Monitoring and physiotherapy integrated electronic sports glove and signal processing method thereof

Abstract

The invention provides a monitoring and physiotherapy integrated electronic sports glove and a signal processing method thereof.The glove comprises an elastic glove body, and the elastic glove body is provided with a myoelectricity collecting electrode, an electrical stimulation electrode, an embedded controller and a stretchable circuit; the electromyographic collection electrode and the electrical stimulation electrode are connected with the embedded controller through a stretchable circuit, the embedded controller comprises an electromyographic collection module, a transmission module, an electrical stimulation module and a core chip, and electromyographic signals of a user are collected in real time through the electromyographic collection module and the electromyographic collection electrode; the core chip is used for collecting myoelectric signals and transmitting the collected myoelectric signals to the upper computer through the transmission module, the fatigue state of the user is obtained on the upper computer according to the fatigue judgment model, and when muscle fatigue of the user is monitored, the core chip controls the electrical stimulation module to give out electrical stimulation and electrical stimulation physiotherapy is carried out through the electrical stimulation electrode. The monitoring and physical therapy integrated electronic sports glove can effectively monitor the muscle fatigue state and relieve muscle fatigue in time.

Description

Technical Field

[0001] The present invention relates to the technical field of e-sports wearable equipment, and in particular to an integrated monitoring and physical therapy e-sports glove and a signal processing method thereof. Background Art

[0002] E-sports projects bring certain challenges to the participants' bodies. It is a long-term static work. Whether in daily training or competition, it is necessary to maintain a static posture and high-frequency hand operations for a long time, which will cause the body muscles to be in a long-term state of tension and bear a high-intensity static load. Long-term such a state is prone to chronic injuries. As the main group participating in e-sports, teenagers, these chronic injuries will not only threaten their e-sports performance, but also have a long-term impact on the body, and even endanger their daily life and work status. Studies on e-sports injuries show that more than half of e-sports athletes or e-sports enthusiasts have experienced symptoms of sports injuries. In particular, wrists and fingers, as an important factor that hinders the competitive performance of e-sports athletes, are under tremendous pressure in countless clicks and slides. Long-term sports loads cause chronic sports injuries in the hands of e-sports athletes, such as mouse hand, tendonitis, tenosynovitis, arthritis, etc., which seriously affect their competitive level and career.

[0003] At present, the research on hand injuries of e-sports athletes mainly focuses on the analysis of injury causes and medical treatment, but rarely involves prevention. There are some protective products for e-sports athletes on the market, such as ergonomic mice, gaming finger sleeves, mouse pads, etc., but these products have relatively simple functions, and their functions are mainly focused on improving comfort. They cannot monitor hand fatigue in real time and lack comprehensive attention and protection for hand health. Including some current fatigue monitoring systems, the main function is to collect electromyographic signals. Some systems integrate simple analysis functions. Non-professionals cannot directly obtain the state of the muscles, and cannot provide timely feedback on the fatigue state of the muscles. They lack real-time and effectiveness. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention proposes a monitoring and physical therapy integrated e-sports glove and a signal processing method thereof. The present invention can effectively monitor the muscle fatigue state and relieve muscle fatigue in time.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The invention discloses an integrated monitoring and therapy e-sports glove, comprising an elastic glove body, on which are arranged electromyographic acquisition electrodes, electrical stimulation electrodes, an embedded controller and a stretchable circuit. The electromyographic acquisition electrodes and the electrical stimulation electrodes are connected to the embedded controller via the stretchable circuit. The embedded controller comprises an electromyographic acquisition module, a transmission module, an electrical stimulation module and a core chip. The electromyographic signals of the user are collected in real time via the electromyographic acquisition module and the electromyographic acquisition electrodes, and the collected electromyographic signals are transmitted to a host computer via the transmission module. The fatigue state of the user is derived on the host computer according to a fatigue discrimination model. When muscle fatigue of the user is detected, the core chip controls the electrical stimulation module to emit electrical stimulation and performs electrical stimulation therapy via the electrical stimulation electrodes.

[0007] Preferably, the embedded controller is a flexible circuit board, which is printed by a flexible printer and embedded in the glove to form a closed circuit with the flexible stretchable circuit.

[0008] Preferably, the embedded controller further includes a buzzer. When muscle fatigue of the user is detected, the core chip controls the buzzer to remind the user through the buzzer that the user's hand has reached a fatigue state.

[0009] Preferably, the electromyography acquisition module is used to collect electromyography signals from the muscle surface. After the electromyography acquisition electrodes collect the signals from the skin surface, the signals are amplified, filtered, and adjusted by the entire module circuit and then input into the core chip for processing. The electromyography acquisition module includes a pre-stage amplifier circuit, a high-pass filter circuit, a low-pass filter circuit, a post-stage amplifier circuit, and a voltage boost circuit.

[0010] Preferably, the electrical stimulation module is used to generate a stimulation current, and includes a Boost circuit and an electrical stimulation drive circuit. The Boost circuit achieves continuously adjustable boost by adjusting the duty cycle of the PWM wave, and then converts the PWM wave into a constant current electrical stimulation pulse through the electrical stimulation drive circuit, and then performs electrical stimulation through the electrical stimulation electrodes.

[0011] Preferably, the host computer includes an electromyographic data preprocessing module, a time-frequency domain feature extraction module and a fatigue discrimination model. The collected electromyographic data are processed and feature extracted in the host computer, and then input into the fatigue discrimination model. The fatigue discrimination result is transmitted back to the core chip, and the core chip issues an electrical stimulation instruction.

[0012] Preferably, the electromyographic data preprocessing module of the host computer performs denoising by an empirical mode decomposition method.

[0013] Preferably, the time-frequency domain feature extraction module of the host computer is used to extract features of the preprocessed electromyographic signals, wherein the time domain index selects to extract the electromyographic integral value iEMG, and the frequency domain index selects to extract the mean power frequency MPF. The feature extraction module uses a joint analysis method of time domain and frequency domain to determine whether muscles are fatigued based on the changing trends of time domain features and frequency domain features.

[0014] Preferably, the fatigue discrimination model is used for fatigue state discrimination. After the extracted time domain and frequency domain features of the electromyographic signal are combined with subjective evaluation to mark the labels, they are sent to Matlab to classify and train the data set using a support vector machine to obtain a fatigue discrimination model; the constructed fatigue discrimination model can judge whether the muscle is fatigued and the degree of fatigue through the input feature values, and transmit the results back to the core chip through the transmission module, thereby realizing real-time evaluation of the user's muscle fatigue level.

[0015] Furthermore, the present invention also provides a signal processing method for monitoring the integrated physiotherapy e-sports gloves, comprising the following steps:

[0016] Acquire surface electromyographic signals of target muscle groups in real time;

[0017] Preprocessing the collected surface electromyography signals;

[0018] Perform feature extraction on the preprocessed surface electromyography signal to obtain the time domain features and frequency domain features of the surface electromyography signal;

[0019] The time domain and frequency domain eigenvalues ​​of the surface electromyography signal are input into the trained fatigue discrimination model, and the current fatigue state of the muscle is output to achieve real-time monitoring of the muscle fatigue state.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] 1. The present invention combines the monitoring of human fatigue and the relief of human fatigue into one, integrates monitoring and physical therapy functions, monitors the hand muscle status of e-sports players in real time, and automatically turns on electrical stimulation to relieve fatigue when muscle fatigue is detected, prevents further muscle damage, maintains maximum muscle activity, solves the problem that e-sports players' hands are prone to fatigue and injury and cannot guarantee rest time, and enables e-sports players to get timely relief during training.

[0022] 2. The present invention utilizes flexible stretchable circuits, flexible electrodes, and flexible circuit boards to form embedded monitoring and therapy integrated e-sports gloves, and uses stretchable circuits instead of traditional lead wires to connect embedded controllers, thereby avoiding wire entanglement. The gloves are easy to carry, have a long service life, and do not affect e-sports operations during use.

[0023] 3. The present invention integrates the design of each module to prevent duplication of functions or components between modules, reduce the volume of the overall hardware, and the complexity of wire connections. It can also achieve real-time monitoring of body functions during training and provide feedback after muscle fatigue is detected without the need to connect multiple instruments. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0025] Figure 1 This is a schematic diagram of the structure of the monitoring and physical therapy integrated e-sports gloves of the present invention;

[0026] Figure 2 This is a hardware block diagram of the present invention's monitoring and therapy integrated e-sports gloves;

[0027] Figure 3 This is a flowchart of the signal processing method for monitoring the integrated physiotherapy e-sports gloves of the present invention.

[0028] Figure 4 This is a flow chart of the electromyographic signal processing of the integrated physiotherapy e-sports gloves monitored by the present invention. DETAILED DESCRIPTION

[0029] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0030] When an e-sports operator subjectively feels hand pain, the hand muscles have actually entered a very tired state and may even be injured, and e-sports athletes will not stop training due to hand fatigue; therefore, the present invention provides an integrated monitoring and physical therapy e-sports glove to achieve continuous real-time monitoring of muscles, issue warnings in time before the muscles enter a fatigue state, and perform hand physical therapy in time to prevent hand muscle fatigue.

[0031] Specifically, Figure 1 and Figure 2 As shown, the monitoring and physical therapy integrated e-sports glove comprises an elastic glove body 1, on which are provided electromyographic acquisition electrodes 2, electrical stimulation electrodes 3, an embedded controller 4 and a flexible stretchable circuit 5. The electromyographic acquisition electrodes 2 and the electrical stimulation electrodes 3 are connected to the embedded controller 4 via the flexible stretchable circuit 5.

[0032] In this embodiment, the electromyographic acquisition electrode 2 and the electrical stimulation electrode 3 use flexible fabric electrodes instead of traditional wet electrodes. The fabric electrodes are woven from silver-plated and graphene polymer yarn mixed electrodes, have excellent durability, and are suitable for the field of smart textiles for sports training; the electromyographic acquisition electrode 2 is used to collect electromyographic signals, and the electrical stimulation electrode 3 is used for electrical stimulation; the flexible stretchable circuit 5 can be printed by a flexible printer to replace the lead wire.

[0033] The embedded controller 4 is a flexible circuit board, which is printed by a flexible printer and embedded in the glove to form a closed circuit with the flexible stretchable circuit 5; the embedded controller 4 integrates monitoring and physical therapy functions, including an electromyography acquisition module, a transmission module, an electrical stimulation module, a core chip and a buzzer. The electromyography acquisition module and the electromyography acquisition electrodes collect the user's electromyography signals in real time, and the collected electromyography signals are transmitted to the host computer through the transmission module. The host computer derives the user's fatigue state according to the fatigue discrimination model. When the user's muscle fatigue is detected, the core chip controls the electrical stimulation module to emit electrical stimulation and performs electrical stimulation physical therapy through the electrical stimulation electrodes. At the same time, the core chip controls the buzzer to remind the user that the hand has reached a fatigue state.

[0034] The electromyography acquisition module is used to collect electromyography signals on the surface of the muscle. After the electromyography acquisition electrode 2 collects the signal from the skin surface, it is amplified, filtered, and adjusted by the entire module circuit and then input into the core chip for processing. The electromyography acquisition module includes a pre-amplifier circuit, a high-pass filter circuit, a low-pass filter circuit, a post-amplifier circuit, and a voltage booster circuit; the pre-amplifier circuit is composed of three amplification operators, and the two voltage inputs come from the positive and negative poles of the surface electrodes respectively; the high-pass filter circuit uses a second-order active filter to filter out the low-frequency signal coupled into the electromyography signal acquisition during the acquisition process; the low-pass filter circuit is used to filter out high-frequency interference signals above 500Hz; the post-amplifier circuit is used to amplify the surface electromyography signal for the second time, so that the signal voltage reaches an amplitude range that can be recognized; the voltage booster circuit is used to boost the voltage of the amplified and filtered electromyography signal.

[0035] The electrical stimulation module is used to generate stimulation current to make muscles contract and relax, improve local blood circulation, relieve soreness and swelling, and achieve the effect of muscle relaxation; the electrical stimulation module includes a Boost boost circuit and an electrical stimulation drive circuit. The Boost boost circuit can achieve continuously adjustable boost by adjusting the duty cycle of the PWM wave, and then convert the PWM wave into an unbalanced biphasic electrical stimulation pulse with a constant current through the electrical stimulation drive circuit. The biphasic stimulation pulse is safer than the single-phase wave, ensuring the safety of user use; then electrical stimulation is performed through the electrical stimulation electrode 3, and the electrical stimulation electrode 3 is connected to the embedded controller 4 through the stretchable circuit 5.

[0036] The host computer is mainly responsible for analyzing and processing the electromyographic data, including preprocessing the electromyographic data, extracting time-frequency domain features, and using the fatigue discrimination model trained by the support vector machine algorithm, transmitting the fatigue discrimination results back to the core chip, and the core chip issues an electrical stimulation instruction.

[0037] The myoelectric data preprocessing module of the host computer performs denoising by an empirical mode decomposition method, and preprocesses the collected myoelectric signal data, including removing power supply interference, motion artifacts and other noises that may affect signal quality.

[0038] The time-frequency domain feature extraction module of the host computer is used to extract features from the preprocessed electromyographic signal, and select the commonly used time-frequency domain indicators of the electromyographic signal, wherein the time-domain indicator selects the electromyographic integral value iEMG to be extracted, and the frequency-domain indicator selects the average power frequency MPF to be extracted. The feature extraction module uses the time-domain and frequency-domain joint analysis method to judge whether the muscle is fatigued according to the changing trend of the time-domain characteristics and the frequency-domain characteristics. The time-domain and frequency-domain joint analysis method judges the muscle principle: when the time-domain and frequency-domain indicators increase at the same time, it indicates that the muscle strength increases; when the time-domain indicator decreases and the frequency-domain indicator increases, it indicates that the muscle is in the strength recovery period; when the time-domain and frequency-domain indicators decrease at the same time, it indicates that the muscle strength decreases; when the time-domain indicator increases and the frequency-domain indicator decreases, it indicates that the muscle is fatigued. iEMG can reflect the total discharge of muscle activity units within a certain period of time, and can characterize the changes in the strength of electromyographic signals over time. Within a certain period of time, the more unit motor potentials involved in the activity and the more discharges of each motor unit, the greater the iEMG value. It has good specificity in responding to muscle fatigue and is one of the important indicators for fatigue evaluation. MPF represents the frequency of the center of gravity of the power spectrum curve and is a commonly used method in frequency domain analysis. MPF changes stably and has a smaller amplitude.

[0039] The fatigue discrimination model is used to discriminate the fatigue state. After the extracted time domain and frequency domain features of the electromyographic signal are combined with the subjective evaluation to mark the label, it is sent to Matlab to classify and train the data set using a support vector machine to obtain the fatigue discrimination model. Based on the extracted features, a model for distinguishing the muscle fatigue level is constructed and trained. The constructed fatigue discrimination model can judge whether the muscle is fatigued and the degree of fatigue through the input feature value, and transmit the result back to the core chip through the transmission module to achieve real-time evaluation of the user's muscle fatigue level.

[0040] The workflow of this embodiment is as follows:

[0041] The electromyography acquisition electrodes are used to collect electromyography signals. The core chip performs analog-to-digital conversion to convert the sampled analog signals into digital signals, and transmits them to the host computer through the transmission module for fatigue judgment. After the data transmitted to the host computer is preprocessed and feature extracted, it is judged by the fatigue discrimination model that fatigue occurs. By sending fatigue instructions to the core chip, the core chip controls the electrical stimulation module to generate medium and low frequency pulse signals, and uses the electrical stimulation electrodes to release medium and low frequency pulse currents to relieve hand fatigue. At the same time, the buzzer will emit a buzzing sound, which also generates an auditory reminder.

[0042] Furthermore, the present invention also provides a signal processing method for monitoring the integrated physiotherapy e-sports gloves based on a fatigue discrimination model, such as Figure 3 and Figure 4 As shown, the method comprises the following steps:

[0043] S1: Real-time acquisition of surface electromyographic signals of target muscle groups;

[0044] Specifically, the surface electromyographic signals of the target muscle group are acquired in real time, the user's electromyographic signals are collected through electromyographic acquisition electrodes, the collected electromyographic signals are amplified and filtered, and then stored, analog-to-digital converted and packaged through the main control chip, and then transmitted to the host computer through the transmission module for processing and analysis.

[0045] S2: preprocessing the collected surface electromyography signals;

[0046] Specifically, the surface electromyography signal is an extremely weak, non-stationary, time-varying signal, which is easily disturbed by various noises during the acquisition process, affecting the quality of the acquired signal. After the signal acquisition is completed by the surface electromyography signal acquisition module, the data is transmitted to the host computer through the transmission module, and the empirical mode decomposition method is used for denoising. The collected electromyography signal data is preprocessed, including removing power supply interference, motion artifacts and other noises that may affect the signal quality.

[0047] S3: extracting features from the preprocessed surface electromyography signal to obtain time domain features and frequency domain features of the surface electromyography signal;

[0048] Specifically, in the process of local muscle groups transferring from the daily relaxation state to the deep fatigue state of muscles, the surface electromyographic signal of the target muscle group will increase in the time domain signal amplitude and move the frequency domain spectrum toward the low frequency direction. When selecting fatigue state recognition features, the time-frequency domain features of the signal with obvious changes should be selected based on this change. The joint analysis method of time domain and frequency domain is adopted to process the electromyographic data. According to the trend that the amplitude of the electromyographic signal will change during the fatigue process, the electromyographic integral value (iEMG) is selected as the time domain feature of the analysis, and the mean power frequency (MPF) is selected as the frequency domain feature value of the analysis.

[0049] In the surface electromyographic signal method, the calculation method of the time domain characteristic integrated electromyographic value (iEMG) is:

[0050] iEMG=∫ t 1+T |EMG(t)|dt

[0051] The calculation method of the frequency domain eigenvalue mean power frequency (MPF) is:

[0052]

[0053] Where f is the frequency value of the myoelectric power spectrum within the frequency interval, and P(f) is the frequency spectrum within the myoelectric power frequency interval.

[0054] S4: Input the time domain and frequency domain eigenvalues ​​of the surface electromyography signal into the trained fatigue discrimination model, output the current fatigue state of the muscle, and realize real-time monitoring of the muscle fatigue state.

[0055] Specifically, when muscles become fatigued, the surface electromyographic signals will change, thus reflecting the body state of the muscles. By monitoring this change through surface electromyographic signals, the changes in the muscles can be grasped in real time. The input electromyographic signal characteristic values ​​are classified through the fatigue discrimination model. At this time, if the muscles are fatigued, a fatigue reminder instruction is sent to the core chip. The core chip controls the electrical stimulation module to generate medium and low frequency pulse signals, and uses the electrical stimulation electrodes to release medium and low frequency pulse currents to relieve hand fatigue and effectively prevent muscle damage caused by excessive fatigue. At the same time, the buzzer will sound a reminder.

[0056] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A monitoring and physical therapy integrated e-sports glove, characterized in that: The glove comprises an elastic glove body, on which are arranged electromyographic acquisition electrodes, electrical stimulation electrodes, an embedded controller and a stretchable circuit. The electromyographic acquisition electrodes and the electrical stimulation electrodes are connected to the embedded controller via the stretchable circuit. The embedded controller comprises an electromyographic acquisition module, a transmission module, an electrical stimulation module and a core chip. The electromyographic signals of the user are collected in real time via the electromyographic acquisition module and the electromyographic acquisition electrodes, and the collected electromyographic signals are transmitted to a host computer via the transmission module. The fatigue state of the user is derived on the host computer according to a fatigue discrimination model. When muscle fatigue of the user is detected, the core chip controls the electrical stimulation module to emit electrical stimulation and performs electrical stimulation therapy via the electrical stimulation electrodes.

2. The monitoring and physical therapy integrated e-sports gloves according to claim 1, characterized in that: The embedded controller is a flexible circuit board, which is printed by a flexible printer and embedded in the glove to form a closed circuit with the flexible stretchable circuit.

3. The monitoring and physical therapy integrated e-sports gloves according to claim 1, characterized in that: The embedded controller also includes a buzzer. When muscle fatigue of the user is detected, the core chip controls the buzzer to remind the user that the hand has reached a fatigue state through the buzzer.

4. The monitoring and physical therapy integrated e-sports gloves according to claim 1, characterized in that: The electromyography acquisition module is used to collect electromyography signals from the muscle surface. After the electromyography acquisition electrodes collect the signals from the skin surface, they are amplified, filtered, and adjusted by the entire module circuit and then input into the core chip for processing. The electromyography acquisition module includes a pre-stage amplifier circuit, a high-pass filter circuit, a low-pass filter circuit, a post-stage amplifier circuit, and a voltage boost circuit.

5. The monitoring and physical therapy integrated e-sports gloves according to claim 1, characterized in that: The electrical stimulation module is used to generate stimulation current, including a Boost circuit and an electrical stimulation drive circuit. The Boost circuit achieves continuously adjustable boost by adjusting the duty cycle of the PWM wave, and then converts the PWM wave into a constant current electrical stimulation pulse through the electrical stimulation drive circuit, and then performs electrical stimulation through the electrical stimulation electrodes.

6. The monitoring and physical therapy integrated e-sports gloves according to claim 1, characterized in that: The host computer includes an electromyographic data preprocessing module, a time-frequency domain feature extraction module and a fatigue discrimination model. The collected electromyographic data are processed and feature extracted in the host computer, and then input into the fatigue discrimination model. The fatigue discrimination result is transmitted back to the core chip, and the core chip issues an electrical stimulation instruction.

7. The monitoring and physical therapy integrated e-sports gloves according to claim 6, characterized in that: The EMG data preprocessing module of the host computer performs denoising by using an empirical mode decomposition method.

8. The monitoring and physical therapy integrated e-sports gloves according to claim 6, characterized in that: The time-frequency domain feature extraction module of the host computer is used to extract features of the preprocessed electromyographic signals, wherein the time domain indicator selects to extract the electromyographic integral value iEMG, and the frequency domain indicator selects to extract the mean power frequency MPF. The feature extraction module uses a time domain and frequency domain joint analysis method to determine whether the muscles are fatigued based on the changing trends of the time domain features and the frequency domain features.

9. The monitoring and physical therapy integrated e-sports gloves according to claim 6, characterized in that: The fatigue discrimination model is used to discriminate fatigue status. After the extracted time domain and frequency domain features of the electromyographic signal are combined with subjective evaluation to mark the label, it is sent to Matlab to classify and train the data set using a support vector machine to obtain the fatigue discrimination model; the constructed fatigue discrimination model can judge whether the muscle is fatigued and the degree of fatigue through the input feature value, and transmit the result back to the core chip through the transmission module, thereby realizing real-time evaluation of the user's muscle fatigue level.

10. A signal processing method for monitoring an integrated physiotherapy e-sports glove, characterized in that: The method comprises the following steps: Acquire surface electromyographic signals of target muscle groups in real time; Preprocessing the collected surface electromyography signals; Perform feature extraction on the preprocessed surface electromyography signal to obtain the time domain features and frequency domain features of the surface electromyography signal; The time domain and frequency domain eigenvalues ​​of the surface electromyography signal are input into the trained fatigue discrimination model, and the current fatigue state of the muscle is output to achieve real-time monitoring of the muscle fatigue state.

Images