293 results about "Electromyography" patented technology

The invention provides an intelligent wearable rehabilitation monitoring and evaluation device after anterior cruciate ligament injury, and relates to the technical field of exercise rehabilitation and intelligent medical monitoring, the device comprises a sensor acquisition module, a signal processing module, a compensation determination module, a difference determination module and an evaluation analysis module, a force-electricity coupling flexible sensor, an IMU and a pressure sensor, the method comprises the following steps: synchronously collecting a muscle force signal, a surface electromyogram signal, an attitude signal and a plantar pressure signal at the same position, performing dynamic filtering, confidence enhancement and personalized compensation processing, extracting a difference feature vector, inputting the difference feature vector into a muscle force prediction model, and outputting a quantitative evaluation result. The portable wearable long-term dynamic monitoring is realized, the core indexes of muscles, joints and gaits are covered in multiple dimensions, the assessment is accurate and real-time, the rehabilitation scheme can be optimized, the risk of re-injury is reduced, and the rehabilitation effect and compliance of a patient are improved.

The invention discloses a general electromyographic signal processing method and system based on a large self-supervised model. The general electromyographic signal processing method comprises the following steps: step 1, acquiring a multi-source original multi-electrode channel EMG signal X from an electromyographic acquisition device; and finally, performing data unification processing, and finally converting into a space-time activity diagram with a fixed size of 224 * 224. On the basis of the space-time activity diagram and the fatigue state mark, constructing an AEMG for training according to heterogeneous unlabeled EMG data collected by a collection device; performing light-weight Adapter layer fine adjustment on the pre-trained large myoelectricity model to adapt to gesture recognition muscle force regression gait analysis or rehabilitation evaluation downstream tasks; aiming at the problem that the dimension and the structure of myoelectricity data are not matched due to different acquisition devices, acquisition parts and acquisition tasks, original signals are converted into space-time activity diagrams in a unified format through data unification processing, device differences are represented by combining a sensor embedding module, effective alignment of cross-source data is achieved, and the accuracy of the data is improved. And a basis is provided for large-scale data utilization.

A muscle probe is provided for obtaining electromyography data and optical spectroscopy data from muscle tissue. The muscle probe comprises an elongate needle having an outer wall surrounding a needle interior, the needle interior comprising: a core electromyography electrode; and one or more optical fibres; wherein the needle is arranged to be inserted into a muscle, and further arranged to detect electrical activity from the muscle; and wherein the one or more optical fibres are arranged to direct incident light from a light source toward a target area of the muscle, and further arranged to receive scattered light from the target area. The present disclosure aims to provide a muscle probe to improve the diagnostic pathway for patients with neuromuscular disorders, by developing a minimally invasive bedside test of muscle health.

The invention relates to the field of medical instruments, in particular to a percutaneous microflow acupuncture system closed-loop regulation and control method and system based on multi-channel acupoint impedance, and the method comprises the steps: obtaining a first surface electromyogram signal in a human body action period, and constructing a relation between an action behavior and surface electromyogram; determining a multi-channel implementation path of the percutaneous microflow acupuncture system according to the relationship; impedance characteristics of acupuncture points along the multi-channel implementation path are obtained, and percutaneous microflow electrical stimulation operation is set according to the impedance characteristics; acquiring a second surface electromyogram signal during the implementation of the electrical stimulation operation, and adjusting the electrical stimulation operation according to the first surface electromyogram signal and the second surface electromyogram signal; and acquiring a response signal for adjusting the multi-channel implementation path association region during the implementation of the electrical stimulation operation so as to change the multi-channel electrical stimulation mode. According to the invention, path calibration of multiple acupoint associated stimulation areas is implemented through multiple channels, feedback closed-loop stimulation regulation is formed by combining acupoint impedance and electromyographic signals formed during stimulation, and the stimulation efficiency is improved.

The invention relates to the technical field of nervous system dysfunction, in particular to a nerve regulation and control system for degenerative disease treatment based on multi-modal physiological feedback, which comprises a central processing unit, an optical radiation applicator, a mechanical vibration applicator, an integrated biological signal sensing array and a man-machine interaction module, cooperative stimulation is applied by using a multispectral light source and a broadband vibrator, and multi-dimensional physiological signals such as heart rate variability, myoelectricity, galvanic skin and the like are monitored in real time through a sensor array. A multi-parameter adaptive control algorithm built in the central processing unit can dynamically and intelligently adjust stimulation parameters based on the feedback signals to form an accurate personalized treatment closed loop. Meanwhile, the safety monitoring module based on the biological thermal model ensures the safety boundary of the treatment process. According to the invention, intelligent, self-adaptive and non-invasive treatment of nerve dysfunction is realized.

The invention discloses a sign language-voice conversion system, and belongs to the technical field of auxiliary communication and wearable computing. The system comprises a wearable myoelectricity acquisition module used for acquiring double-arm myoelectricity signals when a user executes sign language; the mobile terminal module is wirelessly connected with the acquisition module and is used for receiving and preprocessing the signal and uploading the signal; the cloud processing module is used for receiving the signal, converting the signal into text information through a sign language recognition model, and further calling a voice synthesis service to convert the text into voice data; and the wearable audio output module is used for receiving and playing the voice data. Through an innovative end-to-end hardware system architecture, natural, accurate and real-time translation and voice output of sign language gestures are realized, communication barriers between hearing-impaired people and healthy hearing people are effectively solved, and the system has the advantages of flexible deployment, user friendliness and privacy protection.

The invention discloses a lower limb exoskeleton robot layered cooperative walking aid control method. The method comprises the steps of data acquisition and preprocessing; human-machine coupling dynamics modeling is carried out, and required moments tau < hip >, tau < knee > and tau < ankle > of the hip joint, the knee joint and the ankle joint are obtained; low-layer joint control, including hip joint moment, knee / ankle virtual impedance moment and friction compensation calculation; middle-layer multi-axis cooperation and gait phase judgment; high-rise energy is optimally distributed, assistance is distributed to three joints in a phase and a safety boundary, meanwhile, the requirements for labor saving and stability are considered, a minimization problem is written in a unified mode, J serves as the total amount, and torque of the hip joint, torque of the knee joint and torque of the ankle joint are solved in a combined mode; according to the step-by-step self-adaption of myoelectricity driving, in order to cope with human body fatigue changes, step-by-step updating is carried out on the virtual stiffness within the movement distance. The method has the advantages of improving man-machine cooperation level, man-machine adaptability and walking aid efficiency.

A device for functional electrical stimulation (FES), neuromuscular electrical stimulation (NMES), and / or in receiving electromyography (EMG) signals includes a sleeve and electrodes. The sleeve is sized and shaped to be worn on a human arm, and comprises a stretchable fabric The sleeve has a distal end disposed on or adjacent a wrist of the human arm when the sleeve is worn on the human arm and a proximal end opposite from the distal end. The electrodes are secured with the sleeve and positioned to contact skin of the human arm when the sleeve is worn on the human arm. The sleeve may include an inner sleeve contact with the skin and an outer sleeve disposed over the inner sleeve. The inner sleeve has openings in which the electrodes are disposed.

The application provides a real-time closed-loop adaptive airway pressure regulating system. The system comprises a respirator mask and a host computer; the respirator mask is provided with an airflow monitoring module, a pressure monitoring module, a snore monitoring module, a lower jaw electromyography monitoring module, a forehead transcutaneous carbon dioxide sensing module and a preprocessing module; the host computer is internally provided with an intelligent module; the preprocessing module pre-processes airflow velocity, pressure data, airway vibration signals, electrical signals corresponding to lower jaw and pharyngeal muscle activity and carbon dioxide content measured by the airflow monitoring module, the pressure monitoring module, the snore monitoring module, the lower jaw electromyography monitoring module and the forehead transcutaneous carbon dioxide sensing module in real time; the intelligent module identifies a risk window period of airway collapse of a user in real time according to the pre-processed data and performs adaptive pressure boosting control on the pressure in the airway of the patient after identification. The application reduces the misjudgment rate of newly occurring CSA events of complex sleep apnea after OSA relief.

The invention provides a nerve regulation and control system and method for a spinal cord ventral epidural region, and the system employs a microprocessor to generate multiple paths of pulse width modulation signals, and drives a voltage-controlled current source after amplitude adjustment. Stimulation current with adjustable frequency, pulse width and amplitude is output to act on a spinal cord ventral nerve structure. Real-time monitoring of stimulation current of each channel is realized through combination of voltage sampling and a single-pole multi-throw analog switch, feedback information of a body position, myoelectricity, pressure and other multi-mode sensors is fused, a closed-loop control mechanism is constructed, and dynamic adjustment and individualized optimization of electrical stimulation parameters are realized. The system has the advantages of being more accurate in electrical stimulation positioning, more sensitive in response, more intelligent in control and the like, and is suitable for intelligent rehabilitation intervention in scenes of spinal cord injury, cerebral palsy, neurological dysfunction and the like.

The invention discloses an obstructive sleep apnea event typing method and device based on respiratory center driving characteristics, electronic equipment and a computer readable storage medium, and belongs to the technical field of medical detection technologies and sleep medicine. According to the method, body surface diaphragm electromyographic signals and respiratory airflow signals of a subject are synchronously collected in a non-invasive mode, the body surface diaphragm electromyographic signals are preprocessed to obtain diaphragm electromyographic characteristic values, and the respiratory airflow signals are segmented and subjected to integral processing according to the respiratory cycle to obtain airflow characteristic values; selecting a characteristic value corresponding to at least one respiratory cycle before the event occurs as a reference baseline, calculating a diaphragm myoelectricity change value and an airflow change value of each respiratory cycle in the event relative to the reference baseline, and calculating the diaphragm myoelectricity change value based on a coupling relationship between the airflow change value and the diaphragm myoelectricity change value, and performing central drive dependent or non-central drive dependent judgment on the obstructive sleep apnea event. The method can provide technical support for typing analysis of the obstructive sleep apnea event.

The invention discloses an orthopedic surgery navigation drilling and implant placement intention real-time optimization method based on multi-modal perception, and relates to the technical field of computer-aided surgery, man-machine interaction and intelligent medical equipment. Multi-modal signals such as electroencephalogram, eye movement and myoelectricity of a doctor are collected in real time through XR glasses and an intelligent surgical drill; and inputting the pre-trained micro-world model to generate a current intention vector and predict a future bone structure trajectory. The intention level is judged by calculating the energy distance between the intention and the master template and an emotional value function: when the intention meets the master level condition, the system automatically generates an XR green optimal path and assists in operation; and when the intention is identified as the risk intention, triggering the skykeeper system to lock the equipment and send out an alarm. The system supports a data federation learning evolutionary model, and immediately destroys an original multi-mode signal after encoding to guarantee data security. According to the invention, the real-time monitoring, evaluation and guidance of the operation intention are realized, and the accuracy and safety of the operation are improved.

The invention discloses a lower limb muscle force deep learning model evaluation method based on high-density electromyographic signals. The method comprises the steps that S1, the lower limb electromyographic signals of a human body are obtained through wearable monitoring equipment and converted into discharge time sequence data; s2, a deep learning hybrid model containing a convolutional neural network CNN and a recurrent neural network LSTM is constructed, a lower limb muscle strength sample database is constructed, the lower limb muscle strength sample database comprises lower limb muscle strength sample data and corresponding lower limb muscle strength label data, and the deep learning hybrid model performs model training by using the lower limb muscle strength sample database; and S3, obtaining discharge time sequence data of a to-be-detected human body, inputting the trained deep learning hybrid model, and outputting lower limb muscle force data of the to-be-detected human body. The lower limb muscle strength data and the lower limb muscle strength level can be accurately predicted and evaluated by acquiring the lower limb muscle electric signals in a contact non-destructive mode, and level-stage quantitative evaluation can be conveniently carried out in clinical diagnosis and rehabilitation training.

The present application relates to the technical field of sleep promotion, in particular to a sleep auxiliary device for relieving arthralgia, comprising a binding part worn on the joint position of a patient, the surface of the binding part is provided with a plurality of multi-modal stimulation mechanisms for mechanically stimulating the joint acupoints; the auxiliary device further comprises a power source, a gyroscope, a surface electromyography sensor and a heart rate sensor; the power source provides stimulation power for the plurality of multi-modal stimulation mechanisms; the multi-modal stimulation mechanism comprises a shell with an open bottom, a pressing device arranged in the shell and a bionic massage device; the pressing device is used for pressing the joint acupoints; the bionic massage device is in transmission connection with the pressing device and is used for driving the pressing surface of the pressing device to swing. The device can automatically switch between the two modes of soft pressing and active pressing and rubbing according to the sleep and wake state information of the patient, relieve arthralgia, significantly reduce the interference to the sleep process and effectively improve the sleep continuity and quality of the patient.

The invention relates to the technical field of automobile collision safety, and discloses a passenger posture prediction method and system based on active safety early warning, and the method comprises the steps: synchronously collecting vehicle dynamics data, passenger target muscle group surface electromyogram signals and kinematics states under a simulated or real AEB working condition; after preprocessing the data, constructing a myoelectricity-attitude prediction model by using a CNN and LSTM hybrid model; training the model by using a large amount of data to learn the internal relationship between the characteristics and the passenger kinematics state change, and predicting the kinematics state of each section of the passenger body at the collision moment; acquiring a vehicle deceleration curve, inputting characteristics to predict the posture of a passenger, converting into a simulation software instruction to complete initialization of a virtual dummy, and running collision simulation; the problem that the initial position of a traditional collision simulation model cannot reflect the actual posture of a passenger under the emergency braking working condition, and consequently data difference is large is solved.

This application discloses an exoskeleton position prediction and closed-loop stepper control system and method. The microcontroller unit completes the functions of electromyography (EMG) signal acquisition, neural network inference, pulse generation, and closed-loop correction. The EMG signal acquisition unit acquires surface EMG signals, performs preprocessing and feature extraction, and outputs digital EMG features. The motor position feedback unit acquires the absolute position and velocity information of the closed-loop stepper motor in real time. The neural network operation unit concatenates the digital EMG features and the absolute position and velocity information of the closed-loop stepper motor into a multi-dimensional input vector to predict the three-dimensional spatial position increment of the exoskeleton at the next moment. The dual closed-loop control unit converts the predicted value of the three-dimensional spatial position increment into stepper motor control commands and performs closed-loop correction in combination with the real-time position of the motor. Zero-delay tracking control is achieved through a predictive-execution parallel pipeline, realizing high-precision, low-delay tracking of exoskeleton movement and achieving high system integration and lightweight design.

The invention discloses a teenager scoliosis eight-section brocade guide massage system and a personalized training method, and relates to the technical field of medical rehabilitation. The system comprises a lateral bending parting evaluation module which measures a Cobb angle and a centrum rotation angle through a 3D spine scanner and detects a muscle tension difference through a surface myoelectricity collector; the eight-section brocade improved action library is used for storing asymmetric improved actions aiming at a right chest bend, a left waist bend and an S-shaped bend, the action angle of the concave side is increased by 5-30 degrees, and the action angle of the convex side is correspondingly reduced; the directional massage auxiliary unit is provided with a pressure silicon controlled rubber massage head, the convex side is released by adopting an 8-10 Newton rolling method, and the concave side is activated by adopting a 3-5 Newton point pressing method; and the intelligent motion correction module monitors spinal motion in real time through five inertial measurement units, and provides voice vibration feedback when the deviation exceeds a threshold value. The training method adopts a progressive scheme, is implemented in stages according to the size of a Cobb angle, and comprehensively intervenes through'massage release-guide correction-acupoint activation '.

This invention discloses a spline-adaptive method for eliminating power frequency interference in surface electromyography (EMG) signals, within the field of EMG signal noise reduction technology. The method includes the following steps: frequency domain input vector generation and frequency domain spline adaptive filtering; power frequency interference elimination; construction of a semi-quadratic criterion cost function and filter coefficient update; iterative update, repeating the above steps until noise reduction is complete. This spline-adaptive method for eliminating power frequency interference in EMG signals employs a robust frequency domain implementation method to construct the spline adaptive noise reduction system, exhibiting good stability, high computational efficiency, and the ability to efficiently eliminate power frequency interference.

The invention relates to the technical field of rehabilitation physiological monitoring, and discloses a nerve-muscle recovery detection method based on HRV recovery rate and sEMG frequency spectrum declination, and the method comprises the steps: firstly obtaining an effective RR interval sequence subjected to quality gating and a steady state sEMG segment of a specific muscle group; then, extracting systemic HRV recovery features and local muscle fatigue features in parallel, and respectively generating a normalized HRV recovery rate score and a myoelectricity recovery score; through multi-level fusion, a global nerve recovery score, a local muscle recovery score array and a comprehensive nerve-muscle recovery score are integrated; and finally, based on the multi-dimensional evaluation results, generating personalized training suggestions. Therefore, the nerve-muscle system preparation degree of an individual can be comprehensively and accurately reflected, and a scientific basis is provided for optimizing a training plan and preventing sport injuries.

The invention discloses an exoskeleton device control method and system for ground wire hooking. Multi-modal features are extracted from surface electromyogram signals, kinematics data and mechanics data, and the motion intention of an operator is recognized in real time. And according to the identified motion intention, main motion and micro-jitter motion are extracted, and a stage reference trajectory of the exoskeleton is generated according to superposition of the task stage and the target state. Thirdly, a cost function is defined to optimize trajectory planning, and trajectory tracking precision, execution energy consumption and obstacle avoidance cost are considered; and on the basis of the collaborative motion trail and real-time feedback of an operator, the needed power-assisted torque is calculated, and impedance parameters are adjusted in a self-adaptive mode according to the power-assisted requirement, errors and confidence coefficients. And finally, according to the deviation between the contact force error and the target force, the total output torque of the exoskeleton joint is generated. By adjusting the control strategy and assisting power output in real time, the response precision and comfort of the exoskeleton device are improved, and motion control and energy efficiency are optimized.

This invention provides a physiotherapy system for pelvic floor function rehabilitation in cervical cancer patients, relating to the field of pelvic floor physiotherapy. The system includes: a data acquisition module for acquiring pelvic floor electromyography (EMG) and ultrasound data from multiple historical patients; a data analysis module for constructing an EMG atlas and an EMG-factor correlation atlas based on the aforementioned data; the data acquisition module is also used to acquire the current patient's pelvic floor EMG data based on the EMG atlas, and to acquire the current patient's pelvic floor ultrasound data based on the current patient's pelvic floor EMG data and the EMG-factor correlation atlas; a treatment plan determination module for determining the current patient's physiotherapy plan based on the current patient's pelvic floor EMG and ultrasound data; and a physiotherapy execution module for controlling the physiotherapy equipment to perform pelvic floor function rehabilitation physiotherapy based on the current patient's physiotherapy plan, thereby improving the flexibility and effectiveness of pelvic floor function rehabilitation physiotherapy for cervical cancer patients.

The invention relates to the technical field of medical auxiliary diagnosis, and particularly discloses an auxiliary diagnosis method for multifocal motor neuropathy and peingshan disease, which comprises the following steps: step S100: performing electromyogram detection, serological examination and muscle biopsy on an examined object to obtain electromyogram signal data, serological examination result data and muscle biopsy result data; s200, performing feature extraction on the electromyogram signal data, the serological examination result data and the muscle biopsy result data, and combining the extracted features to form a feature vector; step S300, obtaining output classification probabilities, wherein the classification probabilities correspond to the multi-focus motor neuropathy and the Pingshan disease, and excluding three categories of the multi-focus motor neuropathy and the Pingshan disease; electromyogram signals, serological examination and muscle biopsy multi-source data are fused to extract core features, a classification model is constructed by using a random forest or XGBoost algorithm, and the automation and standard unification of the whole diagnosis process are realized.

A method and system for monitoring postpartum hemorrhage (PPH) of a patient is configured to: receive PPH factor information for the patient, wherein the PPH factor information includes at least two of: ultrasound data generated based on one or more abdominal ultrasound images of the patient obtained during a measurement period; electromyogram (EMG) data obtained from abdominal electrodes on the patient during the measurement period; cardiac measurement data obtained from the patient during the measurement period; and a uterine health indicator of the patient. The system and method are configured to process the PPH factor information to determine a PPH probability index and a PPH severity index, the PPH probability index indicating a probability that the patient will develop PPH, the PPH severity index predicting a severity of PPH; and generating a PPH risk index for the measurement period based on the PPH probability index and the PPH severity index.

This invention provides a real-time identity recognition method, device, and electronic device based on electromyography (EMG) signals. The real-time identity recognition method includes: acquiring a target EMG signal characterizing limb movement from collected raw EMG signals; determining the target time-frequency features of the target EMG signal; and performing recognition processing on the target time-frequency features based on a preset convolutional neural network to obtain target identity information. Using this method, a terminal device can receive raw EMG signals collected by an EMG wristband in real time and perform time-frequency feature extraction and identity recognition processing on the received raw EMG signals, thereby achieving the goal of real-time identity recognition based on EMG signals and improving the recognition rate of identity information while meeting real-time requirements.

This invention discloses a pneumatic hand rehabilitation system and method, comprising: in a model calibration phase, collecting multi-channel surface electromyography (EMG) signals generated by the forearm of the target patient when performing different hand gestures, and constructing coarse and fine classifier training sets; training multiple heterogeneous classification models using the coarse and fine classifier training sets respectively, and selecting the optimal coarse and fine classifiers; in a rehabilitation training phase, collecting multi-channel EMG signals generated by the forearm of the target patient in real time, calling the trained coarse and fine classifiers for two-stage hierarchical decoding, and outputting motion control commands; a pneumatic execution module parsing the motion control commands and driving the air bladder deformation of the pneumatic rehabilitation glove to drive the patient's hand to complete the corresponding rehabilitation movements. This invention can significantly improve individual adaptability, multi-finger recognition accuracy, and control stability under different physiological characteristics of patients and complex fine motor scenarios.

The invention discloses a real-time monitoring-based implant operation pain self-adaptive regulation and control method and system, and belongs to the field of biomedical engineering. The method comprises the following steps: establishing a tooth position-myoelectricity mapping relation according to an implant tooth position, and deploying bilateral myoelectricity electrodes to establish an individualized myoelectricity baseline; event-related myoelectricity response and skin conductance response are calculated, and pain side positioning is carried out; evaluating the anxiety level, and quantifying and correcting the pain intensity; based on the corrected pain intensity index and anxiety level index, performing state comprehensive judgment by adopting fuzzy logic; self-adaptive regulation and control including cognitive intervention, physical intervention, drug intervention and joint regulation and control are executed according to the state judgment result, and hierarchical upgrading is carried out according to the regulation and control effect. According to the invention, scientific distinguishing between pain and anxiety, accurate positioning of pain side identification and closed-loop self-adaptive regulation and control are realized.

1. Name of the product in this design: Electromyography Evoked Potential Instrument. 2. Purpose of this design: To determine the functional status and suspected lesions of the peripheral neuromuscular system and central nervous system, detect subclinical lesions, and accurately locate lesions. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model. 5. The bottom surface of this product is a part that is not easily seen or cannot be seen during use, so the bottom view is omitted.

The invention discloses a physical training load regulation and control method and system based on self-adaptive physiological coupling, and the method comprises the steps: collecting an electrocardiosignal, a light volume pulse signal, a respiration signal, a surface electromyographic signal and a body surface temperature signal, and generating a multimode sequence with a time mark; self-adaptive time alignment is executed, a timestamp graph is constructed, clock drift estimation is carried out, segmented monotonic reversible time transformation is established, and a multimode sequence is mapped to a unified time axis; reconstructing the missing section and the artifact section, establishing a mask auto-encoder with physiological priori constraints, combining time domain consistency constraints and frequency domain consistency constraints, and outputting a continuous differentiable reconstructed sequence. According to the method, by introducing adaptive time alignment, cross-modal signal reconstruction and dual-time scale state modeling, coordinated recognition and dynamic load regulation and control of multi-source physiological signals are achieved, coupling analysis in the training process is more stable, and an individual model can be continuously and adaptively updated.

A device control system applied to intelligent clothes comprises a clothes body, a main control device arranged on the clothes body and a sensing device, the sensing device comprises an inertia sensor, a myoelectricity sensor and a myoelectricity stimulation device, the sensing device can generate inertia sensing information and myoelectricity sensing information, and the inertia sensing information and the myoelectricity sensing information are transmitted to the main control device. The main control device can continuously transmit packet information to the sensing device and start the electromyographic stimulation device to discharge according to a discharge instruction, the sensing device judges whether the discharge instruction is not received for a plurality of continuous periods, and if the discharge instruction is not received for a plurality of continuous periods, the electromyographic stimulation device starts the electromyographic stimulation device to discharge the electromyographic stimulation device, the electromyographic stimulation device starts the electromyographic stimulation device to discharge the electromyographic stimulation device, and the electromyographic stimulation device starts the electromyographic stimulation device to discharge the electromyographic stimulation device. If yes, the action of the electromyographic stimulation device is forcibly stopped.

The application provides a high-density surface electromyography signal hardware filtering device and method based on FPGA, comprising: an sEMG signal input module for collecting multi-channel noisy surface electromyography signals and at least one reference noise signal; an LMS adaptive filtering calculation module for receiving the noisy surface electromyography signals and the reference noise signal, adopting a fixed-point number operation system and executing an LMS adaptive filtering algorithm through a parallel pipeline structure to output a filtered error signal; a data buffer and output interface module for buffering and outputting the filtered surface electromyography signals; and an FPGA main control module connected with the sEMG signal input module, the LMS adaptive filtering calculation module and the data buffer and output interface module for controlling the work of each module. The application realizes the LMS adaptive filtering algorithm on the FPGA platform, and solves the problems of insufficient real-time performance and large processing delay of software filtering when facing high-density multi-channel sEMG signal processing.