A method, device, medium and program product for fatigue real-time monitoring and negative feedback regulation

Abstract

The application provides a method, device, medium and program product for fatigue real-time monitoring and negative feedback regulation, and relates to the field of intelligent medical treatment. The method comprises the following steps: acquiring electroencephalogram and electrooculogram signals and blood oxygen saturation data of a subject; the electroencephalogram and electrooculogram signals comprise signals of FP1 and FP2 sites; separating electroencephalogram signals and electrooculogram signals from the electroencephalogram and electrooculogram signals; calculating fatigue degree based on the electroencephalogram signals, electrooculogram signals and blood oxygen saturation data; and when the fatigue degree reaches a set threshold, implementing transcranial electrical stimulation on the subject by triggering electrodes located in the frontal lobe cortex. The application improves brain cognitive efficiency by using a multi-modal stimulation paradigm and perfects the key technical system of brain function enhancement.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent medical treatment, and more particularly, to a method, device, medium and program product for real-time monitoring and negative feedback regulation of fatigue. BACKGROUND

[0002] Fatigue refers to a state in which the labor efficiency tends to decrease due to long time or excessive nervous physical or mental work under certain environmental conditions. In medicine, fatigue can be divided into physiological fatigue and psychological fatigue according to the nature of fatigue. The evaluation of fatigue state can be carried out by subjective and objective methods. The subjective evaluation method mainly depends on subjective questionnaire, self-recording table, sleep habit questionnaire and Stanford sleep scale table to evaluate the fatigue degree of the subjects. The objective evaluation method mainly starts from the medical point of view, and uses medical instruments, equipment and other auxiliary tools to test the changes of some indexes of the subjects in the aspects of human behavior, physiology and biochemistry, so as to determine the fatigue degree. The subjective evaluation method is a widely used method for evaluating fatigue, which has the advantages of simple operation, directness, low cost, no interference to task completion and easy acceptance. However, this method is difficult to quantify the grade and degree of fatigue, and there are obvious differences in the understanding of each person, so the result is often not satisfactory.

[0003] In a complex work environment, high-load task workers or high-alert post personnel, such as astronauts, pilots, etc., need to maintain long-time and high-efficiency brain information processing and cognitive ability to ensure stable and efficient work performance. However, due to mental overload, high-intensity work and other problems, the efficiency of high-brain activity is difficult to maintain, the brain cognitive fatigue is easy to occur, and the alertness, memory, analysis and decision-making ability and other brain cognitive functions are decreased. Since the effective target of brain function enhancement intervention is not clear, the portability of the enhancement device is poor, and there is a lack of specific, good compliance and significant effect of brain cognitive efficiency maintenance and enhancement measures. SUMMARY

[0004] The present application aims to at least solve one of the technical problems existing in the prior art. To this end, the present application provides a method, device, medium and program product for real-time monitoring and negative feedback regulation of fatigue; the method improves brain cognitive efficiency by using a multi-modal stimulation paradigm, and perfects the key technical system of brain function enhancement.

[0005] The first aspect of the present application discloses a method for real-time monitoring and negative feedback regulation of fatigue, the method comprising:

[0006] 101, obtaining electroencephalogram and electrooculogram signals and blood oxygen saturation data of a subject; the electroencephalogram and electrooculogram signals include signals of FP1 and FP2 sites; the electroencephalogram and electrooculogram signals are separated from the electroencephalogram and electrooculogram signals; 102, calculating fatigue degree based on the electroencephalogram, electrooculogram and blood oxygen saturation data; 103, when the fatigue degree reaches a set threshold, transcranial electrical stimulation is implemented on the subject by triggering electrodes located in the prefrontal cortex.

[0007] In some embodiments, the prefrontal cortex includes any two or more of the following stimulation sites: FP1, FP2, F3, and Fz.

[0008] Optionally, the stimulation sites of the transcranial electrical stimulation further include: vagus nerves of the left and right auricles.

[0009] Optionally, the blood oxygen saturation data is obtained by a blood oxygen saturation acquisition sensor.

[0010] In some embodiments, the method of separating the electroencephalogram and electrooculogram signals from the electroencephalogram and electrooculogram signals includes: calculating a long-time difference metric electrooculogram fluctuation amplitude of the electroencephalogram and electrooculogram signals; obtaining an amplitude envelope of the electroencephalogram and electrooculogram signals using a low-pass filter, and detecting start and end points of the electrooculogram signals using a double-threshold method; decomposing the electroencephalogram and electrooculogram signals, introducing a Birgé-Massart strategy to adaptively determine a threshold value of wavelet coefficients; accurately estimating the electrooculogram signals through wavelet reconstruction, and decoupling the estimated electrooculogram signals from the original electroencephalogram and electrooculogram signals to separate the electroencephalogram and electrooculogram signals.

[0011] In some embodiments, the method of calculating the fatigue degree includes:

[0012] Inputting the electroencephalogram, electrooculogram and blood oxygen saturation data into a real-time fatigue state evaluation model to calculate the fatigue degree; the real-time fatigue state evaluation model is constructed based on a few-channel fatigue decoding algorithm of a Transformer and an attention mechanism;

[0013] Optionally, the method of constructing the real-time fatigue state evaluation model includes:

[0014] Obtaining a data set of a PVT paradigm for a training set; inputting the data set into a CNN structure to extract local features of electroencephalogram (EEG) signals, using a Transformer to extract long-distance correlations of the EEG signals, while paying attention to local features and global features of the data; introducing a channel attention mechanism and a spatial attention mechanism to measure the importance weight size of different channels and different spatial positions of the features for the decoding task; using a feature fusion strategy to extract feature maps containing multi-layer information; inputting the feature maps into a classifier for continuous optimization to obtain the constructed real-time fatigue state evaluation model.

[0015] In some embodiments, the transcranial electrical stimulation regimen comprises any one or more of: stimulation site, stimulation intensity, stimulation pulse waveform, stimulation frequency, stimulation time.

[0016] Optionally, the frequency calculation method comprises: taking any two last points located just before the falling edge of the waveform, calculating the difference of the data frame indexes of the two points, and the frequency is 250

[0017] (the number of falling edges between the two points) / I d .

[0018] In some embodiments, the method further comprises determining the prediction result of whether the subject is in a fatigue state, a transition state or a wakeful state.

[0019] In some embodiments, the electroencephalogram and electrooculogram signal is a pre-processed signal, and the pre-processing method comprises: eliminating high-frequency interference, differential amplification, and converting into a digital signal.

[0020] The second aspect of the application discloses a computer device, the device comprising: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to realize the steps of the above method.

[0021] The third aspect of the application discloses a computer readable storage medium, which stores a computer program, and the computer program realizes the steps of the above method when executed by a processor.

[0022] The fourth aspect of the application discloses a computer program product, comprising a computer program, which realizes the steps of the above method when executed by a processor.

[0023] The application has the following beneficial effects:

[0024] The application innovatively discloses a method for real-time monitoring and negative feedback regulation of fatigue, which changes the position of data collection, collects electroencephalogram and electrooculogram signals based on FP1 and FP2 electrodes, separates the electroencephalogram signals and the electrooculogram signals through an embedded algorithm, and realizes real-time monitoring of the fatigue state of the human body based on the electroencephalogram signals, the electrooculogram signals and blood oxygen saturation data. When the fatigue of the subject reaches a threshold value, an electrical stimulation module is automatically started to stimulate the frontal lobe cortex FP1, FP2, Fz and F3 brain regions and the auricular vagus nerve to relieve the fatigue of the subject. Thus, a real-time fatigue monitoring and electrical stimulation closed-loop system is formed to complete the biological self-feedback regulation function. According to the state, the stimulation parameters are adjusted to complete a cycle, and through adaptive parameter matching, the biological feedback intervention effect is enhanced. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0026] Figure 1 is a method flowchart provided by the first aspect of the embodiments of the present application;

[0027] Figure 2 is a schematic diagram of a system for real-time monitoring and negative feedback regulation of fatigue provided by the embodiments of the present application;

[0028] Figure 3 is a schematic diagram of a computer device provided by the embodiments of the present application;

[0029] Figure 4 is a schematic diagram of the architecture of an exemplary computing device provided by the embodiments of the present application;

[0030] Figure 5 is a schematic diagram of a storage medium provided by the embodiments of the present application;

[0031] Figure 6 is a schematic diagram of a prototype provided by the embodiments of the present application;

[0032] Figure 7 is a schematic diagram of the electrode distribution inside the prototype provided by the embodiments of the present application;

[0033] Figure 8 is a front view of the electrode distribution inside the prototype provided by the embodiments of the present application;

[0034] Figure 9 is a functional block diagram of the circuit of the prototype provided by the embodiments of the present application;

[0035] Figure 10 is a schematic diagram of the data transmission of the device provided by the embodiments of the present application;

[0036] Figure 11 is a waveform diagram of the self-checking voltage value of the FP1 channel provided by the embodiments of the present application;

[0037] Figure 12 is a schematic diagram of the construction method of the real-time fatigue state evaluation model provided by the embodiments of the present application.

[0038] In the figure, 1, head-mounted device; 11, forehead detection structure; 12, fixed structure; 13, blood oxygen and degree acquisition sensor; 14, electric stimulation ear clip; 15, FP1 electrode; 16, F3 electrode; 17, FP1 and F3 protective cover; 18, FP2 electrode; 19, FP2 protective cover; 110, FZ electrode; 111, FZ and blood oxygen protective cover; 112, protective cover fixing buckle; 2, master control device. DETAILED DESCRIPTION

[0039] In order to enable personnel in the technical field to better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application.

[0040] In some of the processes described in this specification and in the accompanying drawings, multiple operations are described in a specific order. However, it should be clear that these operations can be performed in a different order or in parallel, and the sequence of operations such as 101, 102, etc. is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel. It should be noted that the "first", "second", etc. described herein are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence. Also, "first" and "second" are different types.

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0042] Figure 1 It is a flow chart of a method for real-time monitoring and negative feedback regulation of fatigue provided by the embodiments of the present application. Specifically, the method comprises the following steps:

[0043] 101: Obtain the brain electrical and ocular electrical signals and blood oxygen saturation data of the subject; the brain electrical and ocular electrical signals include the signals of FP1 and FP2 sites; the brain electrical signals and ocular electrical signals are separated from the brain electrical and ocular electrical signals;

[0044] In some embodiments, the term "subject" or "testee" or "test sample" used herein refers to any animal (e.g., a mammal), including but not limited to a human, a non-human primate, a rodent, etc., who will be the recipient of a particular treatment. Generally, the terms "subject" and "patient" are used interchangeably herein when referring to a human subject. Preferably, the subject is a human.

[0045] In some embodiments, the blood oxygen saturation data is collected by a blood oxygen saturation collection sensor.

[0046] In some embodiments, the method for separating the electroencephalogram signal and the electrooculogram signal from the electroencephalogram electrooculogram signal comprises: calculating the long-time difference metric electrooculogram fluctuation amplitude of the electroencephalogram electrooculogram signal; obtaining the amplitude envelope of the electroencephalogram electrooculogram signal by using a low-pass filter, and detecting the start and end points of the electrooculogram signal by using a double-threshold method; decomposing the electroencephalogram electrooculogram signal, introducing the Birgé-Massart strategy to adaptively determine the threshold value of the wavelet coefficient; accurately estimating the electrooculogram signal through wavelet reconstruction, and decoupling the estimated electrooculogram signal from the original electroencephalogram electrooculogram signal to separate the electroencephalogram signal and the electrooculogram signal.

[0047] In some embodiments, the electroencephalogram electrooculogram signal is a preprocessed signal, and the preprocessing method comprises: eliminating high-frequency interference, differential amplification, and converting into a digital signal.

[0048] 102: calculating the fatigue degree based on the electroencephalogram signal, the electrooculogram signal, and the blood oxygen saturation data;

[0049] In some embodiments, the method for calculating the fatigue degree comprises: inputting the electroencephalogram signal, the electrooculogram signal, and the blood oxygen saturation data into a real-time fatigue state evaluation model to calculate the fatigue degree; the real-time fatigue state evaluation model is constructed based on a few-channel fatigue decoding algorithm of a Transformer and an attention mechanism; and the real-time fatigue state evaluation model is defined as an MFFN model.

[0050] Optionally, the method for constructing the real-time fatigue state evaluation model comprises: acquiring a data set of a training set performing a PVT paradigm, specifically, an AINS-FA2 data set; inputting the data set into a CNN structure to extract local features of an electroencephalogram (EEG) signal, using a Transformer to extract long-distance correlation of the EEG signal, and simultaneously paying attention to local features and global features of the data; introducing a channel attention mechanism and a spatial attention mechanism to measure the importance weight size of different channels and different spatial positions of the features for a decoding task; adopting a feature fusion strategy to make the model pay more attention to information that is more helpful for the decoding task, and extract a feature map containing multi-layer information; inputting the feature map into a classifier for continuous optimization to obtain a constructed real-time fatigue state evaluation model. The algorithm can achieve an identification accuracy of 86.7% on a few-channel (only including FP1 and FP2 electrodes) data. Specifically as shown in Figure 12

[0051] The PVT paradigm is a psychomotor vigilance task. The PVT task is a simple key pressing task, which has the characteristics of simple operation, no practice effect, high sensitivity to sleep deprivation and circadian rhythm change, etc. During the experiment, a red circular pattern will be randomly displayed on the screen, and the subject needs to press the space bar quickly to respond to the appearance of the pattern. This task not only has high repeatability, but also requires the subject to maintain high concentration during the entire experiment. The repeatability of this task will cause the cognitive ability of the subject to gradually decline, thereby inducing the fatigue of the subject. During the experiment, the subject's reaction time from the screen displaying the pattern to the subject pressing the space bar to respond is recorded, and the change of the subject's reaction time during the entire experiment can assist in verifying the process of the subject entering the fatigue state.

[0052] For the entire experiment, the average reaction time in the window is calculated using a sliding window, the sliding window covers 10 experiments each time, and the sliding step is 1 experiment, to obtain the average reaction time change graph of the subject. As the experiment progresses, the average reaction time of the subject increases, and the fatigue degree of the subject gradually deepens.

[0053] 103: When the fatigue degree reaches a set threshold, transcranial electrical stimulation is performed on the subject by triggering electrodes located in the prefrontal cortex;

[0054] In some embodiments, the prefrontal cortex includes any two or more of the following stimulation sites: FP1, FP2, F3, Fz; the materials used for the FP1, FP2, F3, Fz electrodes are the same, except that the functions are different.

[0055] Optionally, the stimulation site of the transcranial electrical stimulation further comprises: the vagus nerve of the left and right auricles; relieving the fatigue state of the subject and restoring the cognitive function.

[0056] ​In some embodiments, the transcranial electrical stimulation regimen comprises any one or more of: stimulation site, stimulation intensity, stimulation pulse waveform, stimulation frequency, stimulation time.

[0057] Optionally, the frequency calculation method comprises: taking any two last points located just before the falling edge of the waveform, calculating the difference of the data frame indexes of the two points, and the frequency is 250*

[0058] (the number of falling edges between the two points) / I d .

[0059] In some embodiments, the method further comprises determining the prediction result of whether the subject is in a fatigue state, a transition state or a wakeful state.

[0060] In some embodiments, the threshold is obtained by training the training set samples, which can be a specific threshold or an interval range, and the specific form is not limited in the embodiment.

[0061] In some embodiments, the electrodes and the blood oxygen saturation acquisition sensor in the application are arranged in Figure 6 、 Figure 7 and Figure 8 the prototype, the prototype comprises a head-mounted device, the head-mounted device comprises a forehead detection structure and a fixing structure connected; the forehead detection structure is provided with electrodes for collecting electroencephalogram and electrical stimulation, a blood oxygen saturation acquisition sensor and an electrical stimulation ear clip, the electrodes and the blood oxygen saturation acquisition sensor are in close contact with the forehead skin, and the electrical stimulation ear clip is clamped in the left ear auricle vagus nerve region; the electrodes comprise at least FP1 and FP2 electrodes for collecting electroencephalogram signals of FP1 and FP2 brain regions and negative feedback electrical stimulation of FP1 and FP2 brain regions of prefrontal cortex, and the blood oxygen saturation acquisition sensor is located between the FP1 and FP2 electrodes.

[0062] In some embodiments, the electroencephalogram signals collected by the FP1 and FP2 electrodes comprise electrooculogram signals, and the electrooculogram signals are decoupled from the collected electroencephalogram signals by using a decoupling algorithm.

[0063] In some embodiments, the electrodes further comprise at least FP3 and FZ electrical stimulation electrodes located in FP3 and FZ brain regions, in a normal vision state, the connecting line between the centers of the FP3 and FZ electrical stimulation electrodes is parallel to the horizontal line; the connecting line between the center of the FP3 electrical stimulation electrode and the center of the FP1 electrical stimulation electrode is perpendicular to the horizontal line, and the FZ electrical stimulation electrode is located at the upper end of the blood oxygen saturation acquisition sensor.

[0064] In some embodiments, the forehead detection structure further comprises a protective cover for protecting the electrodes, the protective cover being fixed to the forehead detection structure by a fixing buckle; in particular, the protective cover mainly comprises FP1 and FP3 protective covers, Fz and blood oxygen protective covers, and an FP2 protective cover.

[0065] In some embodiments, the forehead detection structure further comprises a reference electrode, which is attached to the skin of the left and right ears by conductive gel.

[0066] Optionally, the inner surface of the forehead detection structure is consistent with the curvature of the forehead.

[0067] In some embodiments, the fixing structure is an arc-shaped structure consistent with the curvature of the back of the head; the inner surface of the fixing structure is provided with a protective pad to ensure the comfort of the subject.

[0068] In some embodiments, the arc-shaped structure is further provided with a knob for adjusting the tightness, which is suitable for different head circumferences and ensures the comfort.

[0069] In some embodiments, the head-mounted device further comprises an anti-falling structure, the two ends of which can rotate relative to the forehead detection structure or the fixing structure; the two ends of the anti-falling structure are symmetrically arranged on the two sides of the connection between the forehead detection structure or the fixing structure or both; the anti-falling structure is provided in the shape of an integrated hairband or a separated arc.

[0070] Optionally, the inner surface of the anti-falling structure is provided with a protective pad to improve the wearing comfort and prevent falling off.

[0071] In some embodiments, the device further comprises a master control device and a host computer, the head-mounted device being connected to the master control device, and the master control device being connected to the host computer.

[0072] In a specific embodiment, the master control device in the head-mounted device comprises an electroencephalogram acquisition module, an electrical stimulation module, and a data conversion module; the host computer is installed with data processing software (electroencephalogram signal processing, fatigue decoding algorithm, and electrical stimulation self-feedback), which receives electroencephalogram data and blood oxygen data, and performs real-time acquisition, display, calculation, and processing, and real-time calculation of the fatigue degree of the subject; when the subject reaches the fatigue threshold, the subject is subjected to electrical pulse stimulation through the negative feedback electrical stimulation module, so as to relieve the fatigue state of the subject and restore cognitive function.

[0073] In another specific embodiment, the connection mode between the head-mounted device and the master device, and between the master device and the host computer comprises a communication connection, which is a connection mode for transmitting and interacting through a model to constitute communication between connected devices, and includes wired connection and wireless connection, such as connection through a data line, wireless connection such as Bluetooth and WiFi connection; the electrical connection is one of the wired connections, and the electrical connection can be understood as a form of connection between different components through a signal-transmissible physical circuit such as a PCB copper foil or a wire in a circuit structure. The main purpose is to complete data interaction.

[0074] In one embodiment, the protective pad is a sponge pad or a silica gel pad, which is not limited herein.

[0075] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present application, as Figure 3 shown, the device 2000 can include one or more processors 2010 and one or more memories 2020; wherein the memory has computer readable code stored therein, which when run by the one or more processors, can execute the method as described above.

[0076] The processor in the embodiment can be an integrated circuit chip with a signal processing capability. The above-mentioned processor can be a general processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The methods, operations and logic block diagrams disclosed in the embodiments of the present disclosure can be implemented or executed by the above-mentioned processor. The general processor can be a microprocessor or the processor can also be any conventional processor or the like, which can be of X86 architecture or ARM architecture.

[0077] Generally, various example embodiments of the present disclosure can be implemented in hardware or special-purpose circuitry, software, firmware, logic, or any combination thereof. Certain aspects can be implemented in hardware, while other aspects can be implemented in firmware or software which can be executed by a controller, microprocessor or other computing device. When aspects of the present disclosure are illustrated or described as a block diagram, flow chart, or using some other pictorial representation, it will be understood that the blocks, devices, systems, techniques or methods described herein can be implemented in hardware, software, firmware, special-purpose circuitry or logic, general-purpose hardware or controller or other computing device, or some combination thereof.

[0078] For example, the method or device according to the embodiments of the present disclosure can also be implemented by means of the architecture of the computing device 3000 shown in Figure 4 . As Figure 4As shown, the computing device 3000 can include a bus 3010, one or more CPUs 3020, a read only memory (ROM) 3030, a random access memory (RAM) 3040, a communication port connected to a network 3050, an input / output component 3060, a hard disk 3070, etc. The storage devices in the computing device 3000, such as the ROM 3030 or the hard disk 3070, can store various data or files used in processing and / or communication of the method provided by the present disclosure and the program instructions executed by the CPU. The computing device 3000 can also include a user interface 3080. Of course, Figure 4 The architecture shown is exemplary only, and in implementing different devices, components shown can be omitted, components other than those shown can be implemented, and / or different arrangements of the components can be implemented depending on actual needs. Figure 4 One or more components of the computing device shown.

[0079] The embodiments of the present disclosure also provide a computer readable storage medium, such as Figure 5 As shown, a schematic diagram of a storage medium 4000 provided by the embodiments of the present disclosure is shown, and the computer readable instructions 4010 are stored on the computer storage medium 4020. When the computer readable instructions 4010 are executed by a processor, the method according to the embodiments of the present disclosure described with reference to the above figures can be executed. The computer readable storage medium in the embodiments of the present disclosure can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can be a read only memory (ROM), a programmable read only memory (PROM), an erasable programmable read only memory (EPROM), an electrically erasable programmable read only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of RAM can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct ram bus random access memory (DR RAM). It should be noted that the memory of the method described herein is intended to include, but not be limited to, these and any other suitable types of memory. It should be noted that the memory of the method described herein is intended to include, but not be limited to, these and any other suitable types of memory.

[0080] The embodiments of the present disclosure also provide a computer program product or system, including a computer program, which, when executed by a processor, implements the steps of the above method.

[0081] In some embodiments, the embodiments also disclose a system for real-time monitoring and negative feedback regulation of fatigue, such asFigure 2 The system comprises:

[0082] a data acquisition module 201 configured to acquire electroencephalogram and electrooculogram signals and blood oxygen saturation data of a subject; the electroencephalogram and electrooculogram signals comprise signals of FP1 and FP2 sites; the electroencephalogram and electrooculogram signals are separated to obtain electroencephalogram signals and electrooculogram signals;

[0083] a fatigue degree calculation module 202 configured to calculate a fatigue degree based on the electroencephalogram signals, electrooculogram signals and blood oxygen saturation data;

[0084] a regulation judgment module 203 configured to implement transcranial electrical stimulation on the subject by triggering electrodes located in the frontal lobe cortex when the fatigue degree reaches a set threshold value; Embodiments:

[0086] 1. Functional design of the principle prototype: The principle prototype of real-time monitoring of brain fatigue and self-feedback cognitive enhancement is an advanced wearable smart principle prototype. The prototype can accurately collect, process and display physiological signals such as EEG signals, electrooculogram and blood oxygen saturation of the subject in FP1 and FP2 brain regions in real time. The signals are coupled by the built-in algorithm to monitor the fatigue state of the human body in real time. When the subject's fatigue reaches the fatigue threshold, the automatic start of the electrical stimulation module stimulates the frontal lobe cortex FP1, FP2, Fz, F3 brain region and the auricular vagus nerve to relieve the fatigue of the subject. Thus, a real-time fatigue monitoring and electrical stimulation closed-loop system is formed to complete the biological self-feedback regulation function. The device optimizes the human-computer interaction experience, promotes the deep integration of man and machine, and is suitable for fatigue training in various scenes.

[0087] The modes of the principle prototype include:

[0088] Device form: smart monitoring headband; functions and parameters: 8 light sources, 2 detectors fNIR, left and right EEG; fNIR and EEG data stream synchronous acquisition; maximum sampling rate up to 240Hz; data acquisition mode: Type C or Bluetooth; real-time data acquisition, recording left and right brain α, β, γ, θ power spectrum and left and right brain region brain oxygen content changes.

[0089] Device form: smart tablet or notebook computer; functions and parameters: data interface (USB, Bluetooth); signal processing, analysis, recording; brain mental fatigue state algorithm; automatic generation of stimulation scheme and parameters (position, intensity, frequency, waveform, duration, etc.); automatic feedback mode: after starting stimulation, real-time evaluation of fatigue state, adjustment of stimulation parameters according to the state, completion of a cycle, through adaptive parameter matching, to enhance the effect of biological feedback intervention.

[0090] Device form: Headset / Headband stimulation electrode; Function and parameters: brain stimulation site selection; stimulation intensity modulation (0-10 mA); stimulation pulse waveform selection (square wave, triangular wave); stimulation frequency adjustment and duty cycle (0-50 Hz); stimulation time (0-30 min).

[0091] 2. Principle prototype composition: The principle prototype is composed of three parts: a headset, a main control module, and an upper computer. The headset is composed of an oxygen saturation module, an electroencephalogram electrode, and a stimulation electrode; the main control module gathers physiological signals and interacts with the upper computer through USB for data exchange. The main control module is composed of an electroencephalogram acquisition module, an electrical stimulation module, a data conversion module, etc. The upper computer installs self-developed electroencephalogram signal processing, fatigue decoding algorithm, and electrical stimulation self-feedback software; this module is used for real-time acquisition, display, and calculation processing of hardware data, and real-time calculation of the fatigue degree of the subject. When the subject reaches the fatigue threshold, the negative feedback electrical stimulation module is used to stimulate the subject with an electrical pulse to relieve the subject's fatigue state and restore cognitive function.

[0092] 2.1 Appearance of the prototype: As shown in the schematic diagram of the brain fatigue real-time monitoring and self-feedback cognitive enhancement principle prototype. Figure 6

[0093] 2.2 Structure diagram of the principle prototype:

[0094] 2.2.1 Overall structure diagram of the principle prototype: as shown. Figure 6

[0095] 2.2.2 Headset of the principle prototype: After the design of the principle prototype headset, a silicone (model 8400, Shore hardness 40 degrees) material 3D print is made for the part that fits the forehead. The use of silicone ensures that the electroencephalogram acquisition electrode, oxygen saturation, and transcranial electrical stimulation electrode are well embedded in the headset, and the comfort of the subject's skin is ensured. The back of the headset is designed with a sponge backing to ensure the comfort of the subject. As shown in the electrode distribution diagram inside the prototype, Figure 7 As shown in the front view of the forehead of the prototype, Figure 8

[0096] 2.2.3 Main control module of the principle prototype: After the design of the principle prototype main control module, a UV resin (ultraviolet light sensitive resin) material 3D print is made. After polishing, a white opaque paint is applied to improve the appearance and also to effectively protect the circuit board.

[0097] 3. Introduction of each module of the principle prototype:

[0098] 3.1 Overall flow and deployment structure diagram of the principle prototype: As shown in the functional block diagram of the prototype circuit, Figure 9

[0099] ​​​​3.1.1 Host computer: 1) Host computer configuration requirements: CPU: not less than i5 quad-core; memory: not less than 8G; hard disk: not less than 512M; display: not less than 1080P; WIN10 system or higher version; 2) Self-feedback software: used for real-time acquisition, display, calculation and processing of data of hardware, and according to the fatigue degree obtained by calculation, the stimulation parameters are output in a self-feedback mode to adjust the fatigue degree of the user, and the acquisition, calculation and self-feedback data in the process are recorded to facilitate the research of researchers on the self-feedback process.

[0100] 3.1.2 Master module: 1) Electroencephalogram module; 1.1) Electroencephalogram acquisition: The module acquires electroencephalogram signals through silver chloride dry electrodes and high-precision digital-to-analog conversion front end. The silver chloride dry electrodes in the head-mounted device are connected to the module, and the electroencephalogram signals are input into the module. The electroencephalogram signals are first subjected to preposition low-pass RC filter circuit to eliminate high-frequency interference in the input signal. Subsequently, the differential amplifier of the analog-to-digital conversion front end differentially amplifies the electroencephalogram signals, and converts the analog signals into digital signals through two 24-bit synchronous digital-to-analog converters. In addition, the module introduces a right leg drive circuit, which reverses the common mode signal of the input signal and then feeds it back to the human body to eliminate common mode interference.

[0101] 1.2) Electrooculogram acquisition: Since the silver chloride dry electrodes in the head-mounted device are arranged on the forehead, the acquired electroencephalogram signals will be coupled with electrooculogram signals, so the module uses a decoupling algorithm in the background program to decouple the electrooculogram signals from the acquired electroencephalogram signals.

[0102] The decoupling algorithm is based on long-time differential amplitude envelope and wavelet transform. The long-time differential of the electroencephalogram signal is calculated to measure the degree of electrooculogram fluctuation, then the amplitude envelope of the signal is obtained by low-pass filtering, and the double-threshold method is used to accurately detect the start and end points of the electrooculogram. Subsequently, the electroencephalogram signal is decomposed using sym5 wavelet, and the Birgé-Massart strategy is introduced to adaptively determine the threshold value of the wavelet coefficients. The estimated electrooculogram signal is accurately estimated by wavelet reconstruction, and the estimated electrooculogram signal is decoupled from the original electroencephalogram signal to separate the electrooculogram signal from the electroencephalogram signal.

[0103] 2) Electrical stimulation module: The electrical stimulation module is composed of a power supply part, three independent power supplies, a boost circuit, an electrical stimulation main circuit, a control circuit and a communication circuit. The power supply and control instructions of this module are provided by the USB interface, according to the instructions (see the electrical stimulation module manual for detailed instruction set), the control of the three independent power supplies of the output module can be realized, and the current of three kinds of waveforms of direct current, square wave and triangular wave can be output according to the needs.

[0104] 3) Data conversion module: The data communication between the electroencephalogram acquisition module and the electrical stimulation module is bridged to a USB interface to interact with the host computer.

[0105] 3.1.3 Headset: The headset is composed of blood oxygen module, electroencephalogram electrode, electrical stimulation electrode, shell, etc.

[0106] 1) Blood oxygen module: The module uses a multi-spectral physiological data measurement sensor to collect blood oxygen saturation. The sensor integrates multi-wavelength LED light source and high-sensitivity photodetector. The LED light source emits specific wavelength red and infrared light to penetrate the skin and tissue, and irradiate the hemoglobin in the blood. Because the absorption rates of oxygenated and deoxygenated hemoglobin are different for these light waves, the photodetector in the module can detect the difference in light intensity after absorption by the blood. These light intensity signals are converted into electrical signals and processed to calculate the blood oxygen saturation by the ratio method.

[0107] 2) Electroencephalogram electrode: The electrode for collecting FP1, FP2 brain region electroencephalogram signal uses silver chloride electrode (shared with electrical stimulation electrode) and electrode wire wrapped shielding wire to reduce signal loss and improve system electroencephalogram collection accuracy.

[0108] 3) Electrical stimulation electrode: The electrode for stimulating FP1, FP2, Fz and F3 brain regions (FP1, FP2 share two electrodes with electroencephalogram collection) silver chloride electrode (FP1, FP2 share electrode with electrical stimulation), auricle vagus nerve stimulation electrode is ear clip dry electrode;

[0109] 4) Shell: The forehead part uses soft silicone to fix the silver chloride electrode and blood oxygen module, and the back of the brain uses a stretchable adjustable device to adapt to the use of different people;

[0110] 3.2 Principle prototype usage process: The principle prototype usage process is described as follows:

[0111] Connect the device with the host computer; 1) Connect the device to the computer; 2) Wear the prototype headset, adjust the tightness to make the electroencephalogram collection and electrical stimulation electrode contact well with the corresponding brain region of the subject; 3) Start the software, connect the electroencephalogram collection and electrical stimulation serial ports; 4) Set the fatigue threshold, electrical stimulation parameters, and establish the subject document; 5) Start the electroencephalogram collection module, real-time display electroencephalogram, electrooculogram and blood oxygen saturation; 6) The built-in fatigue algorithm is coupled with physiological index calculation and real-time display of fatigue state; 7) When the fatigue reaches the set threshold, the electrical stimulation is automatically started, and after the electrical stimulation is finished, the biological signal detection module is automatically started, the subject's fatigue is calculated according to the real-time data, and a new round of electrical stimulation is started when the fatigue reaches the threshold.

[0112] 3.3 Data transmission communication protocol and data description: 3.3.1 Communication protocol;

[0113] 3.3.1.1 Confirm the port number: the acquisition hardware module (hereinafter referred to as "device") adopts a serial communication protocol. As shown in the following figure, connect the device to the computer through the USB line, open the "Device Manager", find the serial number corresponding to the device in the "Port (COM and LPT)" item (the master control module uses CP2102 as a USB-to-serial chip, which will be reflected in the device name). If you can't determine which one, it is recommended to unplug the USB line and see which port disappears. The corresponding one is the one.

[0114] 3.3.1.2 The serial port configuration details are shown in Table 1:

[0115] Table 1

[0116] Serial Port Properties Value Baud Rate 961200 Data Bits 8 Parity None Stop Bits 1 Hardware Flow Control None

[0117] 3.3.1.3 The device instruction table is shown in Table 2:

[0118] Table 2

[0119] Command Function EEG SPOON Normal acquisition mode, start acquisition OFF Stop acquisition in any mode self test ON Enter self-test mode, device sends self-test signal

[0120] Note: The instruction does not have line feed and carriage return.

[0121] 3.3.2 Device data format:

[0122] 3.3.2.1 Device data transmission test: It is recommended to download "Serial Debug Assistant" in Microsoft Store to test the data transmission of the device. Set the relevant parameters according to the left red box in the following figure, then send the "EEG_SPO_ON" instruction, and the data sent by the device can be observed on the right side. The right red box in the figure is a data frame, as shown in Figure 10

[0123] 3.3.2.2 Data frame format and data conversion:

[0124] The data sent by the device is composed of several data frames. A data frame is shown in the above Figure 10 , including 11 bytes, indicating frame header, function code, data length, data bit 1 to data bit 6, and frame tail in turn. Each data frame transmits 6 data bits (6 bytes), and the transmission rate is about 250 data frames per second. The specific format is shown in Table 3 (all in hexadecimal):

[0125] Table 3

[0126]

[0127] ​The function code 01 represents two-channel brain electrical data, and the data length is fixed as 6 bytes, i.e. 6 bytes represented by data bit 1 to data bit 6. Among them, data bit 1 to data bit 3 represent FP1 channel data, and data bit 4 to data bit 6 represent FP2 channel data.

[0128] Taking the data frame in the above table as an example, the decimal corresponding to data bit 1, data bit 2 and data bit 3 is A1, B1 and C1 in turn. First, calculate:

[0129] T1 = 65536 * A1 + 256 * B1 + C1

[0130] If 0≤A1≤127, then:

[0131] V1 = 0.0401 * T1

[0132] On the contrary, if 127<A1≤255, then:

[0133] V1 = 0.0401 * (T1-16777215)

[0134] The calculated V1 is the voltage value of the brain electrical signal corresponding to the FP1 channel.

[0135] The calculation method of the brain electrical signal voltage value corresponding to the FP2 channel is consistent with that of the FP1 channel.

[0136] Taking the data frame in the above table as an example, A1 = 7, B1 = 213, C1 = 223, 0≤A1≤127, then V1 = 0.0401 * (65536 * 7 + 256 * 213 + 223) = 20591.4703 (unit: μV).

[0137] Similarly, A2 = 3, B2 = 112, C2 = 81, 0≤A2≤127, V2 = 0.0401 * (65536 * 3 + 256 * 112 + 81) = 9036.9761 (unit: μV).

[0138] The function code 02 represents blood oxygen data, and the decimal data corresponding to data bit 6 is taken to obtain the blood oxygen saturation at this time, as shown in Table 4, data bit 6 is 0x62 = 98, so the blood oxygen saturation at this time is 98.

[0139] Table 4

[0140]

[0141] The specific connection state is shown in Table 5: C280 is converted into binary as 1100001010000000.

[0142] Table 5

[0143]

[0144] Note that the data bits of

N, P1, P2

[0145] The function code of the self-test signal is also 01. After sending the "self_test_ON" instruction, the device will send the self-test data.

[0146] According to the data conversion method introduced above, collect and convert no less than 2500 data frames, analyze the voltage value data of 2 channels and draw a graph, which should be a square wave with a frequency of 0.9765 Hz (±4%), an amplitude of 3360 μV (±3%), and a duty cycle of 50% (±3%), as shown in Figure 11 , which is the self-test voltage value waveform graph of the FP1 channel. The horizontal coordinate is the data frame index, and the vertical coordinate is the voltage value. The data frame index of point A is 111, and the voltage value is 1641.27 μV. The data frame index of point B is 751, and the voltage value is -1724.01 μV. The same applies to points C-E.

[0147] The calculation formula of the amplitude is (maximum value of the waveform - minimum value of the waveform), so the measured amplitude is 1642.55 - (-1724.01) = 3366.56 μV, and the error from the nominal value is (3366.56 - 3360) / 3360 * 100% = 0.195%, which is much smaller than ±3%;

[0148] The calculation method of the frequency is to take any two points that are exactly located before the falling edge of the waveform, calculate the difference I d between the data frame indexes of the two points, and the frequency is 250 * (the number of falling edges between the two points) / I d ; For example, points A, C, and E in the figure all meet the "last point before the falling edge of the waveform", and the frequency is calculated by taking points A and E, then I d = 2049, and the frequency is 250 * 8 / 2049 = 0.9761 Hz, which deviates from the nominal value of 0.9766 Hz by (0.9766 - 0.9761) / 0.9766 * 100% = 0.05%, which is much lower than ±4%;

[0149] The calculation method of the duty cycle: take a square wave period (B-C-D three points range is a square wave period), the percentage of the high level section (B-C section) in the whole period (B-D section), for example, B-C section has 129 data frames, B-D section has 256 data frames, so the duty cycle is 129 / 256*100% = 50.39%, the deviation from the nominal value 50% is (50.39-50) / 50*100% = 0.78%, far lower than ±3%.

[0150] So far it can be proved that the self-check signal of FP1 channel is correct, and the verification method of FP2 channel is the same.

[0151] 3.3.3 Data background receiving and processing: The receiving of the above data frame, voltage conversion, and fatigue value and eye data calculation are completed by the background program. The program can accept electroencephalogram data and complete corresponding voltage conversion, eye data extraction, and fatigue value calculation, etc. After completing the above work, all data are sent to the foreground program. Its functions include: handshake, exit program, get fatigue value and eye data.

[0152] 3.4 Computer software usage instructions:

[0153] 3.4.1 Introduction of computer software: The software is divided into two modules: 1 Backend_pilao.exe, the background fatigue calculation processing module, 2 Selffeedback.exe, the foreground data acquisition display and processing module. The background module is automatically called by the foreground module and does not need to be manually run. After being called, it resides in the background, calculates and processes the electroencephalogram data sent by the foreground module, and sends the filtered data and fatigue and eye movement data back to the foreground module. Its configuration file is config.ini file. By adjusting the parameters, the background algorithm can be adjusted to calculate the foreground data more accurately.

[0154] 3.4.2 Software settings: Click the "User Settings" button in the main page to get the user management dialog box. After entering the username and serial number in the right side of the dialog box, click Add to add the user to the user list; click the user in the user list, and the user information is displayed in the right information, which can be deleted and modified. After the user management is completed, click OK to close the dialog box. The currently selected user in the list is the current test user. Click "Settings" button in the settings, a dialog box including EEG serial number, electrical stimulation serial number, EEG display buffer size is displayed. The list in the right side of the EEG serial and electrical stimulation serial shows the existing serial list on the computer. The EEG serial contains the Silicon string, and the electrical stimulation serial contains the CH340 string. The EEG display buffer size is the maximum buffer of the image during real-time acquisition, that is, the data can be displayed up to how long ago from the current time.

[0155] 3.4.3 Real-time EEG, EOG, and SpO2 acquisition: In the home page of the front-end program, click "Data acquisition feedback" to display the real-time data of EEG FP1 and FP2, EOG, and SpO2. Among them, EEG FP1 and FP2 and SpO2 are obtained directly from the helmet device, and EOG data are obtained from the back-end computing program.

[0156] After clicking Start, the real-time data starts to display. In the real-time graphs of EEG FP1, FP2, and EOG, click the left mouse button and drag to perform image dragging operation. Scroll up and down with the mouse wheel to zoom the y-axis range. Scroll left and right to zoom the x-axis, i.e., the time range. For mice without left and right scrolling, hold down the Ctrl key on the keyboard and scroll up and down with the mouse wheel to achieve the same effect as scrolling left and right with the mouse wheel, i.e., zooming the x-axis. After zooming or dragging the x-axis, the automatic following of the image movement will stop. Double-click to restore the x-axis automatic following function. Click the Stop button to stop the acquisition and update the image.

[0157] 3.4.4 Real-time fatigue monitoring: In the real-time acquisition interface, there is a real-time fatigue display, which is obtained by the back-end computing module. After the front-end program acquires real-time EEG FP1 and FP2 data, it sends the data to the back-end through the interface of the back-end program. The back-end calculates and sends the calculation results back to the front-end, which includes fatigue data.

[0158] 3.4.5 Self-feedback control: To use the self-feedback function of the software, first define the parameters of the electrical stimulation. In the home page of the program, click the "Electrical stimulation" button. The dialog box displays the stimulation mode, channel 1, channel 2, and channel 3. Under each channel, there are displays for top flow, time, frequency, and pulse width. After setting the parameters of the three channels of electrical stimulation, click the "Start" button to test the output effect of the electrical stimulation parameters. If the parameters are not suitable, click the "Stop" button to stop the electrical stimulation and re-set the electrical stimulation parameters. Refer to the Electrical Stimulation Design section for electrical stimulation parameters. After setting is complete, click OK to save. Then go to the real-time data acquisition interface to adjust the self-feedback parameters. Set the fatigue threshold. When the fatigue exceeds the given threshold, the program automatically turns on the electrical stimulation for self-feedback. After the electrical stimulation is completed, the program automatically restarts the acquisition and detection operations.

[0159] 4. Usage process of the prototype:

[0160] 4.1 Preparation stage: due to the instantaneous current of the device is about 600mA, the USB interface of ordinary computer can not meet the requirements; please connect the device data line to the large current USB interface of the computer, if the computer does not have a large current interface, please connect the USB data line to the prepared self-powered USB-HUB (USB-HUB power connection 5V1A above adapter), and then connect the HUB to the computer USB interface.

[0161] 4.2 Prototype wearing: physiological saline is used to wipe off grease from the forehead, head and left and right ears; the head-mounted device is worn at the designated brain area position, and the reference electrode is attached to the back of the left and right ears using conductive gel; the two electric stimulation ear clips are clamped at the specified position of the left ear.

[0162] 4.3 Data acquisition: open the front-end program Selffeedback.exe, set the EEG serial port and electric stimulation serial port, current user, and electric stimulation parameters according to the above process, open real-time data acquisition, set electric stimulation feedback parameters, click start to perform real-time data acquisition, background data processing, and automatic fatigue self-feedback processing.

[0163] 5 Data management: during the running of the front-end program, the EEG FP1, FP2, and blood oxygen data obtained during running, the EOG and fatigue data calculated by the background program, and the self-feedback action data during program running are saved, and the data are saved in the Data directory established under the directory where the current program is running.

[0164] It should be noted that the flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks can also occur in different order from that indicated in the drawings. For example, two blocks indicated in succession can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0165] In general, the various example embodiments of the present disclosure can be implemented in hardware or special-purpose circuits, software, firmware, logic, or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software which can be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein can be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controler or other computing devices, or some combination thereof.

[0166] The specific working process of the system, device and unit described above can be clearly understood by those skilled in the art, and reference can be made to the corresponding process in the foregoing method embodiments for description and brevity, which will not be repeated here.

[0167] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0168] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0169] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or software functional unit.

[0170] The example embodiments of the present disclosure described in detail above are only illustrative, not restrictive. Those skilled in the art should understand that various modifications and combinations of these embodiments or their features can be made without departing from the principles and spirits of the present disclosure, and such modifications should fall within the scope of the present disclosure.

Claims

1. A computer device for real-time fatigue monitoring and negative feedback control, characterized in that, The device includes: a memory and a processor; the memory is used to store a computer program; the processor executes the computer program to perform the steps of the following method:

101. Acquire the subject's electroencephalogram (EEG) and electrooculogram (EOG) signals and blood oxygen saturation data; the EEG and EOG signals include signals from FP1 and FP2 sites; separate the EEG and EOG signals from the EEG and EOG signals; 102. Calculate fatigue level based on the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data; 103. When the fatigue level reaches the set threshold, transcranial electrical stimulation is applied to the subject by triggering electrodes located in the prefrontal cortex. The method for separating electroencephalogram (EEG) and electrooculogram (EOG) signals from EEG signals includes: calculating the long-term time difference measure of the EOG fluctuation amplitude; obtaining the amplitude envelope of the EEG and EOG signals using low-pass filtering, and detecting the start and end points of the EOG signals using a dual-threshold method; decomposing the EEG and EOG signals, introducing the Birgé-Massart strategy to adaptively determine the threshold of wavelet coefficients; accurately estimating the EOG signals through wavelet reconstruction, and decoupling the estimated EOG signals from the original EEG and EOG signals, thus separating the EEG and EOG signals. The method for calculating fatigue level includes: inputting the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data into a real-time fatigue state assessment model to calculate fatigue level; the real-time fatigue state assessment model is constructed based on a few-channel fatigue decoding algorithm using Transformer and attention mechanisms. The method for constructing the real-time fatigue state assessment model includes: obtaining a training set and performing a PVT paradigm on the dataset; inputting the dataset into a CNN structure to extract local features of EEG signals, using Transformer to extract long-range correlations of EEG signals, and simultaneously focusing on both local and global features of the data; introducing channel attention and spatial attention mechanisms to measure the importance weights of different channels and spatial locations of features for the decoding task; employing a feature fusion strategy to extract feature maps containing multi-layer information; and inputting the feature maps into a classifier for continuous optimization to obtain the constructed real-time fatigue state assessment model.

2. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The prefrontal cortex includes any two or more of the following stimulation sites: FP1, FP2, F3, and Fz.

3. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The stimulation sites for transcranial electrical stimulation also include the vagus nerve in the left and right auricles; relieving subject fatigue and restoring cognitive function.

4. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The blood oxygen saturation data is acquired through a blood oxygen saturation sensor.

5. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The transcranial electrical stimulation protocol includes any one or more of the following: stimulation site, stimulation intensity, stimulation pulse waveform, stimulation frequency, and stimulation time.

6. The computer device for real-time fatigue monitoring and negative feedback control according to claim 5, characterized in that, The frequency calculation method includes: taking any two points exactly before the falling edge of the waveform, calculating the difference between the data frame indices of these two points, and the frequency is... The The difference between the data frame indices of the two points.

7. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The method also includes determining the predictive results of whether the subject is in a fatigued state, a transitional state, or a conscious state.

8. The computer device for real-time fatigue monitoring and negative feedback control according to claim 1, characterized in that, The electroencephalogram (EEG) and electrooculogram (EOG) signals are preprocessed signals. The preprocessing methods include: eliminating high-frequency interference, differential amplification, and conversion into digital signals.

9. A computer-readable storage medium for real-time fatigue monitoring and negative feedback control, characterized in that, It stores a computer program, which, when executed by a processor, implements the steps of the following method:

101. Acquire the subject's electroencephalogram (EEG) and electrooculogram (EOG) signals and blood oxygen saturation data; the EEG and EOG signals include signals from FP1 and FP2 sites; separate the EEG and EOG signals from the EEG and EOG signals; 102. Calculate fatigue level based on the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data; 103. When the fatigue level reaches the set threshold, transcranial electrical stimulation is applied to the subject by triggering electrodes located in the prefrontal cortex. The method for separating electroencephalogram (EEG) and electrooculogram (EOG) signals from EEG signals includes: calculating the long-term time difference measure of the EOG fluctuation amplitude; obtaining the amplitude envelope of the EEG and EOG signals using low-pass filtering, and detecting the start and end points of the EOG signals using a dual-threshold method; decomposing the EEG and EOG signals, introducing the Birgé-Massart strategy to adaptively determine the threshold of wavelet coefficients; accurately estimating the EOG signals through wavelet reconstruction, and decoupling the estimated EOG signals from the original EEG and EOG signals, thus separating the EEG and EOG signals. The method for calculating fatigue level includes: inputting the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data into a real-time fatigue state assessment model to calculate fatigue level; the real-time fatigue state assessment model is constructed based on a few-channel fatigue decoding algorithm using Transformer and attention mechanisms. The method for constructing the real-time fatigue state assessment model includes: obtaining a training set and performing a PVT paradigm on the dataset; inputting the dataset into a CNN structure to extract local features of EEG signals, using Transformer to extract long-range correlations of EEG signals, and simultaneously focusing on both local and global features of the data; introducing channel attention and spatial attention mechanisms to measure the importance weights of different channels and spatial locations of features for the decoding task; employing a feature fusion strategy to extract feature maps containing multi-layer information; and inputting the feature maps into a classifier for continuous optimization to obtain the constructed real-time fatigue state assessment model.

10. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The prefrontal cortex includes any two or more of the following stimulation sites: FP1, FP2, F3, and Fz.

11. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The stimulation sites for transcranial electrical stimulation also include the vagus nerve in the left and right auricles; relieving subject fatigue and restoring cognitive function.

12. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The blood oxygen saturation data is acquired through a blood oxygen saturation sensor.

13. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The transcranial electrical stimulation protocol includes any one or more of the following: stimulation site, stimulation intensity, stimulation pulse waveform, stimulation frequency, and stimulation time.

14. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 13, characterized in that, The frequency calculation method includes: taking any two points exactly before the falling edge of the waveform, calculating the difference between the data frame indices of these two points, and the frequency is... The The difference between the data frame indices of the two points.

15. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The method also includes determining the predictive results of whether the subject is in a fatigued state, a transitional state, or a conscious state.

16. The computer-readable storage medium for real-time fatigue monitoring and negative feedback control according to claim 9, characterized in that, The electroencephalogram (EEG) and electrooculogram (EOG) signals are preprocessed signals. The preprocessing methods include: eliminating high-frequency interference, differential amplification, and conversion into digital signals.

17. A computer program product for real-time fatigue monitoring and negative feedback control, comprising a computer program, characterized in that, The steps of the method implemented when the computer program is executed by the processor are as follows:

101. Acquire the subject's electroencephalogram (EEG) and electrooculogram (EOG) signals and blood oxygen saturation data; the EEG and EOG signals include signals from FP1 and FP2 sites; separate the EEG and EOG signals from the EEG and EOG signals; 102. Calculate fatigue level based on the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data; 103. When the fatigue level reaches the set threshold, transcranial electrical stimulation is applied to the subject by triggering electrodes located in the prefrontal cortex. The method for separating electroencephalogram (EEG) and electrooculogram (EOG) signals from EEG signals includes: calculating the long-term time difference measure of the EOG fluctuation amplitude; obtaining the amplitude envelope of the EEG and EOG signals using low-pass filtering, and detecting the start and end points of the EOG signals using a dual-threshold method; decomposing the EEG and EOG signals, introducing the Birgé-Massart strategy to adaptively determine the threshold of wavelet coefficients; accurately estimating the EOG signals through wavelet reconstruction, and decoupling the estimated EOG signals from the original EEG and EOG signals, thus separating the EEG and EOG signals. The method for calculating fatigue level includes: inputting the electroencephalogram (EEG), electrooculogram (EOG), and blood oxygen saturation data into a real-time fatigue state assessment model to calculate fatigue level; the real-time fatigue state assessment model is constructed based on a few-channel fatigue decoding algorithm using Transformer and attention mechanisms. The method for constructing the real-time fatigue state assessment model includes: obtaining a training set and performing a PVT paradigm on the dataset; inputting the dataset into a CNN structure to extract local features of EEG signals, using Transformer to extract long-range correlations of EEG signals, and simultaneously focusing on both local and global features of the data; introducing channel attention and spatial attention mechanisms to measure the importance weights of different channels and spatial locations of features for the decoding task; employing a feature fusion strategy to extract feature maps containing multi-layer information; and inputting the feature maps into a classifier for continuous optimization to obtain the constructed real-time fatigue state assessment model.

18. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The prefrontal cortex includes any two or more of the following stimulation sites: FP1, FP2, F3, and Fz.

19. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The stimulation sites for transcranial electrical stimulation also include the vagus nerve in the left and right auricles; relieving subject fatigue and restoring cognitive function.

20. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The blood oxygen saturation data is acquired through a blood oxygen saturation sensor.

21. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The transcranial electrical stimulation protocol includes any one or more of the following: stimulation site, stimulation intensity, stimulation pulse waveform, stimulation frequency, and stimulation time.

22. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 21, characterized in that, The frequency calculation method includes: taking any two points exactly before the falling edge of the waveform, calculating the difference between the data frame indices of these two points, and the frequency is... The The difference between the data frame indices of the two points.

23. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The method also includes determining the predictive results of whether the subject is in a fatigued state, a transitional state, or a conscious state.

24. The computer program product for real-time fatigue monitoring and negative feedback control according to claim 17, characterized in that, The electroencephalogram (EEG) and electrooculogram (EOG) signals are preprocessed signals. The preprocessing methods include: eliminating high-frequency interference, differential amplification, and conversion into digital signals.

Images