoxyhemoglobin (HbR). Simultaneously, a brain-computer interface device was used to collect the subjects' electroencephalogram (EEG) signals.

[0121] Step 2: Data Preprocessing

[0122] The collected near-infrared brain imaging data and EEG signals are preprocessed, including noise removal, filtering, baseline correction and other operations to improve the quality and reliability of the data.

[0123] Step 3: Feature Extraction

[0124] Characteristic parameters reflecting the brain fatigue state, such as the rate of change of blood oxygenation levels and blood oxygen saturation in specific areas of the cerebral cortex, are extracted from the preprocessed near-infrared brain imaging data.

[0125] Extract fatigue-related features from EEG signals, such as EEG spectral features (such as the power spectral density of α waves, β waves, θ waves and δ waves), changes in EEG rhythms, etc.

[0126] Step 4: Fatigue status assessment

[0127] The extracted near-infrared brain imaging features and EEG features are used to comprehensively evaluate the fatigue state of the test subject and output quantitative indicators of the fatigue degree, such as mild fatigue, moderate fatigue, severe fatigue, etc.

[0128] Step 5: Result output and warning

[0129] The fatigue assessment results are output to the user in an intuitive manner, such as displaying the fatigue level on a display screen, issuing a sound prompt, or sending the results to relevant devices (such as mobile phones, computers, etc.) via wireless communication.

[0130] When the fatigue level of the test subject reaches the preset threshold, the early warning mechanism is activated to remind the test subject to take a rest in time or take appropriate intervention measures.

[0131] Experimental results demonstrate that the fatigue monitoring method presented here accurately monitors the fatigue status of test subjects, with high consistency with the assessment results of a subjective fatigue scale. In practical applications, this method can effectively provide fatigue warnings and intervention recommendations to relevant personnel, demonstrating promising application prospects.

[0132] The foregoing is merely an embodiment of the present invention and is not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A fatigue monitoring method based on near-infrared brain imaging and brain-computer interface, characterized in that: include: S1, collecting a user's brain blood oxygen content dataset and an EEG signal set; the EEG signal set includes alpha wave signals, beta wave signals, theta wave signals, and delta wave signals collected at several moments; the brain blood oxygen content dataset includes brain blood oxygen content sequences collected at several moments; S2, performing fatigue feature extraction on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set; S3, performing fatigue monitoring and evaluation on the fatigue feature set to obtain a fatigue evaluation value; the fatigue evaluation value can be light fatigue, moderate fatigue or severe fatigue.

2. The fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to claim 1, characterized in that: The fatigue feature extraction is performed on the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set, including: S21, performing EEG fatigue calculation on the α wave signal, β wave signal, θ wave signal, and δ wave signal of the EEG signal set at each moment to obtain an EEG fatigue characteristic value at each moment; S22, performing brain fatigue calculation on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain a brain fatigue characteristic value at each moment; S23, constructing a fatigue feature set using the EEG fatigue feature values and brain fatigue feature values at all times.

3. The fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to claim 2, characterized in that: The EEG fatigue calculation is performed on the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment to obtain the EEG fatigue characteristic value at each moment, including: Using the α wave signal, β wave signal, θ wave signal and δ wave signal of the EEG signal set at each moment, constructing an EEG signal matrix at the moment; the row vector of the EEG signal matrix is a type of signal; Performing symplectic geometric modal decomposition on each row vector of the EEG signal matrix to obtain a corresponding decomposition vector; Using all decomposition vectors, construct the decomposition matrix; Performing normalized modal calculation on the decomposition matrix to obtain a normalized modal matrix; Performing singular value calculation and norm calculation on the decomposition matrix to obtain a singular value set and a norm value H respectively; Perform a first eigenvalue calculation on the normalized modal matrix to obtain the EEG fatigue eigenvalue at the moment.

4. The fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to claim 3, characterized in that: The expression of the normalized modal matrix is: Among them, sg0 represents the mean of the decomposition matrix, sg ij and ij Represent the elements of the i-th row and j-th column of the decomposition matrix and the EEG signal matrix, respectively, mt ij represents the element of the i-th row and j-th column of the normalized modal matrix, m and n represent the row dimension and column dimension of the decomposition matrix respectively, sg i and i denote the mean of the i-th row of the decomposition matrix and the EEG signal matrix respectively; The expression for calculating the first feature is: Among them, ndp is the EEG fatigue characteristic value at the moment, δ i represents the i-th singular value of the singular value set, and represent the minimum and maximum values of the i-th row of the normalized modal matrix, respectively.

5. The fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to claim 2, characterized in that: The brain fatigue calculation is performed on the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set to obtain the brain fatigue characteristic value at each moment, including: Obtaining the standard value of brain blood oxygen content; subtracting the brain blood oxygen content sequence at each moment of the brain blood oxygen content data set from the brain blood oxygen content standard value to obtain a corresponding difference sequence; The cross-correlation calculation is performed on the brain blood oxygen content sequence at each moment and the corresponding difference sequence to obtain the cross-correlation matrix R; Performing matrix feature transformation on the cross-correlation matrix to obtain a brain blood oxygen transformation matrix V; Calculating the rank value and row vector variance value of the brain blood oxygen conversion matrix; Perform a second characteristic calculation on the rank value and the row vector variance value to obtain the brain fatigue characteristic value at the moment.

6. The fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to claim 5, characterized in that: The expression of the matrix feature transformation is: R=SΛS T , Where R = SΛS T Indicates the eigenvalue decomposition of matrix R, S represents the eigenvalue decomposition matrix, Λ represents the intermediate characteristic matrix, Λ * Represents the conjugate matrix of the intermediate characteristic matrix, S * represents the conjugate matrix of the eigendecomposition matrix; The expression for calculating the second feature is: Among them, nbp is the brain fatigue characteristic value at a moment, N1 is the row dimension of the brain blood oxygen conversion matrix, μ and γ i are the rank value of the brain blood oxygen conversion matrix and the row vector variance value of the i-th row, respectively, and γ0 is the mean of all row vector variance values.

7. A fatigue monitoring device based on near-infrared brain imaging and brain-computer interface, used to implement the fatigue monitoring method based on near-infrared brain imaging and brain-computer interface as described in any one of claims 1 to 6, characterized in that: include: Signal acquisition module, feature extraction module and fatigue assessment module; The signal acquisition module is used to acquire a user's brain blood oxygen content data set and an EEG signal set; The feature extraction module is connected to the signal acquisition module and the fatigue assessment module respectively, and is used to extract fatigue features from the brain blood oxygen content dataset and the EEG signal set to obtain a fatigue feature set; The fatigue assessment module is used to perform fatigue monitoring and assessment on the fatigue feature set to obtain a fatigue assessment value.

8. A fatigue monitoring device based on near-infrared brain imaging and brain-computer interface, 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 fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to 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 fatigue monitoring method based on near-infrared brain imaging and brain-computer interface according to 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 fatigue monitoring method based on near-infrared brain imaging and brain-computer interface as described in any one of claims 1 to 6.

Images