An electroencephalogram sign detection and evaluation method, system, electronic device and storage medium

Abstract

The application provides an electroencephalogram sign detection and evaluation method, system, electronic equipment and storage medium. The system comprises an ear periphery flexible electromyography sensor, an eye periphery flexible electromyography sensor and a wearable in-ear sensor system. The cochlea sensor and the ear canal flexible electromyography sensor of the wearable in-ear sensor system are respectively used for monitoring electroencephalogram information and collecting ear canal electromyography signals. The ear periphery flexible electromyography sensor is used for collecting ear periphery electromyography signals. The eye periphery flexible electromyography sensor is used for collecting eye periphery electromyography signals. The wearable in-ear electrophysiological system is used for fatigue detection and evaluation according to the electroencephalogram information, the ear canal electromyography signals, the ear periphery electromyography signals and the eye periphery electromyography signals. The application uses different muscle group sEMG array image information and electroencephalogram information to construct a human body drowsiness evaluation model, uses the prior nature of electromyography information, adopts a classifier algorithm to realize fatigue discrimination evaluation and prediction, and has an important role in monitoring the drowsiness and health state of a driver.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wearable fatigue detection, and particularly relates to an electroencephalogram sign detection and evaluation method and system, an electronic device and a storage medium. BACKGROUND

[0002] Driving fatigue refers to the phenomenon that the physiological and psychological functions of a driver are out of balance and the driving skills are reduced after long-time continuous driving. The driver is prone to fatigue due to poor sleep quality or long-time driving. Driving fatigue affects the driver's attention, feeling, perception, thinking, judgment, will, decision and movement.

[0003] Neural wearable devices play an important role in monitoring the drowsiness and health status of drivers. At present, drowsiness monitoring solutions based on camera eye tracking, steering wheel trajectory sensors or electro-physiological recording devices have been widely applied in vehicle scenes, but eye tracking is prone to be blocked by sunglasses and other obstacles, and most electro-physiological recording devices are inconvenient to use due to large electrodes and volume, which limits their daily application. SUMMARY

[0004] In order to achieve the above-mentioned purposes and other advantages according to the present application, the first object of the present application is to provide an electroencephalogram sign detection and evaluation method, comprising the following steps:

[0005] processing the ear canal electromyography signal, the periauricular electromyography signal, the periorbital electromyography signal and the electroencephalogram information to improve the signal quality;

[0006] extracting the time domain features and frequency domain features of the ear canal electromyography signal, the periauricular electromyography signal, the periorbital electromyography signal and the electroencephalogram information;

[0007] performing feature-level fusion on the features of the ear canal electromyography signal, the periauricular electromyography signal, the periorbital electromyography signal and the electroencephalogram information to form a high-dimensional feature vector;

[0008] analyzing the high-dimensional feature vector by using multiple basic classifiers;

[0009] taking the prediction results of the multiple basic classifiers as new input features to train a meta-classifier, and performing final discrimination by comprehensively integrating the information of all the classifiers;

[0010] iteratively training multiple weak classifiers into strong classifiers by using a boosting method to improve the accuracy of the overall model.

[0011] Further, the step of processing the ear canal electromyography signal, the periauricular electromyography signal, the periorbital electromyography signal and the electroencephalogram information comprises:

[0012] The ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information are subjected to band-pass filtering processing.

[0013] The ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information are subjected to multi-scale decomposition by wavelet transform, and the signal is reconstructed after noise is removed.

[0014] The reconstructed signal is subjected to high-pass filtering to remove baseline drift.

[0015] The baseline drift is corrected by using low-order polynomial fitting, and the signal quality is further improved.

[0016] All the collected signals are subjected to normalization processing to eliminate the differences between individuals.

[0017] Further, the extraction of the time domain features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information comprises:

[0018] The mean, standard deviation, RMS value and peak-to-peak value of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information are calculated.

[0019] Further, the extraction of the frequency domain features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information comprises:

[0020] The ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information are subjected to fast Fourier transform, the power spectral density of different frequency components is analyzed, the average frequency of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information is calculated, the change of frequency components under fatigue state is analyzed, and the multi-scale features of the signal are analyzed by using continuous wavelet transform.

[0021] Further, the method further comprises the steps of:

[0022] The high-dimensional feature vector is subjected to dimension reduction by using a dimension reduction method to eliminate redundant features.

[0023] Further, a support vector machine, a random forest and a limit gradient boosting algorithm are used as basic classifiers.

[0024] A second object of the present application is to provide an electronic device comprising a memory having program code stored thereon, and a processor connected to the memory, and when the program code is executed by the processor, the above-mentioned method is realized.

[0025] A third object of the present application is to provide a computer readable storage medium having program instructions stored thereon, and the program instructions are executed to realize the above-mentioned method.

[0026] A fourth object of the present application is to provide an electroencephalogram sign detection and evaluation system for implementing the above method, comprising a per-auricular flexible myoelectric sensor, a per-ocular flexible myoelectric sensor, and a wearable in-ear sensor system; wherein,

[0027] The wearable in-ear sensor system comprises a cochlea sensor and an ear canal flexible myoelectric sensor.

[0028] The cochlea sensor is used to monitor electroencephalogram information.

[0029] The ear canal flexible myoelectric sensor is used to collect ear canal myoelectric signals.

[0030] The per-auricular flexible myoelectric sensor is used to collect per-auricular myoelectric signals.

[0031] The per-ocular flexible myoelectric sensor is used to collect per-ocular myoelectric signals.

[0032] The wearable in-ear electrophysiological system is used to perform fatigue detection and evaluation according to the electroencephalogram information, the ear canal myoelectric signals, the per-auricular myoelectric signals, and the per-ocular myoelectric signals.

[0033] Further, the cochlea sensor adopts an in-ear integrated electrochemical and electrophysiological sensor array, which is used to record brain activity and sweat secretion information.

[0034] Further, the cochlea sensor is attached to an earplug to form an in-ear assembled integrated sensor.

[0035] Further, the ear canal flexible myoelectric sensor comprises an EEG detection layer and an electrothermal driving layer, the electrothermal driving layer is used to apply Joule heating generated by an external electric field to trigger a shape memory effect and cause expansion into a predetermined spiral shape with a larger radius, and the EEG detection layer is used to detect ear canal myoelectric signals.

[0036] Compared with the prior art, the present application has the following beneficial effects:

[0037] The present application adopts sEMG array on the ear side, wearable in-ear sensor system, and per-ocular sEMG array, etc. multi-mode information for drowsiness monitoring. The wireless dry electrode earplug integrates dry electrodes, wireless electronic devices, and offline classification algorithms. The present application adopts support vector machine (SVM) classification algorithm, and finds that the wireless dry electrode earplug can be comparable to existing wet electrode collection systems (such as in-ear EEG and scalp EEG systems) in terms of drowsiness classification accuracy. The application of the new wireless dry electrode earplug will lay the foundation for future concealed, wireless, and long-term brain monitoring.

[0038] The above description is only a summary of the technical solutions of the present application. In order to make the technical means of the present application more clearly understood and implemented according to the content of the description, the following will be described in detail in the preferred embodiments of the present application with reference to the accompanying drawings. The specific embodiments of the present application are described in detail by the following embodiments and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings, which are included to provide a further understanding of the present application, constitute a part of this application and illustrate the illustrative embodiments of the present application and its description, which serve to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0040] Figure 1 Monitoring schematic diagram of the electroencephalogram sign detection and evaluation system of embodiment 1;

[0041] Figure 2 Schematic diagram of the earplug type cochlea sensor of embodiment 1;

[0042] Figure 3 Schematic diagram of the ear canal flexible myoelectric sensor of embodiment 1;

[0043] Figure 4 Flowchart of the electroencephalogram sign detection and evaluation method of embodiment 2;

[0044] Figure 5 Flowchart of the signal processing of embodiment 2;

[0045] Figure 6 Schematic diagram of the electronic device of embodiment 3;

[0046] Figure 7 Schematic diagram of the storage medium of embodiment 4. DETAILED DESCRIPTION

[0047] The present application will be further described below in combination with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. It should be noted that the following described embodiments or technical features can be combined in any manner to form new embodiments without conflict.

[0048] 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.

[0049] The figure numbers in the present application are only used to distinguish each step in the scheme, and are not used to limit the execution order of each step. The specific execution order is subject to the description in the specification.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0051] Embodiment 1

[0052] An electroencephalographic sign detection and evaluation system, as shown in Figure 1 includes a per-aural flexible electromyography sensor, a per-ocular flexible electromyography sensor, a wearable in-ear sensor system; wherein,

[0053] The wearable in-ear sensor system contains a cochlea sensor, an ear canal flexible electromyography sensor;

[0054] The cochlea sensor is used to monitor electroencephalographic information;

[0055] The ear canal flexible electromyography sensor is used to collect ear canal electromyography signals;

[0056] The per-aural flexible electromyography sensor is used to collect per-aural electromyography signals;

[0057] The per-ocular flexible electromyography sensor is used to collect per-ocular electromyography signals;

[0058] The wearable in-ear electrophysiological system is used to detect and evaluate fatigue according to the electroencephalographic information, the ear canal electromyography signals, the per-aural electromyography signals, and the per-ocular electromyography signals.

[0059] Since the ear canal is close to the central nervous system, the wearable in-ear sensor system can be used to inconspicuously monitor the brain state. The wearable in-ear sensor system designs an in-ear integrated electrochemical and electrophysiological sensor array by utilizing the exocrine sweat glands of the ear, and the cochlea sensor is placed on a flexible substrate around a user's general earphone to simultaneously monitor lactic acid concentration and brain state through electroencephalogram (EEG), electrooculogram (EOG), and skin electricity activity (EDA), as shown in Figure 2 .

[0060] The design of the in-ear integrated sensor includes electrophysiological and electrochemical sensors for recording brain activity and sweat secretion, in-ear integrated electrophysiological (ePhys) and electrochemical (eChem) sensing electrodes. From bottom to top, the sensor is made of adhesive, TPU, SEBS, PB, stretchable silver, PVA hydrogel, and flexible printed circuit board (fPCB). The flexible sensor is attached to the earplug after stretching deformation, forming an in-ear assembled integrated sensor, i.e., a cochlea sensor.

[0061] The ear canal flexible myoelectric sensor can be driven by electro-thermal to adaptively expand and spiral along the ear canal to ensure close contact. The constituent parts include an EEG detection layer (EEGDL) and an electro-thermal driving layer (EAL). Due to the different shapes and sizes of the auditory canal of each person, and the tortuous internal structure, the ear canal flexible myoelectric sensor is introduced into the ear canal in a compressed temporary shape (smaller spiral form). Then, the shape memory effect is triggered by applying Joule heating generated by an external electric field, and expanded into a predetermined spiral shape with a larger radius, the EEG detection layer is used to detect the ear canal myoelectric signal. In order to form a close contact with the inner wall of the ear canal, the radius of the predetermined spiral is designed to be larger than the radius of the ear canal. During the shape recovery process, it is hindered by the ear canal wall, thereby conforming to the shape of the auditory canal, effectively solving the difference and complexity of the user to the ear canal, such as Figure 3 as shown.

[0062] In view of the low fatigue discrimination recognition rate of a single classifier, the present application provides a multi-weak classifier signal information fusion classification method based on a parallel multi-source information fusion algorithm. Based on the structure of the parallel multi-source information fusion algorithm, a multi-weak classifier signal information fusion classification system is designed according to the number of weak classifiers and different input data, and a multi-mode information fusion method is used to fuse the results of the weak classifiers. For a detailed description of the EEG sign detection and evaluation method corresponding to the EEG sign detection and evaluation system, reference can be made to the corresponding description in the following method embodiment, which will not be repeated here.

[0063] The present embodiment uses ear-side sEMG array, wearable in-ear sensor system and eye-peripheral sEMG array, etc. multi-mode information for drowsiness monitoring. The wireless dry electrode earplug integrates dry electrodes, wireless electronic devices and offline classification algorithms. The present embodiment uses support vector machine (SVM) classification algorithm, and finds that the wireless dry electrode earplug can be comparable to existing wet electrode collection systems (such as in-ear EEG and scalp EEG systems) in terms of drowsiness classification accuracy. The application of the new wireless dry electrode earplug will lay the foundation for future concealed, wireless and long-term brain monitoring.

[0064] Embodiment 2

[0065] The EEG sign detection and evaluation method corresponding to the EEG sign detection and evaluation system provided by Embodiment 1, for a detailed description of the system, reference can be made to the corresponding description in the above system embodiment, which will not be repeated here. As Figure 4 shown, the method comprises the following steps:

[0066] S1, processing ear canal myoelectric signals, ear-peripheral myoelectric signals, eye-peripheral myoelectric signals and brain electrical information to improve signal quality;

[0067] As Figure 5As shown, the processing steps of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information include:

[0068] S11, band-pass filtering the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information to filter out low and high frequency noise, etc.

[0069] S12, using wavelet transform to perform multi-scale decomposition on the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information, and reconstructing the signal after removing noise; for example, using Daubechies wavelet transform to perform multi-scale decomposition on the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information, and reconstructing the signal after removing noise.

[0070] S13, high-pass filtering the reconstructed signal to remove baseline drift and ensure signal stability.

[0071] S14, using low-order polynomial fitting to correct baseline drift and further improve signal quality.

[0072] S15, normalizing all collected signals to eliminate individual differences. For example, Z-score normalization is performed on all collected signals to eliminate individual differences and ensure consistency in subsequent analysis.

[0073] S2, extracting time domain features and frequency domain features of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information.

[0074] In some embodiments, the extraction of the time domain features of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information includes:

[0075] Calculating the mean, standard deviation, RMS value, peak-to-peak value, and other parameters of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information.

[0076] In some embodiments, the extraction of the frequency domain features of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information includes:

[0077] Performing fast Fourier transform on the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information, analyzing the power spectral density (PSD) of different frequency components, calculating the average frequency of the ear canal muscle electrical signal, the periauricular muscle electrical signal, the periorbital muscle electrical signal, and the brain electrical information, analyzing the changes in frequency components under fatigue state, and then using continuous wavelet transform (CWT) to analyze the multi-scale features of the signal.

[0078] S3, the ear muscle electrical signal, the ear muscle electrical signal, the eye muscle electrical signal, the brain electrical information is fused in feature level, and high-dimensional feature vector is formed;

[0079] In some embodiments, further comprising the steps of:

[0080] The high-dimensional feature vector is reduced in dimension using a dimension reduction method, and redundant features are eliminated.

[0081] S4, a plurality of basic classifiers are used to analyze the high-dimensional feature vector; for example, support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost) and the like are used as basic classifiers.

[0082] S5, the prediction results of a plurality of the basic classifiers are used as new input features, and a meta-classifier is trained to make a final judgment by integrating the information of all the classifiers.

[0083] S6, a plurality of weak classifiers are iteratively trained using a boosting method to become strong classifiers, so as to improve the accuracy of the overall model.

[0084] The embodiment uses different muscle group sEMG array image information and brain electrical information to construct a human drowsiness evaluation model, uses the prior information of the muscle electrical information, and uses a classifier algorithm to realize the evaluation and prediction of fatigue discrimination, which plays an important role in monitoring the drowsiness and health status of drivers.

[0085] The present application is based on a parallel multi-source information fusion algorithm structure, and according to the number of weak classifiers and different input data, a multi-weak classifier signal information fusion classification system is designed, and a multi-mode information fusion method is used to fuse the results of the weak classifiers.

[0086] Embodiment 3

[0087] An electronic device, such as Figure 6 As shown, comprising: a memory, program code is stored on the memory; a processor connected with the memory, and when the program code is executed by the processor, a brain electrical sign detection evaluation method is realized. For detailed description of the method, please refer to the corresponding description in the above method embodiment, which will not be repeated here.

[0088] Embodiment 4

[0089] A computer readable storage medium, such as Figure 7As shown, a program instruction is stored thereon, and the program instruction is executed to implement a brain electrical sign detection and evaluation method. For detailed description of the method, reference can be made to the corresponding description in the method embodiments described above, which will not be repeated here.

[0090] The number of devices and the scale of processing described herein are intended to be illustrative of the present application. Applications, modifications and variations of the present application will be apparent to those skilled in the art.

[0091] Although embodiments of the present application have been disclosed as above, it is not limited to the applications and embodiments listed in the specification and the embodiments, and can be fully applied to various fields suitable for the present application, and additional modifications can be easily implemented by those skilled in the art, and therefore the present application is not limited to specific details and the figures shown and described herein, without departing from the general concept defined by the claims and the equivalent scope.

[0092] The apparatus, electronic device, non-volatile computer storage medium and method provided by the embodiments of the present application are corresponding, and therefore the apparatus, electronic device, non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, electronic device, non-volatile computer storage medium will not be repeated here.

[0093] Those skilled in the art also know that in addition to implementing the controller in the form of pure computer readable program code, the controller can also be implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers and embedded microcontrollers by logically programming the method steps to achieve the same functions. Therefore, such a controller can be considered as a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can even be considered as both software units implementing the method and structures within the hardware component.

[0094] The system, apparatus or unit illustrated in the above embodiments can be specifically implemented by a computer chip or an entity, or by a product having certain functions. For the convenience of description, the above apparatus is described in various units according to functions. Of course, the functions of each unit can be implemented in the same or more software and / or hardware when implementing one or more embodiments of the present application.

[0095] Those skilled in the art will appreciate that embodiments of the present description can be readily used as a method, a system or a computer program product. Accordingly, embodiments of the present description can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer readable program code.

[0096] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0097] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0098] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flowcharts and / or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0099] It is also to be noted that the terms "comprising", "including", and "having" or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises, includes, or has a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a", "has... a", "includes... a", or "having... a" does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises, includes, or has that element.

[0100] The specification can be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. The specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules can be located in both local and remote computer storage media including memory storage devices.

[0101] The various embodiments described in the specification can be presented with respect to a progressive manner, and the same or similar parts between the various embodiments can be mutually referred to. Each embodiment focuses on the differences from other embodiments. In particular, the system embodiments are described in a relatively simple manner, and the relevant parts can be referred to the description of the method embodiments.

[0102] The specification is merely an example of one or more embodiments and is not intended to limit one or more embodiments of the specification. One or more embodiments of the specification can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of the specification should be included in the scope of the claims of one or more embodiments of the specification.

Claims

1. A method of electroencephalographic sign detection assessment, comprising: The method comprises the following steps: Processing ear canal myoelectric signal, periauricular myoelectric signal, periorbital myoelectric signal and brain electrical information to improve signal quality; Extracting time domain features and frequency domain features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information; Fusing features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information to form a high-dimensional feature vector; Analyzing the high-dimensional feature vector by using multiple basic classifiers; Taking prediction results of the multiple basic classifiers as new input features to train a meta-classifier to make a final determination by integrating information of all classifiers; Iteratively training multiple weak classifiers into strong classifiers by using a boosting method to improve accuracy of the overall model; The step of extracting time domain features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information comprises: Calculating mean value, standard deviation, RMS value and peak-to-peak value of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information; The step of extracting frequency domain features of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information comprises: Performing fast Fourier transform on the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information, analyzing power spectral density of different frequency components, calculating average frequency of the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information, analyzing changes of frequency components in the fatigue state, and further analyzing multi-scale features of the signal by using continuous wavelet transform.

2. The method of claim 1, wherein the method further comprises: The step of processing the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information comprises: Performing band-pass filtering on the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information; Performing multi-scale decomposition on the ear canal myoelectric signal, the periauricular myoelectric signal, the periorbital myoelectric signal and the brain electrical information by using wavelet transform, reconstructing the signal after removing noise; Performing high-pass filtering on the reconstructed signal to remove baseline drift; Using low-order polynomial fitting to correct the baseline drift and further improve the signal quality; Further normalizing all collected signals to eliminate differences between individuals.

3. The method of claim 1, wherein the method further comprises: The method further comprises the following steps: Using a dimension reduction method to reduce the high-dimensional feature vector and eliminate redundant features.

4. The method of claim 1, wherein: Support vector machines, random forests and extreme gradient boosting algorithms are used as basic classifiers.

5. An electronic device, comprising: The method comprises: a memory having program codes stored thereon; a processor connected to the memory, and when the program codes are executed by the processor, the method of any one of claims 1-4 is implemented.

6. A computer-readable storage medium, characterized in that, program instructions stored thereon, which when executed, implement the method of any one of claims 1-4.

7. An electroencephalographic sign detection and evaluation system for implementing the method according to any one of claims 1 to 4, characterized in that: The method comprises a periauricular flexible myoelectric sensor, a periorbital flexible myoelectric sensor and a wearable in-ear sensor system. The wearable in-ear sensor system comprises a cochlear sensor and an ear canal flexible myoelectric sensor. The cochlear sensor is used to monitor brain electrical information. The ear canal flexible myoelectric sensor is used for collecting ear canal myoelectric signals. The periauricular flexible myoelectric sensor is used for collecting periauricular myoelectric signals. The periorbital flexible myoelectric sensor is used for collecting periorbital myoelectric signals. The wearable in-ear electrophysiological system is used for fatigue detection and evaluation according to the brain electrical information, the ear canal myoelectric signals, the periauricular myoelectric signals, and the periorbital myoelectric signals.

8. An electroencephalographic sign detection and evaluation system as in claim 7, wherein: The cochlea sensor adopts an in-ear integrated electrochemical and electrophysiological sensor array for recording brain activity and sweat secretion information.

9. An electroencephalographic sign detection and evaluation system as in claim 8, wherein: The cochlea sensor is attached to an earplug to form an integrated sensor assembled in the ear.

10. The electroencephalographic sign detection and evaluation system of claim 7, wherein: The ear canal flexible myoelectric sensor includes an EEG detection layer and an electrothermal driving layer, the electrothermal driving layer is used for applying Joule heating generated by an external electric field to trigger a shape memory effect and cause expansion into a predetermined spiral shape with a larger radius, and the EEG detection layer is used for detecting ear canal myoelectric signals.

Images