68 results about "Muscle activation" patented technology

The invention discloses an anti-resistance exercise training system for old people based on intelligent wearable equipment, and relates to the technical field. The problems that in the prior art, a dynamic action monitoring error correction mechanism is lacked, exercise intensity adjustment is not personalized and real-time, interaction and data feedback functions do not exist, and equipment portability and wearing adaptability are insufficient are solved. The system collects data in real time through the whole body position intelligent wearable device, corrects non-standard actions through the action recognition feedback module, dynamically regulates the intensity through the exercise intensity evaluation module, reduces the risks of muscle strain, cardiovascular burden and the like, takes standardized action guidance, personalized intensity adaptation and data visualization as the core, ensures target muscle activation, and improves the training efficiency. The training effect is quantified, the operation is simple, the use threshold is reduced through voice guidance, the boring feeling is relieved through personalized plans and summary reports, the training achievement feeling and compliance of the old people are enhanced, the muscle strength can be improved through whole body position training, and the anti-resistance exercise requirement of the old people is met.

The invention discloses an elbow joint rehabilitation training evaluation method and system, and the method comprises the following steps: S1, collecting multi-cycle motion data and surface myoelectricity data when a patient executes a specified rehabilitation motion in a standard state through an inertia measurement unit and a surface myoelectricity sensor which are disposed on the upper limb of the patient, based on this data, establishing a personal motion baseline template comprising a standard angle-time curve and a standard muscle activation level; s2, in the rehabilitation training process, motion data and surface myoelectricity data are collected in real time, and the following operations are executed: S21, a joint motion range and a motion smoothness index are extracted from the motion data; s22, muscle activation intensity and collaborative shrinkage are extracted from the surface myoelectricity data; according to the method, individuation of evaluation standards, diversification of monitoring dimensions and dynamic weight adjustment are achieved, the accuracy and safety of rehabilitation training can be effectively improved, and the method has important clinical application value.

The invention relates to the technical field of rehabilitation medical treatment, in particular to a hand rehabilitation training system based on virtual reality and gesture interaction, and the system comprises a gesture sensing module which collects a hand movement track, a muscle electric signal, grip pressure and a joint movement angle; the VR rehabilitation scene construction module constructs a rehabilitation training virtual scene, simulates a hand interaction behavior and a force feedback effect through an adaptive physical engine and a neural action mapping algorithm, and outputs simulation data; the intelligent evaluation center evaluates the action standard degree and the muscle activation efficiency based on an improved CNN-GRU model, identifies an action compensation mode and abnormal force generation, and outputs an evaluation report; the interactive training unit renders a motion state and a training process in real time, and generates personalized training guidance in combination with voice, visual and tactile prompts; and the personalized regulation and control unit predicts a rehabilitation trend and a stage target through a reinforcement learning algorithm, and dynamically adjusts training parameters and scene difficulty. Therefore, the problems of low interaction precision, incapability of sharing and the like in the prior art are solved.

The present disclosure describes devices, methods and systems for modifying or altering gait kinematics via sensory augmentation and / or modifying muscle activation patterns via augmented motor learning to slow the progression of and / or reduce the pain associated with knee OA, particularly during gait (e.g., walking, running, stair climbing, etc.). Sensors can be used to measure gait parameters and characteristics and muscle activation patterns. Stimulation can be provided to the individual in order to promote learning new gait kinematics and muscle activation patterns.

The invention relates to a closed-loop control method suitable for personalized lower limb exercise training, belongs to the technical field of exercise rehabilitation, and designs a closed-loop control method for dynamically adjusting lower limb training load according to muscle activation degree by combining surface myoelectricity characteristics with a personalized training model and a closed-loop control algorithm. According to the method, the resistance load can be adjusted in real time according to the muscle state, and finally the muscle activation level in the training process is maintained in an expected range. In the pre-training stage, sEMG data are collected to establish a personalized mapping model, and response characteristics of individual muscles are quantified; in the formal training stage, the muscle state is monitored in real time, the reference load is predicted through the model, and a closed-loop control algorithm is adopted to generate dynamic adjustment amount to adjust resistance output in real time. The invention further provides a closed-loop control system suitable for personalized lower limb exercise training.

Techniques for cuffless blood pressure monitoring with multiparameter correction are described and are implementable to reduce measurement inaccuracies in wearable cuffless blood pressure devices. In an example, a wearable device includes a sensor arrangement to collect physiological timing data indicative of a pulse propagation time along a cardiovascular pathway and a correction sensor that is configured to measure a correction parameter that impacts the pulse propagation time independent of a corresponding change to blood pressure, such as body temperature, skin temperature, perfusion index, hydration level, or muscle activation.  A processor of the wearable device is configured to process the physiological timing data to determine the pulse propagation time and generate a blood pressure measurement based on the pulse propagation time and measurements of the correction parameter.  Accordingly, the techniques described herein generate blood pressure measurements that account for physiological variables that have an independent impact on pulse propagation characteristics.

The application discloses a dual-arm robot autonomous control system and method based on remote operation and visual features, comprising a remote operation acquisition module, a multi-view visual perception module, a data synchronization and demonstration acquisition module, a strategy model training module, an autonomous strategy execution module, a trajectory deviation detection and takeover module and a hybrid control interface module. The application completes human demonstration through remote operation, and acquires multi-modal information such as images, trajectories, grippers and muscle activations. The perception features are fused by using multi-view space-time alignment and cross-view attention mechanism, and strategy learning is completed in combination with an end-to-end large model. In the autonomous operation stage, the risk of current operation is evaluated through trajectory deviation detection and collision probability prediction, the autonomous control proportion is dynamically adjusted, manual intervention is allowed when necessary, the safety and stability of the overall system are improved, a robot control mode of seamless switching of human-machine cooperation, autonomy and remote operation is realized, and the application is suitable for object operation tasks in complex and high-variable environments.

The invention discloses an artificial shoulder joint prosthesis design method and system, and the method comprises the steps: collecting the motion trail and muscle activation state of a shoulder joint in different motion modes, separating the feature frequency and amplitude of the shoulder joint motion, and extracting a dynamic motion feature set of the shoulder joint; inputting the dynamic motion feature set into a contact mechanical model based on a discrete element method, and simulating contact force and friction behaviors between the shoulder joint prosthesis and the skeleton to obtain contact mechanical characteristics of the prosthesis and the skeleton; and according to the contact mechanical characteristics, generating an initial structure of the prosthesis by using a topological optimization algorithm based on a generative adversarial network, generating a prosthesis topological structure with gradient material distribution, and obtaining an optimized prosthesis design scheme. By utilizing the embodiment of the invention, a prosthesis design scheme with gradient material distribution can be generated, the weight of the prosthesis is reduced, and the strength and durability of the prosthesis are enhanced.

Introduced here are computer-implemented platforms (also referred to as "muscle activation platforms") that are able to determine activated muscles of individuals performing physical activities. By predicting activated muscles, the muscle activation platforms are able to more accurately determine whether the individuals are performing the physical activities correctly.

This application relates to the fields of biomedical engineering and rehabilitation engineering technology, and discloses a functional electrical stimulation method and system based on physiological simulation and adaptive closed-loop feedback. The method includes: calculating an ideal muscle activation curve based on a target trajectory; performing spatiotemporal asynchronous co-coding to generate a biomimetic stimulation pulse sequence by simulating temporal asynchrony, spatial and intensity modulation, and multi-muscle synergistic timing; simultaneously applying stimulation while monitoring the actual kinematic state and muscle physiological state in real time using sensors; and dynamically adjusting the internal parameters of the spatiotemporal asynchronous co-coding (T-S-C coding) based on the evaluation results of trajectory error and fatigue index to form an adaptive closed loop. This application, by combining biomimetic coding with an intelligent closed loop, fundamentally solves the problems of motion stiffness, muscle fatigue, and poor control precision caused by traditional FES, achieving smooth, sustained, and precise personalized motor function rehabilitation.

The invention belongs to the technical field of underwater bionic robots, and particularly relates to a bionic duty ratio gait control method for an elastic robotic fish, a program, equipment and a storage medium. According to the method, improvement is carried out based on a traditional Hopf oscillator, a CPG oscillator simulating a red muscle activation mode of fish is constructed, a CPG network model based on an improved Hopf central pattern generator is constructed according to the structure of the elastic robotic fish, and actuator control mapping is completed; and a PID-CPG closed-loop controller is constructed, and the actual maximum angle of each joint gradually approaches the maximum angle expected value through continuous iteration of the motion period. The universal gait control method of the bionic robotic fish is constructed according to the physiological characteristics of fish red muscle activation, the power consumption of the elastic robotic fish can be effectively reduced, and the efficiency can be improved.

The invention relates to the technical field of biomedical engineering and rehabilitation engineering, and discloses a functional electrical stimulation method and system based on physiological simulation and adaptive closed-loop feedback. The method comprises the following steps: calculating an ideal muscle activation curve based on a target trajectory; space-time asynchronous cooperative coding is executed, and a bionic stimulation pulse sequence is generated by simulating time asynchronism, space and intensity modulation and a multi-muscle cooperative time sequence; when stimulation is applied, the actual kinematics state and the muscle physiology state are monitored in real time through a sensor; and dynamically adjusting the internal parameters of the time-space asynchronous cooperative coding (T-S-C coding) based on the evaluation results of the trajectory error and the fatigue index to form a self-adaptive closed loop. According to the method, bionic coding and intelligent closed loop are combined, so that the problems of stiff movement, easy fatigue of muscles and poor control precision caused by traditional FES are fundamentally solved, and smooth, lasting and accurate personalized movement function rehabilitation is realized.

The invention discloses a gait muscle force and activation real-time prediction method based on a physical constraint model, and belongs to the technical field of sports biomechanics and artificial intelligence. The method comprises the following steps: 1, inputting only hip, knee and ankle joint angles as input data; 2, a model backbone is a Transform; 3, multi-task loss constraint model training; 4, adjusting model parameters; and 5, calculating muscle activation. According to the invention, force and activation of multiple muscles can be output in real time only by inputting a joint angle sequence; the joint moment constraint is added in the loss, so that the prediction meets the biomechanical law, the precision, robustness and interpretability are considered, the traditional static optimization or dynamic optimization method can be replaced, and the process can be carried out in multiple scenes.

The invention discloses a multi-modal-based immersive self-adaptive treadmill rehabilitation training method and system, and the method comprises the steps: constructing a multi-modal synchronous data stream through synchronously collecting real-time posture data, surface electromyogram signals and treadmill state data of a user; further analyzing the gait quality, muscle activation and interaction state of the user in real time, and generating a multi-dimensional state vector; based on a preset self-adaptive strategy table, the state vector is compared with an expected threshold value of the current training stage, and a cooperative adjustment instruction aiming at the speed / gradient of the treadmill, the dynamic characteristics of the virtual scene and audio feedback is generated through intelligent decision; finally, closed-loop self-adaptive control is formed through multi-channel real-time feedback execution, and the training stage is automatically transited when conditions are met. According to the method, deep interaction and self-adaptive linkage of the physical training environment and the virtual immersion scene are realized, safer and more personalized rehabilitation training experience rich in sense of participation can be provided, and the accuracy and effect of rehabilitation training are effectively improved.

This invention relates to the field of lower limb rehabilitation data recognition and monitoring technology, specifically disclosing a method for recognizing lower limb rehabilitation movement postures and an intelligent ankle bracelet for preventing VTE, comprising: Step 1, real-time acquisition of three-dimensional spatial motion data and recognition of lower limb motion data, extracting kinematic parameter features; Step 2, identification of movement types based on kinematic parameter features, acquisition of movement pattern consistency scores, and determination of whether rehabilitation training is qualified; Step 3, acquisition of surface electromyographic signals of the rehabilitation participant's leg-raising force exertion movement during rehabilitation training and simultaneous acquisition of lower limb motion data, extraction of force exertion data, evaluation and analysis to generate a muscle activation efficiency score; Step 4, establishment of a mapping model based on historical hemodynamic data, inputting the extracted force exertion data into the mapping model to output a VTE prevention efficiency score; Step 5, calculation of the movement pattern consistency score, muscle activation efficiency score, and VTE prevention efficiency score through movement evaluation analysis to generate a movement evaluation quality coefficient.

Embodiments of the present disclosure relate to the technical field of biomedical engineering, and provide a movement assistance method, device and apparatus, an electronic device, and a storage medium. The method comprises: acquiring, in real time, target foot features of a subject based on a current activity type, wherein the target foot features comprise: a plurality of target foot actions and moments corresponding to the target foot actions; on the basis of a preset movement relationship feature model, determining a first correspondence describing a target foot action and the current activity type as a target correspondence, and determining a target waiting duration, a target auxiliary muscle group, and a target stimulation duration described in the target correspondence; and determining a stimulation moment on the basis of a moment corresponding to the target foot action and the target waiting duration, and assisting muscle activation of the subject by providing, at the stimulation moment, a stimulation signal of which the duration is the target stimulation duration to the target auxiliary muscle group, thereby achieving movement assistance.

This invention discloses a method for analyzing upper limb surface electromyography (sEMG) signals by integrating deep and wide learning, belonging to the field of upper limb surface EMG signal analysis technology. The method includes the following steps: acquiring multi-channel EMG signals to establish a complete sEMG dataset; designing the same number of convolutional neural network branches with residual structures for the acquired multi-channel sEMG signals; inputting the output features of the residual convolutional neural network structure of each channel into its respective wide learning sub-model; calculating weights through pseudo-inverse regression; obtaining a contribution index by normalizing the absolute value; stabilizing the contribution index through cross-validation; analyzing the muscle activation weights corresponding to upper limb movements; and validating the representation of muscle activation degree. This achieves the collaborative extraction of multi-channel muscle features and the quantification of muscle activation contribution, thereby solving the problem of insufficient representation ability of traditional muscle co-activation indices for the real neuromuscular control process, and realizing high-precision, interpretable quantification of muscle co-activation relationships.

The present application belongs to the technical field of underwater bionic robots, and particularly relates to a bionic duty cycle gait control method for an elastic robotic fish, a program, an equipment and a storage medium. The present application is improved based on a traditional Hopf oscillator, a CPG oscillator simulating the red muscle activation mode of fish is constructed, a CPG network model based on the improved Hopf central pattern generator is constructed according to the structure of the elastic robotic fish, and actuator control mapping is completed; a proportional-integral-derivative (PID) CPG closed-loop controller is constructed, and through continuous iteration of the motion cycle, the actual maximum angle of each joint gradually approaches the maximum angle expected value. According to the physiological characteristics of the red muscle activation of fish, the present application constructs a general gait control method for bionic robotic fish, which can effectively reduce the power consumption of the elastic robotic fish and improve the efficiency.

A muscle activation detection device includes: a first sEMG (surface electromyogram) sensor configured to receive a first sEMG signal associated with a user; a second sEMG sensor configured to receive a second sEMG signal associated with the user; and a processing unit configured to determine a muscle contraction of the user based on the first and second sEMG signals.

The application relates to the technical field of computers and discloses a tracking method and system applied to orthopedic patient rehabilitation progress, which comprises the following steps: synchronously collecting image sequences and echo signals under patient free activity through high-frame-rate optical imaging and millimeter wave radar; performing three-dimensional reconstruction of human key points and muscle micro-vibration micro-Doppler feature extraction; inputting joint trajectories and muscle activation signals into a biomechanics constraint timing analysis model to output standardized joint angles, muscle strengths and motion fluency sequences; constructing a multi-dimensional rehabilitation progress trajectory graph and generating a structured evaluation report. The system comprises a multi-modal perception layer, a data preprocessing layer, a biomechanics analysis layer and a rehabilitation evaluation layer. The application realizes inductive, continuous and fine-grained rehabilitation tracking, and significantly improves the comprehensiveness, timeliness and individualization level of evaluation.

The utility model discloses an orthopedic joint rehabilitation training device, which is applied to the technical field of medical instruments and can effectively improve the movement range of elbow joints, enhance the coordination of elbow and forearm muscles and promote blood circulation around the joints through controllable bending and unbending actions. Joint stiffness and soft tissue adhesion can be prevented through regular movement, and meanwhile the hand grabbing capacity is enhanced in combination with the holding action; due to the design of adjustable holding distance, arm lengths of different patients can be accurately adapted, and it is ensured that a hand holding point is aligned with the axis of a shoulder and wrist joint during elbow joint flexion and extension training; muscle strength levels of different rehabilitation stages of a patient cannot be matched due to fixed training intensity, so that joint injury is caused by overlarge early load or muscle activation is delayed due to insufficient later load.

The application discloses a shoulder movement estimation method based on glenohumeral joint positioning and electromyography cooperation, and relates to the technical field of robot-assisted rehabilitation, and comprises the following steps: collecting surface electromyography signals and kinematics data; according to the surface electromyography signals and the kinematics data, solving a dynamic glenohumeral joint position in real time by minimizing distance residual based on anatomical constraints and step residual for ensuring continuity; determining muscle activation according to the surface electromyography signals; the muscle activation constitutes a muscle activation matrix; decomposing the muscle activation matrix into a muscle cooperation matrix and a command matrix; and estimating an upper arm angle according to elements in the command matrix. The method can realize high-precision, low-cost and long-term stable estimation of shoulder joint movement, and provides reliable technical support for robot-assisted rehabilitation.

The invention relates to the technical field of tennis training, in particular to a tennis core strength training model establishing method, which comprises the following steps of: inducing to generate muscle activation stimulation in a core muscle group through tennis training actions, and acquiring a total training stimulation amount based on a process that the muscle activation stimulation is captured by a muscle fiber and a nerve-muscle joint movement unit; determining a core strength increase equation based on the total training stimulation amount, and integrating the individual characteristic parameters of the athletes to construct a scalable core strength increase model; a scalable fatigue recovery model based on a BP neural network is obtained and used for quantifying the dynamic relation between the fatigue index and the athlete individual characteristics, training parameters and recovery time, and training cycle planning is optimized; a core strength increasing model and a fatigue recovery model are fused, a core strength training effect scalable model is formed, the change relation between the training effect and athlete individual characteristics, training parameters and training stages is comprehensively measured, and scientific and personalized core strength training scheme design and dynamic adjustment are achieved.

This invention discloses a wavelet-enhanced co-activation method for multi-target temporal modulation of functional electrical stimulation (FES), relating to the field of biomedical engineering technology. The model constructs a time-frequency energy salient feature matrix by analyzing multi-channel surface electromyography (SEMG) signals using an overlapping sliding window combined with energy proportions. Simultaneously, it constructs an intermuscular co-activation matrix within the multi-channel SEMG sliding window. Each single-channel time-frequency energy salient feature matrix and the multi-channel intermuscular co-activation matrix are then combined to form a multi-channel high-dimensional matrix. This high-dimensional matrix is ​​then dimensionality-reduced to a multi-channel, multi-dimensional time-frequency energy-intermuscular co-activation matrix. An adaptive threshold logic combination rule is used to filter muscle activation temporal vectors, and finally, the activation temporal sequence is applied to FES experiments. This invention, by analyzing multi-channel SEMG signals and multi-target muscle co-activation characteristics, accurately predicts hand movements in the sagittal plane and dynamically adjusts FES parameters, achieving precise control over muscle activity phases.

This invention relates to the technical field of exoskeleton and construction tool coordination, and discloses a phase calibration method for exoskeleton and construction tool coordination. The method includes attaching electrodes and a first sensor to the muscle groups of a construction worker, and attaching a second sensor to the handle of the construction tool. The construction worker uses the tool to perform a task: when the worker is not wearing the exoskeleton, a first signal set is collected; when the worker is wearing the exoskeleton, a second signal set is collected; a muscle activation timing reference value is set based on the first signal set; based on the second signal set and the muscle activation timing reference value, the phase difference between the first and second electrode signals is determined, and the triggering time of the exoskeleton's auxiliary force is calibrated based on the phase difference to bring the phase difference close to zero. This invention's phase calibration method for exoskeleton and construction tool coordination achieves synchronization between exoskeleton auxiliary force and human force exertion by aiming for a phase difference close to zero, avoiding the phenomena of arm-mounted or weight-bearing loads.

The invention relates to the cross technical field of artificial intelligence, digital twinning, biomechanics and the like, in particular to an AI Agent construction method based on motion digital twinning and deep motion data analysis, and the method comprises the following steps: collecting motion data of a user, calculating joint angles and displacements at each moment, calculating moments borne by joints, and obtaining motion data of the user; then, the activation degree and muscle force of each muscle in the model at each moment are solved by taking the minimum muscle activation quadratic sum as a target, then heel landing and tiptoe off-ground events are recognized, a feature time sequence is obtained, distance features with training set samples are calculated and embedded into a target low-dimensional space, and embedded features are obtained; and generating personalized feedback information according to the embedded features. Therefore, the problems that in the prior art, only a displacement-time sequence can be observed in a real scene, external force information is lost, and fine labeling of a muscle layer is scarce, so that driving mechanical quantity is difficult to recover, evaluation cannot be explained, and engineering landing is difficult are solved.

This invention discloses a closed-loop control method for functional electrical stimulation (fEP) that combines muscle activation and deep learning. It integrates muscle activation analysis with an LSTM model from deep learning to design and develop a closed-loop control method for fEP based on muscle activation and LSTM. This method can automatically learn appropriate fEP parameters based on real-time analysis of electromyographic signals to determine muscle state. This allows the method to automatically adjust the fEP parameters according to changes in muscle activation when the patient clenches their fist on the healthy side, making the grip strength on the affected and healthy sides more consistent. Furthermore, the LSTM model continuously learns and optimizes the output fEP parameters as the input dataset increases. This solves the problems in clinical fEP treatment where parameters cannot be adjusted in real-time according to the user's muscle state, parameter adjustment relies entirely on experience, patient participation is low, and active rehabilitation is not possible.

The invention discloses a lower limb electrical stimulation equipment performance test method and system based on sEMG and electroencephalogram signals, and relates to the field of biological data processing, and the method comprises the steps: obtaining a basic electroencephalogram signal of a user, and judging whether the user is in a lower limb movement preparation stage or not; if yes, an initial stimulation instruction is generated, and electrical stimulation equipment is controlled to apply electrical stimulation under the initial electrical stimulation parameters to the target muscle group of the lower limb; sEMG signals and electroencephalogram signals are synchronously collected and subjected to preprocessing and channel selection respectively, the preprocessed sEMG signals and the electroencephalogram signals subjected to channel selection are obtained and input into a trained lower limb electrical stimulation equipment performance prediction model, and the sEMG signals and the electroencephalogram signals are input into sEMG branches and electroencephalogram branches respectively for feature extraction; the muscle activation features and the nerve response features are spliced through a splicing layer and then input into an ECA module, and fusion features are obtained; and the fused features pass through a performance evaluation module to obtain a predicted performance index. The problem that a single index test cannot be dynamically regulated and controlled is solved.

The invention discloses an upper limb surface electromyogram signal analysis method fusing depth and width learning, and relates to the technical field of upper limb surface electromyogram signal analysis. Comprising the following steps: collecting multi-channel electromyographic signals to establish a complete sEMG data set, and designing convolutional neural network branches with the same number and residual structures according to the collected multi-channel sEMG signals; the residual convolutional neural network structure output features of each channel are input into the respective width learning sub-model, the weight is calculated through pseudo-inverse regression, the contribution degree index is obtained through absolute value normalization, the contribution degree is stabilized through cross validation of a mean value, the muscle activation weight corresponding to the upper limb action is analyzed, the muscle activation degree characterization is verified, and the muscle activation degree characterization is analyzed. Cooperative extraction of multi-channel muscle characteristics and quantification of muscle activation contribution degree are realized, the problem that the traditional muscle cooperative activation index is insufficient in representation capability of a real nerve-muscle control process is solved, and high-precision and interpretable quantification of a muscle cooperative relationship is realized.