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.
