Muscle activation judgment method, system and device and establishment method of muscle activation judgment model

Abstract

The invention provides a muscle activation judgment method, system and device for electromyographic signal processing and a method for establishing a model of the muscle activation judgment method, system and device. The muscle activation judgment method comprises the steps of acquiring original electromyographic signal sample data, filtering, extracting features, identifying a model and judging the muscle activation degree and state. By the adoption of the muscle activation judgment method and system device and the establishment method of the muscle activation judgment model, noise and interference can be reduced, power consumption can be reduced, the accuracy and reliability of detecting muscle activation from the electromyographic signals are remarkably improved, and safety is further improved.

Description

Technical Field

[0001] The present invention relates to the field of electromyographic signal processing, and in particular to a method, system, device and model establishment method for determining muscle activation based on electromyographic signals in electromyographic signal processing. Background Art

[0002] Electromyography (EMG) signals are electrical signals generated by muscle fibers when stimulated by nerves. It is a non-invasive detection technology for evaluating and recording skeletal muscle electrical activity. When people do fitness and rehabilitation exercises, EMG signals provide a lot of information about fitness and rehabilitation. The applications of EMG signals include but are not limited to: diagnosing muscle and nerve diseases, evaluating muscle function, analyzing movement patterns, human-computer interface development, etc.

[0003] Traditional electromyographic signal collection methods, systems, and devices need to test and collect electromyographic signals of multiple muscles and evaluate the functions of multiple muscles. They are easily affected by noise and interference, such as power supply noise, motion artifacts, random noise of the electromyographic signal itself, etc., and it is difficult to accurately determine whether the muscle is activated, especially in an environment mixed with noise and motion artifacts. Denoising of electromyographic signals is an important research topic. CN202410065438.1 proposes a surface electromyographic signal denoising method, which performs wavelet packet decomposition on the surface electromyographic signal and reconstructs multiple new wavelet packet coefficients to solve the technical problem of removing various interference noises in the surface electromyographic signal while retaining the true surface electromyographic signal. However, there is no mention of accurately determining whether the muscle is activated, and traditional systems have challenges in noise filtering, power consumption processing, and user safety. Summary of the invention

[0004] The present invention provides a method, system, device and model establishment method for muscle activation determination based on electromyographic signals in electromyographic signal processing, with the aim of reducing noise and interference, lowering power consumption, significantly improving the accuracy and reliability of detecting muscle activation from electromyographic signals, and further improving safety.

[0005] In a first aspect, the present application provides a method for determining muscle activation, the method comprising:

[0006] Step S1. Obtaining sample data: obtaining electromyographic signal data of a determined muscle position of a human body;

[0007] Step S2. Filtering: obtaining a preprocessed signal within a certain frequency band through filtering;

[0008] Step S3. Feature extraction: normalize the preprocessed signal to extract signal features, where the signal features include at least frequency domain features and time domain features;

[0009] Step S4. Model identification: input the frequency domain features and / or time domain features into the interference identification random forest model, and return the judgment result;

[0010] Step S5. Determine the degree of muscle activation based on the amplitude: When the judgments of the interference recognition random forest model are all negative, obtain the signal amplitude corresponding to the signal feature and perform electromyographic signal amplitude judgment based on the amplitude to determine whether the muscle is activated and output the judgment result; when one of the judgments of the interference recognition random forest model is yes, the output amplitude is zero, and the muscle is judged to be inactive.

[0011] Preferably, the step S2 uses a signal feedback elimination unit to eliminate power frequency interference from the electromyographic signal data, and the preprocessed signal within a certain frequency band obtained by filtering is a preprocessed signal between 20 Hz and 500 Hz.

[0012] Preferably, the interference recognition random forest model in step S4 includes an electromagnetic interference recognition model and a motion artifact recognition model, and when the electromagnetic interference recognition model or the motion artifact recognition model returns a yes result, the muscle activation judgment is no.

[0013] Preferably, the step S5 determines whether the muscle is activated and the degree of activation according to the signal amplitude. When the signal amplitude exceeds a set threshold, the intensity of muscle activation is determined and displayed through an indicating unit.

[0014] Preferably, the indicating unit is not limited to an indicator light, a display screen or an application program.

[0015] Preferably, the training of the electromagnetic interference recognition model and the motion artifact recognition model includes multiple acquisitions of electromyographic signal data from different experimenters, muscle positions and action types.

[0016] Preferably, the training of the electromagnetic interference recognition model and the motion artifact recognition model includes randomly extracting subsamples from the electromyographic signal data set and randomly selecting features when each internal node is split, and the results are obtained by majority voting or mean regression.

[0017] Preferably, the electromagnetic interference recognition model and the motion artifact recognition model are trained by adjusting hyperparameters to optimize prediction accuracy, and the adjustable hyperparameters include the number and depth of decision trees, the sample ratio of new branches and / or the sample ratio of leaf nodes.

[0018] A second aspect of the present invention is a muscle activation determination system, comprising an electromyographic sensing acquisition unit, an impedance conversion unit, an amplification unit, a signal feedback elimination unit, a filtering unit, a processor unit and a power management unit, wherein:

[0019] The myoelectric sensing acquisition unit obtains myoelectric signal data for determining muscle positions of the human body;

[0020] The impedance conversion unit is used to reduce the voltage division of the input impedance to obtain accurate electromyographic signal data;

[0021] The amplification unit is used to amplify the acquired electromyographic signal data;

[0022] The signal feedback elimination unit is used to eliminate interference signals in a certain frequency band;

[0023] The filtering unit is used to retain the preprocessed signal within a certain frequency band;

[0024] The processor unit is used to run a computer program to perform muscle activation determination, and when the program is run, all or part of the steps of any one of the first items of the present invention are executed.

[0025] Preferably, the filtering unit comprises a bandpass filter, and the filtering unit is used to retain signals between 20 Hz and 500 Hz; the signal feedback elimination unit comprises a notch filter, and the signal feedback elimination unit is used to eliminate 50 Hz and its multiple frequency signals.

[0026] Preferably, it also includes a human safety protection unit and a sleep system.

[0027] Preferably, the human body safety protection unit comprises a current limiting filter.

[0028] Preferably, the muscle activation determination system further includes a transient voltage suppressor diode (TVS) or a capacitor.

[0029] In a third aspect, the present application provides an electronic device for determining muscle activation, the electronic device comprising: a processor for calling and running a computer program from a memory so that the electronic device performs all or part of the steps in the method described in the first aspect above; the electronic device also comprises: the memory and / or a communication interface, the memory being used to store the computer program, and the communication interface being used to send and receive data / signals.

[0030] In a fourth aspect, the present application provides a computer program storage medium for muscle activation determination, wherein the computer readable medium stores a program code, and when the computer program code runs on a computer, the computer executes all or part of the steps in the method described in the first aspect above.

[0031] In a fifth aspect, the present application provides a muscle activation determination chip system, which includes at least one processor. When program instructions are executed in the at least one processor, all or part of the steps in the method described in the first aspect above are executed.

[0032] In a sixth aspect, the present application provides a method for establishing a muscle activation model based on electromyographic signals, comprising the following steps:

[0033] Obtain sample data: obtain electromyographic sensor data of different muscle positions and different states of different people;

[0034] The sample data is processed: common mode interference is performed on the sample data to eliminate common mode noise, and then filtering is performed to obtain the electromyographic signal within a certain frequency band through filtering to obtain the preprocessed signal

[0035] Signal feature extraction: normalize the preprocessed signal to extract signal features, where the signal features include at least frequency domain features and time domain features;

[0036] Fitting: Fit the signal features through the random forest model to obtain a model with signal features as input and EMG signal amplitude as output;

[0037] Activation judgment: judge the degree and state of muscle activation based on the amplitude of the output electromyographic signal.

[0038] Preferably, the fitting process further includes: fitting the signal features through a random forest model to obtain the input as the signal features and the output as a judgment of whether the signal contains motion artifacts and / or whether the signal contains severe electromagnetic interference; when one of the judgments is yes, the output electromyographic signal amplitude is zero; when one of the judgments is no, the signal amplitude corresponding to the signal features is obtained and output.

[0039] Furthermore, the signal characteristics also include amplitude.

[0040] The muscle activation determination method, determination system, electronic device, computer program storage unit and chip system based on electromyographic signal processing and the method for establishing a muscle activation model provided in the present application can reduce noise and interference, reduce power consumption, significantly improve the accuracy and reliability of detecting muscle activation from electromyographic signals, and further improve safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a muscle activation determination method in one embodiment of the present application.

[0042] Figure 2a , Figure 2b , Figure 2c It is a schematic diagram demonstrating three types of signals in one embodiment of the present application.

[0043] Figure 3 It is a functional module flow chart of a muscle activation determination system in one embodiment of the present application.

[0044] Figure 4 This is a schematic diagram of wearing an electromyographic sensing acquisition unit in one embodiment of the present application. DETAILED DESCRIPTION

[0045] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention are only used to illustrate one (some) implementations of the present invention, rather than to limit the present invention. Simple changes similar to the present embodiment by ordinary technicians in the field all fall within the scope of protection of the present invention.

[0046] The terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations on the present application. As used in the specification and the appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include expressions such as "one or more", unless there is a clear contrary indication in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one, two or more. The term "and / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist; for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0047] References to "one embodiment" or "some embodiments" etc. described in this specification mean that a particular feature, structure or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear at different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0048] The electronic device in the embodiments of the present application may refer to user equipment, access terminal, mobile device, user terminal, terminal, wireless communication device. The terminal device may also be a wired or wireless phone, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device, etc., which is not limited in the embodiments of the present application.

[0049] In a first aspect, the present application provides a method for determining muscle activation. Figure 1 : is a flow chart of a muscle activation determination method in one embodiment of the present application, the method comprising:

[0050] Step S1. Obtaining sample data: obtaining electromyographic signal data of a determined muscle position of a human body;

[0051] Step S2. Filtering: obtaining a preprocessed signal within a certain frequency band through filtering;

[0052] Step S3. Feature extraction: normalize the preprocessed signal to extract signal features, where the signal features include at least frequency domain features and time domain features;

[0053] Step S4. Model identification: input frequency domain features and / or time domain features into the interference identification random forest model, and return the judgment result;

[0054] Step S5. Determine the degree of muscle activation based on the amplitude: When the judgments of the interference recognition random forest model are all negative, obtain the signal amplitude corresponding to the signal feature and perform electromyographic signal amplitude judgment based on the amplitude to determine whether the muscle is activated and output the judgment result; when one of the judgments of the interference recognition random forest model is yes, the output amplitude is zero, and the muscle is judged to be inactive.

[0055] In this embodiment, when the judgments of the interference identification random forest model are all negative, the corresponding signal amplitude of the corresponding signal feature is obtained from the preprocessed signal. In another embodiment, when the feature extraction signal feature includes amplitude, when the judgments of the interference identification random forest model are all negative, the corresponding amplitude is directly obtained from the signal feature; the degree of muscle activation is judged according to the corresponding amplitude.

[0056] When one of the judgments of the interference identification random forest model is yes, no matter whether the signal amplitude of the corresponding signal feature is obtained from the preprocessed signal or the signal amplitude is obtained from the signal feature, the obtained value is zero, and the muscle is judged to be inactivated.

[0057] Furthermore, step S2 uses a signal feedback elimination unit to eliminate power frequency interference from the electromyographic signal data, obtains a preprocessed signal between 20Hz and 500Hz by filtering, and extracts signal features through normalization processing in step S3, and the signal features include at least frequency domain features and time domain features. The frequency domain features and / or time domain features are input into the electromagnetic interference recognition model and the motion artifact recognition model. When the electromagnetic interference recognition model or the motion artifact recognition model returns a yes result, the muscle activation is judged to be no. When the electromagnetic interference recognition model and the motion artifact recognition model return no results, it is further judged whether to perform muscle activation and the intensity of activation. At this time, it is necessary to input the signal features, including frequency domain features, time domain features and amplitude, and perform electromyographic signal amplitude judgment, judge whether the muscle is activated and the degree of activation according to the size of the signal amplitude, and when the signal amplitude exceeds the set threshold, judge the intensity of muscle activation and display it to the user through the indicator unit.

[0058] Furthermore, the indication unit is not limited to an indicator light, a display screen or an application program.

[0059] In another embodiment, the signal characteristic comprises amplitude.

[0060] In the embodiment of the present application, the training of the electromagnetic interference recognition model and the motion artifact recognition model includes multiple acquisitions of electromyographic signal data from different experimenters, muscle positions and action types. During training, subsamples are randomly selected from the electromyographic signal data set, and features are randomly selected when each internal node is split. The prediction results are obtained by majority voting or mean regression. Please refer to Figure 4 It is a schematic diagram of wearing the electromyographic sensing acquisition unit 100 for acquiring different muscle parts of different human bodies in one embodiment of the present application.

[0061] Furthermore, the training of the electromagnetic interference recognition model and the motion artifact recognition model optimizes the prediction accuracy by adjusting hyperparameters, and the adjustable hyperparameters include the number and depth of decision trees, the sample ratio of new branches and / or the sample ratio of leaf nodes.

[0062] The present application also provides a muscle activation determination system. Figure 2a-2c The following is a functional module flow chart of a muscle activation determination system in one embodiment of the present application. The muscle activation determination system includes an electromyographic sensor acquisition unit, an impedance conversion unit, an amplification unit, a signal feedback elimination unit, a filtering unit, a processor unit, and a power management unit, wherein:

[0063] The myoelectric sensing acquisition unit obtains the myoelectric signal data of the determined muscle position of the human body;

[0064] Impedance conversion unit, used to reduce the voltage division of input impedance to obtain accurate electromyographic signal data;

[0065] An amplifying unit, used for amplifying the acquired electromyographic signal data;

[0066] A signal feedback elimination unit is used to eliminate interference signals in a certain frequency band;

[0067] A filtering unit, used to retain the preprocessed signal within a certain frequency band;

[0068] A processor unit is used to run a computer program to perform muscle activation determination, and when the program is run, all or part of the steps of any one of the first items of the present invention are executed.

[0069] Furthermore, in this embodiment, the filtering unit includes a bandpass filter, and the filtering unit is used to retain signals between 20 Hz and 500 Hz.

[0070] The signal feedback elimination unit includes a notch filter, which is used to eliminate 50HZ and its frequency multiple signals. At the same time, the notch filter feeds back the electromyographic signal after eliminating the interference signal to the electromyographic sensor acquisition unit to provide a signal reference benchmark to facilitate the acquisition of accurate electromyographic signal data. In a preferred embodiment, a multi-stage power supply filter, a high power supply rejection ratio input power supply, a high-precision, low-noise amplifier and a processor unit can be used to reduce noise.

[0071] Furthermore, the muscle activation determination system for electromyographic signal processing can use low-power components, including microcontroller unit MCU, linear voltage regulator, switching power supply and battery charging chip and other low-power components to reduce power consumption.

[0072] In a preferred embodiment, after obtaining the electromyographic signal data of the human body to determine the muscle position, a signal between 20 Hz and 500 Hz is obtained by filtering as a preprocessing signal; then, the preprocessing signal is normalized, and the frequency domain features and time domain features are extracted to obtain the corresponding waveform diagram; the above waveform diagrams are respectively input into the electromagnetic interference recognition model and the motion artifact recognition model, and the waveforms are compared, and the judgment result is returned. A standard waveform is preset in the interference model as the corresponding reference waveform. For example, in this embodiment, the reference waveforms are respectively preset in the motion artifact recognition model and the electromagnetic interference recognition model. Figure 2a It is a schematic diagram of the motion artifact signal waveform; Figure 2b It is a schematic diagram of the electromagnetic interference signal waveform; Figure 2c The figure is a schematic diagram of a normal muscle contraction signal waveform. The preprocessed signal is normalized to obtain a real-time waveform, and different waveforms are obtained, but they can all be compared with the reference waveform to determine whether it is a motion artifact signal or an electromagnetic interference signal or a waveform composed of a normal muscle contraction signal.

[0073] In the embodiment of the present application, the waveform obtained in real time is input into the motion artifact recognition model, and compared with the reference waveform, if the judgment result is yes, it is judged as a motion artifact, and if the judgment result is no, it is judged not to be a motion artifact; similarly, the waveform obtained in real time is input into the electromagnetic interference recognition model for comparison, and compared with the reference waveform, if the judgment result is yes, it is judged as electromagnetic interference, and if the judgment result is no, it is judged not to be electromagnetic interference; when one of the motion artifact recognition model and the electromagnetic interference recognition model is yes, the output amplitude is zero, and the muscle is judged not to be activated. If the motion artifact recognition model and the electromagnetic interference recognition model both judge no, the amplitude of the signal feature is judged as the amplitude of the electromyographic signal, the waveform is input and compared with the normal muscle contraction signal reference waveform, whether the muscle is activated and the judgment result is output; or by comparing the normal amplitude size or by comparing with the preset amplitude, the degree of muscle activation is judged, and the judgment result is that the muscle is not activated, weakly activated or strongly activated, etc.

[0074] Figure 3 For the wearing of the electromyographic sensing acquisition unit in one embodiment of the present application, in a preferred embodiment, the muscle activation determination system for electromyographic signal processing also includes a human body safety protection unit, and a current limiting filter is set to prevent excessive current from flowing into the human body. A transient voltage suppression diode (TVS) or a capacitor may also be included to prevent static electricity.

[0075] In order to further reduce power consumption, the system provided by the present application also includes a sleep system, and the processor unit can shut down the sleep system when there is no trigger within a fixed time. In addition, when the processor detects a current detection fault, an overcurrent fault, etc., the power management unit is automatically cut off to shut down the system.

[0076] In a third aspect, the present application provides an electronic device for determining muscle activation, the electronic device comprising: a processor for calling and running a computer program from a memory so that the electronic device performs all or part of the steps in the muscle activation determination method. The electronic device also comprises: a memory and / or a communication interface, the memory being used to store the computer program, and the communication interface being used to send and receive data / signaling.

[0077] In a fourth aspect, the present application provides a computer program storage medium for muscle activation determination, wherein the computer readable medium stores program code, and when the computer program code runs on a computer, the computer executes all or part of the steps in the muscle activation determination method.

[0078] In a fifth aspect, the present application provides a muscle activation determination chip system, the chip system comprising at least one processor, and when program instructions are executed in at least one processor, all or part of the steps in the muscle activation determination method are executed.

[0079] In a sixth aspect, the present application provides a method for establishing a muscle activation model based on electromyographic signals, comprising the following steps:

[0080] Obtain sample data: obtain electromyographic sensor data of different muscle positions and different states of different people;

[0081] The obtained sample data is processed: common mode interference is performed on the sample data to eliminate common mode noise, and then filtering is performed to obtain electromyographic signals within a certain frequency band through filtering to obtain preprocessed signals;

[0082] Signal feature extraction: normalize the preprocessed signal and extract signal features, which include at least frequency domain features and time domain features;

[0083] Fitting: Fit the signal features through the random forest model to obtain a model with signal features as input and EMG signal amplitude as output;

[0084] Activation judgment: judge the degree and state of muscle activation based on the amplitude of the output electromyographic signal.

[0085] Furthermore, the signal characteristics also include amplitude; the fitting process further includes: fitting the signal characteristics through a random forest model, obtaining the input as the signal characteristics, and the output as a judgment of whether the signal contains motion artifacts and / or whether the signal contains severe electromagnetic interference; when one of the judgments is yes, the output electromyographic signal amplitude is zero; when all the judgments are no, the signal amplitude corresponding to the signal characteristics is obtained and output.

[0086] Furthermore, the fitting process of the present application can be fitted by the method of the first aspect as above, including establishing a standard reference comparison waveform by normalization and waveform comparison; such as establishing an electromagnetic interference recognition model and a motion artifact recognition model including a reference waveform.

[0087] The muscle activation determination method, determination system, electronic device, computer program storage unit and chip system, and determination model establishment method provided in the present application can reduce noise and interference, reduce power consumption, significantly improve the accuracy and reliability of detecting muscle activation from EMG signals, and further improve safety.

[0088] Those of ordinary skill in the art will appreciate that the units and method algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0089] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional module in each embodiment of the present application can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module. If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk. The above is only a specific implementation method of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A muscle activation determination method, characterized in that: The method includes: Step S1. Obtaining original electromyographic signal data: obtaining electromyographic signal data of a determined muscle position of a human body; Step S2. Filtering: Processing the original electromyographic signal data, and obtaining a pre-processed signal within a certain frequency band through filtering; Step S3. Feature extraction: normalize the preprocessed signal to extract signal features, where the signal features include frequency domain features and time domain features; Step S4. Model identification: input the frequency domain features and / or time domain features into the interference identification random forest model, and return the judgment result; Step S5. Determine the degree of muscle activation according to the amplitude: When the judgment of the interference identification random forest model is negative, obtain the signal amplitude corresponding to the signal feature and perform electromyographic signal amplitude judgment according to the amplitude to determine whether the muscle is activated and output the judgment result; When one of the judgments of the interference identification random forest model is yes, the output amplitude is zero and the muscle is judged to be inactive.

2. The muscle activation determination method according to claim 1, characterized in that: The step S2 uses a signal feedback elimination unit to eliminate power frequency interference from the electromyographic signal data, and the preprocessed signal within a certain frequency band obtained by filtering is a preprocessed signal between 20 Hz and 500 Hz.

3. The muscle activation determination method according to claim 2, characterized in that: The interference identification random forest model in step S4 includes an electromagnetic interference identification model and a motion artifact identification model. When the electromagnetic interference identification model or the motion artifact identification model returns a yes result, the muscle activation judgment is no.

4. The muscle activation determination method according to claim 3, characterized in that: The step S5 determines whether the muscle is activated and the degree of activation according to the signal amplitude. When the signal amplitude exceeds a set threshold, the intensity of muscle activation is determined and displayed to the user.

5. The muscle activation determination method according to claim 4, characterized in that: The muscle activation intensity information is displayed to the user through an indication unit, and the indication unit is not limited to an indicator light, a display screen or an application.

6. The muscle activation determination method according to claim 4, characterized in that: The training of the electromagnetic interference recognition model and the motion artifact recognition model includes multiple acquisitions of electromyographic signal data from different experimenters, muscle positions and action types.

7. The muscle activation determination method according to claim 6, characterized in that: The training of the electromagnetic interference recognition model and the motion artifact recognition model includes randomly extracting subsamples from the electromyographic signal data set and randomly selecting features when each internal node is split, and the results are obtained through majority voting or mean regression.

8. The muscle activation determination method according to claim 7, characterized in that: The electromagnetic interference recognition model and the motion artifact recognition model are trained by adjusting hyperparameters to optimize prediction accuracy. The adjustable hyperparameters include the number and depth of decision trees, the sample ratio of new branches and / or the sample ratio of leaf nodes.

9. A muscle activation determination system, characterized in that: It includes an electromyography sensor acquisition unit, an impedance transformation unit, an amplification unit, a signal feedback elimination unit, a filtering unit, a processor unit and a power management unit, wherein: The myoelectric sensing acquisition unit obtains myoelectric signal data for determining muscle positions of the human body; The impedance conversion unit is used to reduce the voltage division of the input impedance to obtain accurate electromyographic signal data; The amplification unit is used to amplify the acquired electromyographic signal data; The signal feedback elimination unit is used to eliminate interference signals in a certain frequency band; The filtering unit is used to retain the preprocessed signal within a certain frequency band; The processor unit is used to run a computer program to perform muscle activation determination, and the program executes all or part of the steps according to any one of claims 1 to 8 when running.

10. The muscle activation determination system according to claim 9, characterized in that: The filtering unit includes a bandpass filter, which is used to retain signals between 20 Hz and 500 Hz; the signal feedback elimination unit includes a notch filter, which is used to eliminate 50 Hz and its frequency multiplication signals and eliminate power frequency interference caused by power lines.

11. The muscle activation determination system according to claim 10, characterized in that: It also includes a human safety protection unit and a hibernation system.

12. The muscle activation determination system according to claim 11, characterized in that: The human body safety protection unit includes a current limiting filter.

13. The muscle activation determination system according to claim 12, characterized in that: The muscle activation determination system further includes a transient voltage suppressor diode (TVS) or a capacitor.

14. An electronic device for determining muscle activation, characterized in that: The electronic device includes a processor, which is used to call and run a computer program from a memory, so that the electronic device performs all or part of the steps in the method as claimed in any one of claims 1 to 8; the electronic device also includes the memory and / or communication interface, the memory is used to store the computer program, and the communication interface is used to send and receive data / signaling.

15. A muscle activation determination computer program storage medium, characterized in that: The computer-readable medium stores a program code, and when the program code is executed on a computer, the computer is caused to execute all or part of the steps in any one of the methods of claims 1 to 8.

16. A muscle activation determination chip system, characterized in that: The chip system comprises at least one processor, and when the program instructions are executed in the at least one processor, all or part of the steps in any one of the methods of claims 1 to 8 are executed.

17. A method for establishing a muscle activation model based on electromyographic signals, characterized in that: The method comprises the following steps: obtaining sample data: obtaining myoelectric sensor data of different determined muscle positions and different states of different populations; The obtained sample data is processed: common mode interference is performed on the sample data to eliminate common mode noise, and then filtering is performed to obtain electromyographic signals within a certain frequency band through filtering to obtain preprocessed signals; Signal feature extraction: normalize the preprocessed signal to extract signal features, where the signal features include at least frequency domain features and time domain features; Fitting: Fit the signal features through the random forest model to obtain a model with signal features as input and EMG signal amplitude as output; Activation judgment: judge the degree and state of muscle activation based on the amplitude of the output electromyographic signal.

18. The method for establishing a muscle activation model based on electromyographic signals according to claim 17, characterized in that: The fitting process further includes: fitting the signal features through a random forest model, obtaining the input as the signal features and the output as the judgment of whether the signal contains motion artifacts and / or whether the signal contains severe electromagnetic interference; when one of the judgments is yes, the output electromyographic signal amplitude is zero; when all the judgments are no, obtaining the signal amplitude corresponding to the signal features and outputting it.

Images