In this article,to reduce the complexity and improve the generalization ability of current gesture recognition systems,we propose a novel SE-CNN attention architecture for sEMG-based hand gesture recognition.The propo...In this article,to reduce the complexity and improve the generalization ability of current gesture recognition systems,we propose a novel SE-CNN attention architecture for sEMG-based hand gesture recognition.The proposed algorithm introduces a temporal squeeze-and-excite block into a simple CNN architecture and then utilizes it to recalibrate the weights of the feature outputs from the convolutional layer.By enhancing important features while suppressing useless ones,the model realizes gesture recognition efficiently.The last procedure of the proposed algorithm is utilizing a simple attention mechanism to enhance the learned representations of sEMG signals to performmulti-channel sEMG-based gesture recognition tasks.To evaluate the effectiveness and accuracy of the proposed algorithm,we conduct experiments involving multi-gesture datasets Ninapro DB4 and Ninapro DB5 for both inter-session validation and subject-wise cross-validation.After a series of comparisons with the previous models,the proposed algorithm effectively increases the robustness with improved gesture recognition performance and generalization ability.展开更多
The human-computer interaction (HCI) is now playing a great role in computer technology. This study introduces an automatic document control technique which is based on the human hand waving movements. The recognition...The human-computer interaction (HCI) is now playing a great role in computer technology. This study introduces an automatic document control technique which is based on the human hand waving movements. The recognition of hand movement is realized according to the surface electromyography (sEMG). A collector is set on the forearm. The sEMG signal is recorded and conveyed to a PC terminal by using wireless Zigbee. An automatic algorithm is developed in order to extract the characteristics of sEMG, recognize the waving movements, and transmit to document control command. The developed human-computer interaction technique can be used as a new gallery for teaching, as well as an assistant tool for disabled person.展开更多
Surface electromyography(sEMG)is widely used for analyzing and controlling lower limb assisted exoskeleton robots.Behavior intention recognition based on sEMG is of great significance for achieving intelligent prosthe...Surface electromyography(sEMG)is widely used for analyzing and controlling lower limb assisted exoskeleton robots.Behavior intention recognition based on sEMG is of great significance for achieving intelligent prosthetic and exoskeleton control.Achieving highly efficient recognition while improving performance has always been a significant challenge.To address this,we propose an sEMG-based method called Enhanced Residual Gate Network(ERGN)for lower-limb behavioral intention recognition.The proposed network combines an attention mechanism and a hard threshold function,while combining the advantages of residual structure,which maps sEMG of multiple acquisition channels to the lower limb motion states.Firstly,continuous wavelet transform(CWT)is used to extract signals features from the collected sEMG data.Then,a hard threshold function serves as the gate function to enhance signals quality,with an attention mechanism incorporated to improve the ERGN’s performance further.Experimental results demonstrate that the proposed ERGN achieves extremely high accuracy and efficiency,with an average recognition accuracy of 98.41%and an average recognition time of only 20 ms-outperforming the state-of-the-art research significantly.Our research provides support for the application of lower limb assisted exoskeleton robots.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
文摘为了提高表面肌电信号(surface electromyography,sEMG)的手势分类准确率,通过惯性测量单元(inertial measurement unit,IMU)与采集姿态信号与sEMG的混合信号,提出了GRUBiLSTM双层网络的实时手势分类算法。第1层门控循环单元(gated recurrent unit,GRU)利用能量组合算子特征对混合信号进行突变点检测,定位运动态数据起始点;第2层双向长短时记忆循环神经网络(Bi-directional long short term memory,BiLSTM)使用能量核相图特征对运动态混合信号进行2个方向10种手势的分类。通过离线模型优化,分类算法识别时间低于40 ms,突变点检测精度88.7%以上,手势分类准确率为85%,信息传输率(informationtranslaterate, ITR)达到89.9 bits/min,与基于机器学习的分类算法相比,在准确率与计算效率上具有优势。
基金funded by the National Key Research and Development Program of China(2017YFB1303200)NSFC(81871444,62071241,62075098,and 62001240)+1 种基金Leading-Edge Technology and Basic Research Program of Jiangsu(BK20192004D)Jiangsu Graduate Scientific Research Innovation Programme(KYCX20_1391,KYCX21_1557).
文摘In this article,to reduce the complexity and improve the generalization ability of current gesture recognition systems,we propose a novel SE-CNN attention architecture for sEMG-based hand gesture recognition.The proposed algorithm introduces a temporal squeeze-and-excite block into a simple CNN architecture and then utilizes it to recalibrate the weights of the feature outputs from the convolutional layer.By enhancing important features while suppressing useless ones,the model realizes gesture recognition efficiently.The last procedure of the proposed algorithm is utilizing a simple attention mechanism to enhance the learned representations of sEMG signals to performmulti-channel sEMG-based gesture recognition tasks.To evaluate the effectiveness and accuracy of the proposed algorithm,we conduct experiments involving multi-gesture datasets Ninapro DB4 and Ninapro DB5 for both inter-session validation and subject-wise cross-validation.After a series of comparisons with the previous models,the proposed algorithm effectively increases the robustness with improved gesture recognition performance and generalization ability.
文摘The human-computer interaction (HCI) is now playing a great role in computer technology. This study introduces an automatic document control technique which is based on the human hand waving movements. The recognition of hand movement is realized according to the surface electromyography (sEMG). A collector is set on the forearm. The sEMG signal is recorded and conveyed to a PC terminal by using wireless Zigbee. An automatic algorithm is developed in order to extract the characteristics of sEMG, recognize the waving movements, and transmit to document control command. The developed human-computer interaction technique can be used as a new gallery for teaching, as well as an assistant tool for disabled person.
基金The Research and the Development Fund of the Institute of Environmental Friendly Materials and Occupational Health,Anhui University of Science and Technology,Grant/Award Number:ALW2022YF06Academic Support Project for Top-Notch Talents in Disciplines(Majors)of Colleges and Universities in Anhui Province,Grant/Award Number:gxbjZD2021052+1 种基金The University Synergy Innovation Program of Anhui Province,Grant/Award Number:GXXT-2022-053Anhui Province Key R&D Program of China,Grant/Award Number:2022i01020015.
文摘Surface electromyography(sEMG)is widely used for analyzing and controlling lower limb assisted exoskeleton robots.Behavior intention recognition based on sEMG is of great significance for achieving intelligent prosthetic and exoskeleton control.Achieving highly efficient recognition while improving performance has always been a significant challenge.To address this,we propose an sEMG-based method called Enhanced Residual Gate Network(ERGN)for lower-limb behavioral intention recognition.The proposed network combines an attention mechanism and a hard threshold function,while combining the advantages of residual structure,which maps sEMG of multiple acquisition channels to the lower limb motion states.Firstly,continuous wavelet transform(CWT)is used to extract signals features from the collected sEMG data.Then,a hard threshold function serves as the gate function to enhance signals quality,with an attention mechanism incorporated to improve the ERGN’s performance further.Experimental results demonstrate that the proposed ERGN achieves extremely high accuracy and efficiency,with an average recognition accuracy of 98.41%and an average recognition time of only 20 ms-outperforming the state-of-the-art research significantly.Our research provides support for the application of lower limb assisted exoskeleton robots.
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.
