In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention i...In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention in the assisted rehabilitation process of the robots,it is crucial to establish the human motion prediction model.In this paper,a hybrid prediction model built on long short-term memory(LSTM)neural network using surface electromyography(sEMG)is applied to predict the elbow motion of the users in advance.This model includes two sub-models:a back-propagation neural network and an LSTM network.The former extracts a preliminary prediction of the elbow motion,and the latter corrects this prediction to increase accuracy.The proposed model takes time series data as input,which includes the sEMG signals measured by electrodes and the continuous angles from inertial measurement units.The offline and online tests were carried out to verify the established hybrid model.Finally,average root mean square errors of 3.52°and 4.18°were reached respectively for offline and online tests,and the correlation coefficients for both were above 0.98.展开更多
This study is aimed at assessing muscle fatigue during a static contraction using multifractal analysis and found that the surface electromyographic （SEMG） signals characterized multiffactality during a static contr...This study is aimed at assessing muscle fatigue during a static contraction using multifractal analysis and found that the surface electromyographic （SEMG） signals characterized multiffactality during a static contraction. By applying the method of direct determination ofthef（a） singularity spectrum, the area of the multifractal spectrum of the SEMG signals was computed. The results showed that the spectrum area significantly increased during muscle fatigue. Therefore the area could be used as an assessor of muscle fatigue. Compared with the median frequency （MDF）--the most popular indicator of muscle fatigue, the spectrum area presented here showed higher sensitivity during a static contraction. So the singularity spectrum area is considered to be a more effective indicator than the MDF for estimating muscle fatigue.展开更多
An improved approximate entropy (ApEn) is presented and applied to characterize surface electromyography (sEMG) signals. In most previous experiments using nonlinear dynamic analysis, this certain processing was often...An improved approximate entropy (ApEn) is presented and applied to characterize surface electromyography (sEMG) signals. In most previous experiments using nonlinear dynamic analysis, this certain processing was often confronted with the problem of insufficient data points and noisy circumstances, which led to unsatisfactory results. Compared with fractal dimension as well as the standard ApEn, the improved ApEn can extract information underlying sEMG signals more efficiently and accu- rately. The method introduced here can also be applied to other medium-sized and noisy physiological signals.展开更多
The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotio...The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotion modes.sEMG signals recorded from residual thigh muscles were chosen as inputs to pattern classifier for locomotion-mode identification.High-order zero-crossing were computed as the sEMG features regarding locomotion modes.Relevance vector machine(RVM)classifier was investigated.Bat algorithm(BA)was used to compute the RVM classifier kernel function parameters.The classification performance of the particle swarm optimization-relevance vector machine(PSO-RVM)and RVM classifiers was compared.The BA-RVM produced lower classification error in sEMG pattern recognition for the transtibial amputees over a variety of locomotion modes:upslope,downgrade,level-ground walking and stair ascent/descent.展开更多
The sEMG signals are collected from the vastus lateralis,vastus medialis,biceps femoris,and semitendinosus of lower extremity during level walking among control subjects and knee osteoarthritis (OA) patients,the latte...The sEMG signals are collected from the vastus lateralis,vastus medialis,biceps femoris,and semitendinosus of lower extremity during level walking among control subjects and knee osteoarthritis (OA) patients,the latter including mild,moderate and severe degree.The 5-fold cross-validation is used to measure the accuracy of the proposed analysis algorithm on collected sEMG recordings.For comparison,the more classical feature vectors of form factor,degree of skewness,kurtosis,and wavelet entropy are also tested.In experiment,the normalized energy ratio and marginal spectrum ratio achieve larger accuracy than the other features for all the four muscular groups.Moreover the accuracy of vastus medialis and biceps femoris are larger than that of vastus lateralis and semitendinosus.These results suggest that the normalized energy ratio and marginal spectrum ratio via the analysis of knee sEMG signals by HHT can server as characteristic parameters to easily classify osteoarthritis with noninvasive method.The more important muscular groups for maintaining the knee joint function are medialis and biceps femoris;as a result of that they should be exercise especially for rehabilitation.展开更多
The surface electromyography(sEMG)is one of the basic processing techniques to the gesture recognition because of its inherent advantages of easy collection and non-invasion.However,limited by feature extraction and c...The surface electromyography(sEMG)is one of the basic processing techniques to the gesture recognition because of its inherent advantages of easy collection and non-invasion.However,limited by feature extraction and classifier selection,the adaptability and accuracy of the conventional machine learning still need to promote with the increase of the input dimension and the number of output classifications.Moreover,due to the different characteristics of sEMG data and image data,the conventional convolutional neural network(CNN)have yet to fit sEMG signals.In this paper,a novel hybrid model combining CNN with the graph convolutional network(GCN)was constructed to improve the performance of the gesture recognition.Based on the characteristics of sEMG signal,GCN was introduced into the model through a joint voting network to extract the muscle synergy feature of the sEMG signal.Such strategy optimizes the structure and convolution kernel parameters of the residual network(ResNet)with the classification accuracy on the NinaPro DBl up to 90.07%.The experimental results and comparisons confirm the superiority of the proposed hybrid model for gesture recognition from the sEMG signals.展开更多
Surface electromyogram(sEMG)signals are valuable in healthcare and human-machine interaction.However,s EMG signals are inherently weak and unstable bioelectrical signals,rendering them highly susceptible to perturbati...Surface electromyogram(sEMG)signals are valuable in healthcare and human-machine interaction.However,s EMG signals are inherently weak and unstable bioelectrical signals,rendering them highly susceptible to perturbations from various external factors.In this work,we firstly proposed utilizing the industrially producible Gen-4.5 heterogeneous integration technology to design an active 16-channel microelectrode array(MEA)based on amorphous indium-gallium-zinc oxide thin-film transistors(a-IGZO TFTs)capable of capturing and decoding sEMG signals.The a-IGZO TFTs demonstrate exceptional stability under bias(±20 V),temperature(200℃),and bending(6 mm,30000 cycles),with a threshold voltage shift of less than 0.1 V and a standard deviation under 0.07 V for 100 randomly selected devices.Our state-of-the-art 16-channel active MEAs can collect sEMG signals from various hand gestures and analysis of motor unit action potential trains,expanding possibilities for human-machine interaction and electronic healthcare applications.The signal-to-noise ratio of sEMG signals reaches 85 dB,enabling a high average hand gesture recognition accuracy of 96.2%.This work highlights the potential of the scalable sEMG arrays with exceptional stability for multi-channel sEMG signal acquisition,representing a significant advancement in wearable health monitoring and interactive systems.展开更多
Objective:To observe the clinical effect of combined acupuncture and kinesiotherapy on upper cross syndrome(UCS) by a parallel randomized clinical trial.Methods:A total of 45 patients with UCS were recruited from the ...Objective:To observe the clinical effect of combined acupuncture and kinesiotherapy on upper cross syndrome(UCS) by a parallel randomized clinical trial.Methods:A total of 45 patients with UCS were recruited from the outpatients of AcupunctureMoxibustion,Tuina and Rehabilitation Department of the First Affiliated Hospital of Hunan University of Chinese Medicine,the students of Hunan University of Chinese Medicine and the patients from the nearby communities in accordance with the inclusion criteria.Using the random number table method,they were divided into a combined treatment group(acupuncture plus kinesiotherapy,23 cases) and a simple kinesiotherapy group(22 patients).Treatment for 4 weeks was one course,and two consecutive courses were required.The visual analog scale(VAS) score,the score of the assessment scale for cervical spondylosis,the value of surface electromyography(root mean square,RMS),and the cervical curvature value were used in the evaluation.The allocation scheme was concealed from the outcome assessors.Results:The data from 23 cases of the combined treatment group and 22 cases of the simple kinesiotherapy group were analyzed.Before treatment,the differences were not statistically significant in the general conditions,VAS score,assessment score of cervical spondylosis,cervical curvature value,and RMS in UCS patients between the two groups(all P> 0.05).After treatment,the VAS score was reduced compared with that before treatment in both groups(all P <0.05).In two courses of treatment,the VAS score decreased as compared with that in one course of treatment in both groups(both P <0.05),and the VAS score in the combined treatment group decreased more obviously after each course of treatment(both P <0.05).The RMS decreased compared with that before treatment in each group(both P <0.05),and the decrease in the combined treatment group was more obvious(P <0.05).After treatment of each course,the assessment score was all increased as compared with that before treatment in two groups(all P <0.05).In two courses of treatment,the assessment score was increased as compared with that in one course of treatment in both groups(both P <0.05),and the score in the combined treatment group was increased more obviously in the two courses of treatment(P <0.05).Regarding either the intra-group comparison or the inter-group comparison before and after treatment,the differences were not statistically significant(all P> 0.05),suggesting no obvious improvement of cervical curvature in the two courses of treatment in patients with UCS.However,cervical curvature tended to improve in the combined treatment group.The total effective rate was significantly different between the two groups(P <0.05),indicating that the total effective rate in the combined treatment group was better than that in the simple kinesiotherapy group.No any adverse reactions occurred.Conclusion:Combined treatment with acupuncture,kinesiotherapy,and kinesiotherapy alleviated pain,relieved the symptoms and physical signs,and improved the daily movement of the patients.However,the combined treatment of acupuncture and kinesiotherapy had a much better effect on UCS.展开更多
A novel 5-DOF exoskeletal rehabilitation robot for upper limbs of hemiplegic patients caused by stroke is proposed in this paper. Its hardware structure is introduced and the control methods are ana- lyzed. To impleme...A novel 5-DOF exoskeletal rehabilitation robot for upper limbs of hemiplegic patients caused by stroke is proposed in this paper. Its hardware structure is introduced and the control methods are ana- lyzed. To implement intelligent and interactive rehabilitation exercises, motion intention of patients＇ up- per limb is introduced into control methods of rehabilitation exercises. In passive motions, according to the character of unilateral impaired, multi-channels surface electromyogram （sEMG） signals of patients＇ healthy arm muscles are acquired and analyzed to recognize the upper limb motions, then drive the robot and assist paralysis ann＇s rehabilitation exercises. In active-resistant motions, because patients are re- covered with some muscle forces and active motion ability after a rehabilitation period, the terminal force loaded on the robot by an impaired arm are estimated with multi-channel joint torque sensors, according to which, the terminal velocity of the robot is controlled to drive the joint motions with a damp controller.展开更多
A surface electromyography(sEMG)signal acquisition circuit based on high-order filtering is designed.We use a two-stage adjustable amplifier and a high-order Sallen-Key bandpass filter to solve the problems of non-adj...A surface electromyography(sEMG)signal acquisition circuit based on high-order filtering is designed.We use a two-stage adjustable amplifier and a high-order Sallen-Key bandpass filter to solve the problems of non-adjustable amplification gain and low filtering order in traditional acquisition circuits.The experimental results show that the designed sEMG signal acquisition device can eliminate power frequency interference effectively,the stopband drop of the filtering part reaches approximately-100 dB/dec,which can effectively extract useful signals between 20-500 Hz,and the amplification gain reaches 60 dB.展开更多
Purpose:To observe the relative change in foot-strike pattern,pressure characteristics,surface electromyography(sEMG) recordings,and stride characteristics in forefoot strike runners wearing both minimalist and tradit...Purpose:To observe the relative change in foot-strike pattern,pressure characteristics,surface electromyography(sEMG) recordings,and stride characteristics in forefoot strike runners wearing both minimalist and traditional shoes during a 50-km run.Methods:Four experienced minimalist runners were enrolled in this study.Each runner ran a 50-km simulated run in both minimalist shoes and traditional shoes.Pressure data,sEMG recordings,and limited 3D motion capture data were collected during the initial 0.8 km and final 0.8 km for each trial.Results:Three runners in the traditional shoe type condition and one runner in the minimalist shoe type condition demonstrated a more posterior initial contact area(midfoot strike(MFS) pattern) after the 50-km run.which was supported by increased activity of the tibialis anterior in the pre-contaet phase(as per root mean square(RMS) values).In addition,in both pre- and post-run conditions,there were increased peak pressures in the minimalist shoe type,specifically in the medial forefoot.Muscle fatigue as defined by a decreased median frequency observed in isometric,constant force contractions did not correspond with our hypothesis in relation to the observed foot strike change pattern.Finally,step rate increased and step length decreased after the 50-km run in both shoe type conditions.Conclusion:More runners adopted a more posterior initial contact area after the 50-km run in the traditional shoe type than in the minimalist shoe type.The runners who adopted a more posterior initial contact area were more closely associated with an increased median frequency of the medial gastrocnemius,which suggests there may be a change in motor unit recruitment pattern during long-distance,sustained velocity running.The increased peak pressures observed in the medial forefoot in the minimalist shoe type may predispose to metatarsal stress fractures in the setting of improper training.展开更多
Facial muscles are uniquely attached to the skin,densely innervated,and exhibit complex coactivation patterns enabling fine motor control.Facial surface Electromyography(sEMG)effectively assesses muscle function,yet t...Facial muscles are uniquely attached to the skin,densely innervated,and exhibit complex coactivation patterns enabling fine motor control.Facial surface Electromyography(sEMG)effectively assesses muscle function,yet traditional setups require precise electrode placement and limit mobility due to mechanical artifacts.Signal extraction is hindered by noise and cross-talk from adjacent muscles,making it challenging to associate facial muscle activity with expressions.We leverage a novel 16-channel conformal sEMG system to extract meaningful electrophysiological data from 32 healthy individuals.By applying denoising and source separation techniques,we extracted independent components,clustered them spatially,and built a facial muscle atlas.Furthermore,we established a functional mapping between these clusters and specific muscle units,providing a framework for understanding facial muscle activation.Using this foundation,we demonstrated a deep-learning model to predict facial expressions.This approach enables precise,participant-specific monitoring with applications in medical rehabilitation and psychological research.展开更多
For intelligent transportation systems(ITS),understanding pedestrian motion intention is crucial for enhancing traffic safety,enabling human-centered mobility services,and facilitating adaptive vehicle-pedestrian inte...For intelligent transportation systems(ITS),understanding pedestrian motion intention is crucial for enhancing traffic safety,enabling human-centered mobility services,and facilitating adaptive vehicle-pedestrian interactions.This paper proposes a pedestrian gait recognition method based on a modified particle swarm optimization-support vector machine(MPSO-SVM),utilizing fused surface electromyography(sEMG)signals and ankle joint angles.Seven lower-limb gait features were extracted from these signals to characterize walking patterns.The MPSO algorithm optimizes the support vector machine(SVM)parameters to improve classification performance.Experimental results based on data collected from healthy subjects demonstrate a recognition accuracy exceeding 92.5%across four gait phases.The proposed method offers significantly enhanced accuracy and robustness compared to traditional classifiers.These results suggest that the method is suitable for deployment in intelligent traffic control systems,autonomous vehicle navigation,and urban pedestrian behavior prediction.展开更多
Deciphering hand motion intention from surface electromyography(sEMG)encounters challenges posed by the requisites of multiple degrees of freedom(DOFs)and adaptability.Unlike discrete action classification grounded in...Deciphering hand motion intention from surface electromyography(sEMG)encounters challenges posed by the requisites of multiple degrees of freedom(DOFs)and adaptability.Unlike discrete action classification grounded in pattern recognition,the pursuit of continuous kinematics estimation is appreciated for its inherent naturalness and intuitiveness.However,prevailing estimation techniques contend with accuracy limitations and substantial computational demands.Kalman estimation technology,celebrated for its ease of implementation and real-time adaptability,finds extensive application across diverse domains.This study introduces a continuous Kalman estimation method,leveraging a system model with sEMG and joint angles as inputs and outputs.Facilitated by model parameter training methods,the approach deduces multiple DOF finger kinematics simultaneously.The method’s efficacy is validated using a publicly accessible database,yielding a correlation coefficient(CC)of 0.73.With over 45,000 windows for training Kalman model parameters,the average computation time remains under 0.01 s.This pilot study amplifies its potential for further exploration and application within the realm of continuous finger motion estimation technology.展开更多
Surface electromyography(sEMG)control interface is a common method for human-centered robotics.Researchers have frequently improved the recognition accuracy of sEMG through multichannel or high-precision signal acquis...Surface electromyography(sEMG)control interface is a common method for human-centered robotics.Researchers have frequently improved the recognition accuracy of sEMG through multichannel or high-precision signal acquisition devices.However,this increases the cost and complexity of the control system.Therefore,this study developed a control interface based on the sEMG enveloped signal for a collaborative wearable robot to improve the accuracy of sEMG recognition based on the time-domain(TD)features.Specifically,an acquisition device is developed to obtain the sEMG envelope signal,and 11 types of TD features are extracted from the sEMG envelope signal acquired from the upper limb.Furthermore,a dimension reduction method based on the correlation coefficient is proposed,transforming the 11-dimensional feature into a five-dimensional envelope feature set without decreasing the accuracy.Moreover,a recognition algorithm based on a neural network has also been proposed for gesture classification.Finally,the recognition accuracy of the proposed method,principal component analysis(PCA)feature set,and Hudgins TD feature set is compared,with their accuracy at 84.39%,72.44%,and 70.89%,respectively.Therefore,the results indicate that the envelope feature set performs better than the common gesture recognition method based on signal channel sEMG envelope signal.展开更多
Surface electromyogram(sEMG)serves as a means to discern human movement intentions,achieved by applying epidermal electrodes to specific body regions.However,it is difficult to obtain high-fidelity sEMG recordings in ...Surface electromyogram(sEMG)serves as a means to discern human movement intentions,achieved by applying epidermal electrodes to specific body regions.However,it is difficult to obtain high-fidelity sEMG recordings in areas with intricate curved surfaces,such as the body,because regular sEMG electrodes have stiff structures.In this study,we developed myoelectrically sensitive hydrogels via 3D printing and integrated them into a stretchable,flexible,and high-density sEMG electrodes array.This electrode array offered a series of excellent human-machine interface(HMI)features,including conformal adherence to the skin,high electron-to-ion conductivity(and thus lower contact impedance),and sustained stability over extended periods.These attributes render our electrodes more conducive than commercial electrodes for long-term wearing and high-fidelity sEMG recording at complicated skin interfaces.Systematic in vivo studies were used to investigate its efficacy to control a prosthetic hand by decoding sEMG signals from the human hand via a multiple-channel readout circuit and a sophisticated artificial intelligence algorithm.Our findings demonstrate that the 3D printed gel myoelectric sensing system enables real-time and highly precise control of a prosthetic hand.展开更多
基金the National Key Research and Development Program of China(No.2020YFC2007500)the Science and Technology Commission of Shanghai Municipality(No.20DZ2220400)。
文摘In the face of the large number of people with motor function disabilities,rehabilitation robots have attracted more and more attention.In order to promote the active participation of the user's motion intention in the assisted rehabilitation process of the robots,it is crucial to establish the human motion prediction model.In this paper,a hybrid prediction model built on long short-term memory(LSTM)neural network using surface electromyography(sEMG)is applied to predict the elbow motion of the users in advance.This model includes two sub-models:a back-propagation neural network and an LSTM network.The former extracts a preliminary prediction of the elbow motion,and the latter corrects this prediction to increase accuracy.The proposed model takes time series data as input,which includes the sEMG signals measured by electrodes and the continuous angles from inertial measurement units.The offline and online tests were carried out to verify the established hybrid model.Finally,average root mean square errors of 3.52°and 4.18°were reached respectively for offline and online tests,and the correlation coefficients for both were above 0.98.
基金Project (No. 2005CB724303) supported by the National Basic Re-search Program (973) of China
文摘This study is aimed at assessing muscle fatigue during a static contraction using multifractal analysis and found that the surface electromyographic （SEMG） signals characterized multiffactality during a static contraction. By applying the method of direct determination ofthef（a） singularity spectrum, the area of the multifractal spectrum of the SEMG signals was computed. The results showed that the spectrum area significantly increased during muscle fatigue. Therefore the area could be used as an assessor of muscle fatigue. Compared with the median frequency （MDF）--the most popular indicator of muscle fatigue, the spectrum area presented here showed higher sensitivity during a static contraction. So the singularity spectrum area is considered to be a more effective indicator than the MDF for estimating muscle fatigue.
基金Project supported by the National Natural Science Foundation of China (No. 60171006) and the National Basic Research Program (973) of China (No. 2005CB724303)
文摘An improved approximate entropy (ApEn) is presented and applied to characterize surface electromyography (sEMG) signals. In most previous experiments using nonlinear dynamic analysis, this certain processing was often confronted with the problem of insufficient data points and noisy circumstances, which led to unsatisfactory results. Compared with fractal dimension as well as the standard ApEn, the improved ApEn can extract information underlying sEMG signals more efficiently and accu- rately. The method introduced here can also be applied to other medium-sized and noisy physiological signals.
基金the Center Plain Science and Technology Innovation Talents(No.194200510016)the Science and Technology Innovation Team Project of Henan Province University(No.19IRTSTHN013)the Key Scien-tific Research Support Project for Institutions of Higher Learning in Henan Province(No.18A413014)。
文摘The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode.Surface electromyography(sEMG)combined with high-order zero-crossing was used to identify the prosthetic leg locomotion modes.sEMG signals recorded from residual thigh muscles were chosen as inputs to pattern classifier for locomotion-mode identification.High-order zero-crossing were computed as the sEMG features regarding locomotion modes.Relevance vector machine(RVM)classifier was investigated.Bat algorithm(BA)was used to compute the RVM classifier kernel function parameters.The classification performance of the particle swarm optimization-relevance vector machine(PSO-RVM)and RVM classifiers was compared.The BA-RVM produced lower classification error in sEMG pattern recognition for the transtibial amputees over a variety of locomotion modes:upslope,downgrade,level-ground walking and stair ascent/descent.
基金Sponsored by the International Science and Technology Cooperation Project of China(Grant No.2009DFA32050)
文摘The sEMG signals are collected from the vastus lateralis,vastus medialis,biceps femoris,and semitendinosus of lower extremity during level walking among control subjects and knee osteoarthritis (OA) patients,the latter including mild,moderate and severe degree.The 5-fold cross-validation is used to measure the accuracy of the proposed analysis algorithm on collected sEMG recordings.For comparison,the more classical feature vectors of form factor,degree of skewness,kurtosis,and wavelet entropy are also tested.In experiment,the normalized energy ratio and marginal spectrum ratio achieve larger accuracy than the other features for all the four muscular groups.Moreover the accuracy of vastus medialis and biceps femoris are larger than that of vastus lateralis and semitendinosus.These results suggest that the normalized energy ratio and marginal spectrum ratio via the analysis of knee sEMG signals by HHT can server as characteristic parameters to easily classify osteoarthritis with noninvasive method.The more important muscular groups for maintaining the knee joint function are medialis and biceps femoris;as a result of that they should be exercise especially for rehabilitation.
基金supported by the Development of Sleep Disordered Breathing Detection and Auxiliary Regulation System Project(No.2019I1009)。
文摘The surface electromyography(sEMG)is one of the basic processing techniques to the gesture recognition because of its inherent advantages of easy collection and non-invasion.However,limited by feature extraction and classifier selection,the adaptability and accuracy of the conventional machine learning still need to promote with the increase of the input dimension and the number of output classifications.Moreover,due to the different characteristics of sEMG data and image data,the conventional convolutional neural network(CNN)have yet to fit sEMG signals.In this paper,a novel hybrid model combining CNN with the graph convolutional network(GCN)was constructed to improve the performance of the gesture recognition.Based on the characteristics of sEMG signal,GCN was introduced into the model through a joint voting network to extract the muscle synergy feature of the sEMG signal.Such strategy optimizes the structure and convolution kernel parameters of the residual network(ResNet)with the classification accuracy on the NinaPro DBl up to 90.07%.The experimental results and comparisons confirm the superiority of the proposed hybrid model for gesture recognition from the sEMG signals.
基金financial support given by the National Natural Science Foundation of China(52227808,62574124)Shanghai Science and Technology Commission(25ZR1401120)+2 种基金the National Science Foundation for Distinguished Young Scholars of China(51725505)the Development Fund for Shanghai Talents(2021003)Digital Medical Research Institute,Shanghai University(SHU-UM-JBGS-2025-14)。
文摘Surface electromyogram(sEMG)signals are valuable in healthcare and human-machine interaction.However,s EMG signals are inherently weak and unstable bioelectrical signals,rendering them highly susceptible to perturbations from various external factors.In this work,we firstly proposed utilizing the industrially producible Gen-4.5 heterogeneous integration technology to design an active 16-channel microelectrode array(MEA)based on amorphous indium-gallium-zinc oxide thin-film transistors(a-IGZO TFTs)capable of capturing and decoding sEMG signals.The a-IGZO TFTs demonstrate exceptional stability under bias(±20 V),temperature(200℃),and bending(6 mm,30000 cycles),with a threshold voltage shift of less than 0.1 V and a standard deviation under 0.07 V for 100 randomly selected devices.Our state-of-the-art 16-channel active MEAs can collect sEMG signals from various hand gestures and analysis of motor unit action potential trains,expanding possibilities for human-machine interaction and electronic healthcare applications.The signal-to-noise ratio of sEMG signals reaches 85 dB,enabling a high average hand gesture recognition accuracy of 96.2%.This work highlights the potential of the scalable sEMG arrays with exceptional stability for multi-channel sEMG signal acquisition,representing a significant advancement in wearable health monitoring and interactive systems.
基金Supported by Leading Talents Training Program of Hunan Province High-Level Health Talents 225 Project (Hunan Health-20N9-N9S)。
文摘Objective:To observe the clinical effect of combined acupuncture and kinesiotherapy on upper cross syndrome(UCS) by a parallel randomized clinical trial.Methods:A total of 45 patients with UCS were recruited from the outpatients of AcupunctureMoxibustion,Tuina and Rehabilitation Department of the First Affiliated Hospital of Hunan University of Chinese Medicine,the students of Hunan University of Chinese Medicine and the patients from the nearby communities in accordance with the inclusion criteria.Using the random number table method,they were divided into a combined treatment group(acupuncture plus kinesiotherapy,23 cases) and a simple kinesiotherapy group(22 patients).Treatment for 4 weeks was one course,and two consecutive courses were required.The visual analog scale(VAS) score,the score of the assessment scale for cervical spondylosis,the value of surface electromyography(root mean square,RMS),and the cervical curvature value were used in the evaluation.The allocation scheme was concealed from the outcome assessors.Results:The data from 23 cases of the combined treatment group and 22 cases of the simple kinesiotherapy group were analyzed.Before treatment,the differences were not statistically significant in the general conditions,VAS score,assessment score of cervical spondylosis,cervical curvature value,and RMS in UCS patients between the two groups(all P> 0.05).After treatment,the VAS score was reduced compared with that before treatment in both groups(all P <0.05).In two courses of treatment,the VAS score decreased as compared with that in one course of treatment in both groups(both P <0.05),and the VAS score in the combined treatment group decreased more obviously after each course of treatment(both P <0.05).The RMS decreased compared with that before treatment in each group(both P <0.05),and the decrease in the combined treatment group was more obvious(P <0.05).After treatment of each course,the assessment score was all increased as compared with that before treatment in two groups(all P <0.05).In two courses of treatment,the assessment score was increased as compared with that in one course of treatment in both groups(both P <0.05),and the score in the combined treatment group was increased more obviously in the two courses of treatment(P <0.05).Regarding either the intra-group comparison or the inter-group comparison before and after treatment,the differences were not statistically significant(all P> 0.05),suggesting no obvious improvement of cervical curvature in the two courses of treatment in patients with UCS.However,cervical curvature tended to improve in the combined treatment group.The total effective rate was significantly different between the two groups(P <0.05),indicating that the total effective rate in the combined treatment group was better than that in the simple kinesiotherapy group.No any adverse reactions occurred.Conclusion:Combined treatment with acupuncture,kinesiotherapy,and kinesiotherapy alleviated pain,relieved the symptoms and physical signs,and improved the daily movement of the patients.However,the combined treatment of acupuncture and kinesiotherapy had a much better effect on UCS.
基金supported by the High Technology Research and Development Programme of China(No.2004AA421030)
文摘A novel 5-DOF exoskeletal rehabilitation robot for upper limbs of hemiplegic patients caused by stroke is proposed in this paper. Its hardware structure is introduced and the control methods are ana- lyzed. To implement intelligent and interactive rehabilitation exercises, motion intention of patients＇ up- per limb is introduced into control methods of rehabilitation exercises. In passive motions, according to the character of unilateral impaired, multi-channels surface electromyogram （sEMG） signals of patients＇ healthy arm muscles are acquired and analyzed to recognize the upper limb motions, then drive the robot and assist paralysis ann＇s rehabilitation exercises. In active-resistant motions, because patients are re- covered with some muscle forces and active motion ability after a rehabilitation period, the terminal force loaded on the robot by an impaired arm are estimated with multi-channel joint torque sensors, according to which, the terminal velocity of the robot is controlled to drive the joint motions with a damp controller.
基金Science and Technology Plan Project of Weinan City(No.2020ZDYF-JCYJ-177)Power Supply Technology Innovation Team of Shaanxi Railway Engineering Vocational and Technical College(No.KJTD201901)Graduate Program Funded Project of Shaanxi Railway Engineering Vocational and Technical College Scientific Research Fund(No.KY2018-77)。
文摘A surface electromyography(sEMG)signal acquisition circuit based on high-order filtering is designed.We use a two-stage adjustable amplifier and a high-order Sallen-Key bandpass filter to solve the problems of non-adjustable amplification gain and low filtering order in traditional acquisition circuits.The experimental results show that the designed sEMG signal acquisition device can eliminate power frequency interference effectively,the stopband drop of the filtering part reaches approximately-100 dB/dec,which can effectively extract useful signals between 20-500 Hz,and the amplification gain reaches 60 dB.
基金the Medical College of Wisconsin's Department of Physical Medicine & Rehabilitation,as well as by grant 1UL1RR031973 from the Clinical and Translational Science Award(CTSA)program of the National Center for Research Resources,National Institutes of Health
文摘Purpose:To observe the relative change in foot-strike pattern,pressure characteristics,surface electromyography(sEMG) recordings,and stride characteristics in forefoot strike runners wearing both minimalist and traditional shoes during a 50-km run.Methods:Four experienced minimalist runners were enrolled in this study.Each runner ran a 50-km simulated run in both minimalist shoes and traditional shoes.Pressure data,sEMG recordings,and limited 3D motion capture data were collected during the initial 0.8 km and final 0.8 km for each trial.Results:Three runners in the traditional shoe type condition and one runner in the minimalist shoe type condition demonstrated a more posterior initial contact area(midfoot strike(MFS) pattern) after the 50-km run.which was supported by increased activity of the tibialis anterior in the pre-contaet phase(as per root mean square(RMS) values).In addition,in both pre- and post-run conditions,there were increased peak pressures in the minimalist shoe type,specifically in the medial forefoot.Muscle fatigue as defined by a decreased median frequency observed in isometric,constant force contractions did not correspond with our hypothesis in relation to the observed foot strike change pattern.Finally,step rate increased and step length decreased after the 50-km run in both shoe type conditions.Conclusion:More runners adopted a more posterior initial contact area after the 50-km run in the traditional shoe type than in the minimalist shoe type.The runners who adopted a more posterior initial contact area were more closely associated with an increased median frequency of the medial gastrocnemius,which suggests there may be a change in motor unit recruitment pattern during long-distance,sustained velocity running.The increased peak pressures observed in the medial forefoot in the minimalist shoe type may predispose to metatarsal stress fractures in the setting of improper training.
基金support from the Deutsche Forschungsgemeinschaft(DFG),Grant No.GU-463/12-1support by the Israel Science Foundation(ISF)Grant No.1355/17,and the European Research Council(ERC),Grant Outer-Ret—101053186support of the Tel Aviv University Center for AI&Data Science。
文摘Facial muscles are uniquely attached to the skin,densely innervated,and exhibit complex coactivation patterns enabling fine motor control.Facial surface Electromyography(sEMG)effectively assesses muscle function,yet traditional setups require precise electrode placement and limit mobility due to mechanical artifacts.Signal extraction is hindered by noise and cross-talk from adjacent muscles,making it challenging to associate facial muscle activity with expressions.We leverage a novel 16-channel conformal sEMG system to extract meaningful electrophysiological data from 32 healthy individuals.By applying denoising and source separation techniques,we extracted independent components,clustered them spatially,and built a facial muscle atlas.Furthermore,we established a functional mapping between these clusters and specific muscle units,providing a framework for understanding facial muscle activation.Using this foundation,we demonstrated a deep-learning model to predict facial expressions.This approach enables precise,participant-specific monitoring with applications in medical rehabilitation and psychological research.
基金partly supported by the Research Project of Higher Education in Henan Province(Grant no.23A413008)partly by the Project of the Science and Technology Department of Henan Province(Grant no.252102221011).
文摘For intelligent transportation systems(ITS),understanding pedestrian motion intention is crucial for enhancing traffic safety,enabling human-centered mobility services,and facilitating adaptive vehicle-pedestrian interactions.This paper proposes a pedestrian gait recognition method based on a modified particle swarm optimization-support vector machine(MPSO-SVM),utilizing fused surface electromyography(sEMG)signals and ankle joint angles.Seven lower-limb gait features were extracted from these signals to characterize walking patterns.The MPSO algorithm optimizes the support vector machine(SVM)parameters to improve classification performance.Experimental results based on data collected from healthy subjects demonstrate a recognition accuracy exceeding 92.5%across four gait phases.The proposed method offers significantly enhanced accuracy and robustness compared to traditional classifiers.These results suggest that the method is suitable for deployment in intelligent traffic control systems,autonomous vehicle navigation,and urban pedestrian behavior prediction.
基金supported in part by the National Key R&D Program of China(#2020YFC2007900)the National Natural Science Foundation of China(#82161160341,#62271477,and #61901464)+2 种基金the Science and Technology Program of Guangdong Province(#2022A0505090007)“The Belt and Road”Innovative Talent Exchange program for foreign experts(DL2022024002L)Jinan 5150 Program for Talents Introduction.
文摘Deciphering hand motion intention from surface electromyography(sEMG)encounters challenges posed by the requisites of multiple degrees of freedom(DOFs)and adaptability.Unlike discrete action classification grounded in pattern recognition,the pursuit of continuous kinematics estimation is appreciated for its inherent naturalness and intuitiveness.However,prevailing estimation techniques contend with accuracy limitations and substantial computational demands.Kalman estimation technology,celebrated for its ease of implementation and real-time adaptability,finds extensive application across diverse domains.This study introduces a continuous Kalman estimation method,leveraging a system model with sEMG and joint angles as inputs and outputs.Facilitated by model parameter training methods,the approach deduces multiple DOF finger kinematics simultaneously.The method’s efficacy is validated using a publicly accessible database,yielding a correlation coefficient(CC)of 0.73.With over 45,000 windows for training Kalman model parameters,the average computation time remains under 0.01 s.This pilot study amplifies its potential for further exploration and application within the realm of continuous finger motion estimation technology.
基金supported by the Fundamental Research Funds for the Central Universities,China(NS2020036 and NP2022304)the National Natural Science Foundation of China(52105103 and 52205018)the External Project of AECC Sichuan Gas Turbine Establishment(GJCZ-2020-0044).
文摘Surface electromyography(sEMG)control interface is a common method for human-centered robotics.Researchers have frequently improved the recognition accuracy of sEMG through multichannel or high-precision signal acquisition devices.However,this increases the cost and complexity of the control system.Therefore,this study developed a control interface based on the sEMG enveloped signal for a collaborative wearable robot to improve the accuracy of sEMG recognition based on the time-domain(TD)features.Specifically,an acquisition device is developed to obtain the sEMG envelope signal,and 11 types of TD features are extracted from the sEMG envelope signal acquired from the upper limb.Furthermore,a dimension reduction method based on the correlation coefficient is proposed,transforming the 11-dimensional feature into a five-dimensional envelope feature set without decreasing the accuracy.Moreover,a recognition algorithm based on a neural network has also been proposed for gesture classification.Finally,the recognition accuracy of the proposed method,principal component analysis(PCA)feature set,and Hudgins TD feature set is compared,with their accuracy at 84.39%,72.44%,and 70.89%,respectively.Therefore,the results indicate that the envelope feature set performs better than the common gesture recognition method based on signal channel sEMG envelope signal.
基金supported by the National Natural Science Foundation of China(grant numbers 42177440 and 52075177)the National Key Research and Development Program of China(Grant No.2021YFB3301400).
文摘Surface electromyogram(sEMG)serves as a means to discern human movement intentions,achieved by applying epidermal electrodes to specific body regions.However,it is difficult to obtain high-fidelity sEMG recordings in areas with intricate curved surfaces,such as the body,because regular sEMG electrodes have stiff structures.In this study,we developed myoelectrically sensitive hydrogels via 3D printing and integrated them into a stretchable,flexible,and high-density sEMG electrodes array.This electrode array offered a series of excellent human-machine interface(HMI)features,including conformal adherence to the skin,high electron-to-ion conductivity(and thus lower contact impedance),and sustained stability over extended periods.These attributes render our electrodes more conducive than commercial electrodes for long-term wearing and high-fidelity sEMG recording at complicated skin interfaces.Systematic in vivo studies were used to investigate its efficacy to control a prosthetic hand by decoding sEMG signals from the human hand via a multiple-channel readout circuit and a sophisticated artificial intelligence algorithm.Our findings demonstrate that the 3D printed gel myoelectric sensing system enables real-time and highly precise control of a prosthetic hand.
