Two-channel electroencephalogram fatigue detection method, device, equipment, medium and product

Through the dual-channel EEG fatigue detection method, the dual-layer bidirectional long and short-term memory model is used to reduce and identify EEG signals. Combined with physical stimulation, the problems of complex, unreal-time and subjective factors in the existing technology are solved, and efficient , accurate fatigue detection and relief.

CN119014881AInactive Publication Date: 2024-11-26TIANJIN POLYTECHNIC UNIV

Patent Information

Application Number
CN202411124617.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing EEG fatigue detection methods have high computational complexity, are not real-time, and are greatly affected by subjective factors. Traditional equipment is greatly affected by light and occlusion factors, making it difficult to accurately and timely reflect the fatigue status of the subjects.

Method used

The dual-channel EEG fatigue detection method is used to obtain EEG signals for preprocessing and feature extraction, and the two-layer bidirectional long and short-term memory model based on fatigue-induced experiments is used for dimensionality reduction and fatigue identification, and combined with physical stimulation methods to relieve fatigue. Real-time detection and mitigation.

Benefits of technology

It reduces the computational complexity of fatigue detection, improves the accuracy and real-timeness of the detection, can promptly reflect the subject's fatigue status, and quickly and efficiently relieve fatigue through physical stimulation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119014881A_ABST
    Figure CN119014881A_ABST
Patent Text Reader

Abstract

The invention discloses a two-channel electroencephalogram fatigue detection method, device and equipment, a medium and a product, and relates to the field of fatigue detection. The method comprises the following steps: acquiring an electroencephalogram signal; performing preprocessing and feature extraction on the electroencephalogram signal to obtain an extracted signal; inputting the extracted signal into a fatigue detection model, and performing dimension reduction processing and fatigue identification processing to obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long-short-term memory model determined based on electroencephalogram signals collected in a fatigue induction experiment and a corresponding KSS scale; the fatigue detection information is dual-lead combined signal data. According to the invention, fatigue detection can be efficiently realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of fatigue detection, and in particular to a dual-channel EEG fatigue detection method, device, equipment, medium and product. Background Art

[0002] Subjective detection and objective detection are the two main methods for detecting brain fatigue status. Subjective self-assessment mainly involves the subjects filling out a scale based on their subjective mental state and feelings to assess fatigue status. The main scales used are the Karolinska Sleepiness Scale (KSS), the Stanford Sleepiness Scale (SSS), and the Child Fatigue Scale. The subjective assessment of fatigue is affected by factors such as the subject's mood and personality, and the results are often inaccurate. Therefore, using physiological signals to assess fatigue has gradually become a research hotspot. Traditional mental fatigue prediction methods, such as machine vision, have the problem of being greatly affected by lighting and occlusion (wearing glasses). Assessing the degree of brain fatigue by detecting changes in brain waves is considered to be a safe, effective and promising method.

[0003] Electroencephalogram (EEG) signals contain a large amount of physiological and disease information. The purpose of detecting and preventing brain fatigue can be achieved by effectively extracting and classifying EEG signals. Currently, most EEG-based brain fatigue detection uses 32, 64, 128 or 256 multi-channel devices to collect data for analysis. The data volume is large and the calculation is complex. In addition, most EEG-based brain fatigue detection is in the offline detection stage and cannot reflect the fatigue state of the subject in a timely manner. Summary of the invention

[0004] The purpose of this application is to provide a dual-channel EEG fatigue detection method, device, equipment, medium and product, which can efficiently realize fatigue detection.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a dual-channel EEG fatigue detection method, comprising:

[0007] Acquire EEG signals;

[0008] Preprocessing and feature extraction are performed on the EEG signal to obtain an extracted signal;

[0009] The extracted signal is input into a fatigue detection model to perform dimensionality reduction processing and fatigue identification processing to obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long-short-term memory model determined based on the EEG signal collected in the fatigue inducing experiment and the corresponding KSS scale; the fatigue detection information is dual-lead combined signal data.

[0010] Optionally, the dual-channel EEG fatigue detection method further includes:

[0011] Determine fatigue state information according to the fatigue detection information; the fatigue state information includes: fatigue level;

[0012] Determining whether to perform fatigue relief processing based on the fatigue state information;

[0013] If the fatigue status information exceeds the set fatigue level, physical stimulation is used to perform fatigue relief processing.

[0014] Optionally, physical stimulation methods include: 1mA-2mA transcranial direct current anode electrical stimulation, low-frequency magnetic field stimulation with an intensity of 1mT-3mT and a frequency of 50Hz or 100Hz, and random fatigue-relieving music sound stimulation.

[0015] Optionally, acquiring the EEG signal specifically includes: using a 64-channel EEG device to collect 64-channel data, and determining the 64-channel data as the EEG signal.

[0016] Optionally, the preprocessing includes: filtering processing, interpolation processing, elimination processing and independent component analysis processing.

[0017] Optionally, the dual-channel EEG fatigue detection method further includes:

[0018] The fatigue status information is transmitted to the server terminal via a serial port or Bluetooth for display.

[0019] In a second aspect, the present application provides a dual-channel EEG fatigue detection device, comprising:

[0020] A signal acquisition module, used for acquiring EEG signals;

[0021] A signal extraction module, used for preprocessing and feature extraction of the EEG signal to obtain an extracted signal;

[0022] The detection module is used to input the extracted signal into a fatigue detection model, perform dimensionality reduction processing and fatigue identification processing, and obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long short-term memory model determined based on the EEG signal collected in the fatigue inducing experiment and the corresponding KSS scale; the fatigue detection information is dual-lead combined signal data.

[0023] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned dual-channel EEG fatigue detection method.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned dual-channel EEG fatigue detection method.

[0025] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned dual-channel EEG fatigue detection method.

[0026] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0027] The present application provides a dual-channel EEG fatigue detection method, device, equipment, medium and product. Based on the fatigue detection model, the EEG signal after preprocessing and feature extraction is subjected to dimensionality reduction processing and fatigue identification processing to obtain fatigue detection information; since the fatigue detection information is dual-lead combined signal data, the complexity of fatigue detection calculation is reduced; and since the fatigue detection model is a double-layer bidirectional long and short-term memory model determined based on the EEG signal collected in the fatigue induction experiment and the corresponding KSS scale, the accuracy of fatigue detection can be improved. Therefore, the present application can efficiently realize fatigue detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 This is a flow chart of the dual-channel EEG fatigue detection method of this application;

[0030] Figure 2 It is a schematic diagram of the system composition based on dual-channel EEG detection;

[0031] Figure 3 It is a schematic diagram of the process based on dual-channel EEG detection;

[0032] Figure 4 This is a schematic diagram of reducing 64-channel EEG data to dual-channel EEG data;

[0033] Figure 5This is the lead position diagram of dual-channel EEG;

[0034] Figure 6 Flow chart for the fatigue-inducing experimental paradigm;

[0035] Figure 7 A schematic diagram of the structure of a computer device provided in this application. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0038] like Figure 1 As shown, the embodiment of the present application provides a dual-channel EEG fatigue detection method, the method comprising:

[0039] Step 100: Acquire EEG signals.

[0040] In one embodiment, acquiring the EEG signal specifically includes: using a 64-channel EEG device to collect 64-channel data, and determining the 64-channel data as the EEG signal.

[0041] Step 200: Preprocess and extract features of the EEG signal to obtain an extracted signal.

[0042] Preprocessing includes: filtering, interpolation, elimination and independent component analysis.

[0043] Step 300: Input the extracted signal into the fatigue detection model, perform dimensionality reduction processing and fatigue identification processing, and obtain fatigue detection information. The fatigue detection model is a two-layer bidirectional long short-term memory model determined based on the EEG signal collected in the fatigue induction experiment and the corresponding KSS scale; the fatigue detection information is the dual-lead combined signal data.

[0044] In one embodiment, the dual-channel EEG fatigue detection method further includes:

[0045] Fatigue status information is determined according to the fatigue detection information; the fatigue status information includes: fatigue level.

[0046] Whether to perform fatigue relief processing is determined based on the fatigue state information.

[0047] If the fatigue status information exceeds the set fatigue level, physical stimulation is used to relieve fatigue.

[0048] Specifically, the physical stimulation methods include: 1mA-2mA transcranial direct current anode electrical stimulation, low-frequency magnetic field stimulation with an intensity of 1mT-3mT and a frequency of 50Hz or 100Hz, and random fatigue-relieving music sound stimulation.

[0049] As an optional implementation, the dual-channel EEG fatigue detection method further includes:

[0050] The fatigue status information is transmitted to the server terminal via serial port or Bluetooth for display.

[0051] Based on the same inventive concept, the embodiment of the present application also provides a dual-channel EEG fatigue detection device for implementing the dual-channel EEG fatigue detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more dual-channel EEG fatigue detection device embodiments provided below can refer to the limitations of the dual-channel EEG fatigue detection method above, and will not be repeated here.

[0052] In an exemplary embodiment, a dual-channel EEG fatigue detection device is provided, comprising:

[0053] The signal acquisition module is used to acquire EEG signals.

[0054] The signal extraction module is used to preprocess and extract features of the EEG signal to obtain the extracted signal.

[0055] The detection module is used to input the extracted signal into the fatigue detection model, perform dimensionality reduction processing and fatigue identification processing, and obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long short-term memory model determined based on the EEG signals collected in the fatigue inducing experiment and the corresponding KSS scale; the fatigue detection information is the dual-lead combined signal data.

[0056] This application targets redundant channels existing in fatigue detection systems, combines significance analysis with classification results, reduces the number of channels from 64 to 2, and achieves the best performance, reducing computational complexity.

[0057] In addition, this application is based on a two-layer Bi-LSTM algorithm, that is, a fatigue detection model is used to classify the features extracted in the early stage, and a good effect is achieved in fatigue identification based on EEG. Physical intervention equipment is used to relieve fatigue, including sound, electricity and magnetic stimulation, which can quickly and efficiently relieve fatigue.

[0058] In practical applications, such as Figure 3As shown, the operation steps of the method mentioned in this application may also include:

[0059] Step 1: Use a 64-channel EEG device to collect EEG signals.

[0060] Step 2: Send the data to the server terminal or mobile terminal display in real time via the serial port or Bluetooth.

[0061] Step 3: Preprocess and extract features of the acquired EEG signals.

[0062] Step 4: Input the processed 64-channel data into the fatigue detection model, i.e., the two-layer Bi-LSTM model for channel dimension reduction and fatigue identification.

[0063] Step 5: Detect the fatigue status of the human body in real time according to the model and display it on the monitor synchronously.

[0064] Step 6: When the model output fatigue level reaches level three or four (a total of one, two, three and four fatigue levels, the degree of fatigue increases successively), physical stimulation is given to relieve fatigue. That is, physical stimulation intervention is performed when the fatigue level reaches level three or four.

[0065] Step 7: After the stimulation is completed, repeat the above steps to detect the fatigue state after stimulation.

[0066] Specifically, in practical applications, it is mainly divided into three stages: training stage, identification stage and intervention stage.

[0067] Training phase: Use BIOSEMI EEG equipment (64 leads) to collect EEG signals in the resting state (referring to collecting baseline levels when the subjects are not working or performing tasks); collect the KSS sleepiness scale filled out by the subjects.

[0068] The fatigue induction experiment was used to induce fatigue in the subjects; the fatigue induction experiment consisted of a cognitive task 2-back (letters) plus a parity check (numbers), as follows: Figure 6 As shown. In the experiment, letters and numbers appear alternately, with an interval of 800ms. When a letter appears on the screen, you need to judge whether the current letter is the same as the previous letter. If they are the same, press the H key. If they are not the same, do not react. When a number appears on the screen, you need to judge the parity of the current number. If it is an odd number, press the J key, and if it is an even number, press the K key.

[0069] The BIOSEMI EEG device (64 leads) was used to collect EEG signals in the fatigue state (referring to the state of mental fatigue after high-intensity work or fatigue-inducing tasks), and the KSS scale filled in by the subjects was collected.

[0070] Based on the EEG signals collected in the fatigue-inducing experiment and the corresponding KSS scale, a double-layer bidirectional long-short-term memory model, that is, a fatigue detection model, was determined.

[0071] Identification stage: The collected 64-channel EEG data are preprocessed and feature extracted. The preprocessing stage includes filtering, interpolation of bad leads and removal of bad segments, re-referencing and independent component analysis (ICA); the 64-channel data are input into the fatigue detection model for training; and the dual-lead combination O1+O2 with the highest accuracy is selected.

[0072] Intervention phase: When the model outputs that the subject's current fatigue level reaches level three or four, fatigue intervention is performed based on physical stimulation, including 1mA-2mA transcranial direct current anode electrical stimulation, low-frequency magnetic field stimulation with an intensity of 1mT-3mT and a frequency of 50Hz or 100Hz, and sound stimulation of 33 randomly played fatigue-relieving music.

[0073] After the stimulation is completed, the subjects refilled the KSS sleepiness form and collected EEG data again; the data was input into the fatigue detection model to check the fatigue level of the subjects output by the fatigue detection model.

[0074] This application uses EEG signals to analyze fatigue, avoiding the influence of the subject's subjective emotions, personality, etc. The use of dual-channel EEG significantly improves convenience compared to traditional 64-channel and 32-channel EEG, and solves the problem of complex and cumbersome EEG acquisition. The sampling rate of the device is 1000Hz, which ensures the capture of most EEG signals and greatly improves the accuracy of EEG signal acquisition. The real-time output of fatigue level can timely reflect the fatigue state of the subject and improve the efficiency of brain fatigue detection. When it is detected that the subject's fatigue reaches a certain level, physical stimulation is given to relieve fatigue, forming a closed loop, and the impact of physical stimulation on the subject's fatigue state can be more intuitively seen.

[0075] like Figure 2 As shown, in actual application, the signal collected by the EEG acquisition device 101 is sent to the EEG signal receiving computer terminal 102 or the EEG signal receiving mobile terminal 104 to obtain the EEG signal.

[0076] Specifically, the EEG signal receiving computer terminal 102 is used to receive the EEG signal collected by the test person on the EEG collection device 101. The positions of the 64-lead EEG electrodes are as follows: Figure 4 As shown in 301, after the double-layer Bi-LSTM model is reduced to a dual channel, the double electrodes are at O1 and O2, as shown in Figure 5 shown.

[0077] The server terminal 103 is used to process the EEG data received by 102 or 104, and input the processed dual-channel data into the fatigue detection model. The model output result, i.e., fatigue detection information, can be displayed on a computer or mobile terminal. When the fatigue status information reaches fatigue level three or four, physical intervention equipment 105 can be used for physical intervention.

[0078] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a dual-channel EEG fatigue detection is realized.

[0079] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0080] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0081] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0082] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0083] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0084] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0085] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0086] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A dual-channel EEG fatigue detection method, It is characterized in that The dual-channel EEG fatigue detection method comprises: Acquire EEG signals; Preprocessing and feature extraction are performed on the EEG signal to obtain an extracted signal; The extracted signal is input into a fatigue detection model to perform dimensionality reduction processing and fatigue identification processing to obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long-short-term memory model determined based on the EEG signal collected in the fatigue inducing experiment and the corresponding KSS scale; the fatigue detection information is dual-lead combined signal data.

2. The dual-channel EEG fatigue detection method according to claim 1, It is characterized in that The dual-channel EEG fatigue detection method also includes: Determine fatigue state information according to the fatigue detection information; the fatigue state information includes: fatigue level; Determining whether to perform fatigue relief processing based on the fatigue state information; If the fatigue status information exceeds the set fatigue level, physical stimulation is used to perform fatigue relief processing.

3. The dual-channel EEG fatigue detection method according to claim 2, It is characterized in that Physical stimulation methods include: 1mA-2mA transcranial direct current anode electrical stimulation, low-frequency magnetic field stimulation with an intensity of 1mT-3mT and a frequency of 50Hz or 100Hz, and random fatigue-relieving music sound stimulation.

4. The dual-channel EEG fatigue detection method according to claim 1, It is characterized in that Acquiring the EEG signal specifically includes: using a 64-channel EEG device to collect 64-channel data, and determining the 64-channel data as the EEG signal.

5. The dual-channel EEG fatigue detection method according to claim 1, It is characterized in that The preprocessing includes: filtering processing, interpolation processing, elimination processing and independent component analysis processing.

6. The dual-channel EEG fatigue detection method according to claim 2, It is characterized in that The dual-channel EEG fatigue detection method also includes: The fatigue status information is transmitted to the server terminal via a serial port or Bluetooth for display.

7. A dual-channel EEG fatigue detection device, It is characterized in that The dual-channel EEG fatigue detection device comprises: A signal acquisition module, used for acquiring EEG signals; A signal extraction module, used for preprocessing and feature extraction of the EEG signal to obtain an extracted signal; The detection module is used to input the extracted signal into a fatigue detection model, perform dimensionality reduction processing and fatigue identification processing, and obtain fatigue detection information; the fatigue detection model is a double-layer bidirectional long short-term memory model determined based on the EEG signal collected in the fatigue inducing experiment and the corresponding KSS scale; the fatigue detection information is dual-lead combined signal data.

8. A computer device, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the dual-channel EEG fatigue detection method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the dual-channel EEG fatigue detection method described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the dual-channel EEG fatigue detection method described in any one of claims 1 to 6 is implemented.

Citation Information

Patent Citations

  • A driver fatigue detection system based on electroencephalogram (EEG) signals

    CN102274032A

  • Mental fatigue intervention device and method

    CN111973880A

  • Cross-subject fatigue state detection method and system based on multi-scale electroencephalogram characteristics

    CN114997215A

  • Driving fatigue state monitoring method and device, electronic equipment and storage medium

    CN116196003A

  • Mental fatigue state monitoring system and method based on multi-dimensional physiological signals

    CN117414136A

Cited By

  • Fatigue intervention method, system, equipment, medium and product

    CN119818800A

  • A fatigue intervention method, system, device, medium, and product

    CN119818800B