文献类型：期刊文献

英文题名：Incremental learning of upper limb action pattern recognition based on mechanomyography

作者：Zhao, Tongtong[1];Cao, Gangsheng[1];Zhang, Yue[2];Zhang, Hanyang[1];Xia, Chunming[1,3]

机构：[1]East China Univ Sci & Technol, Sch Mech & Power Engn, Shanghai 200237, Peoples R China;[2]Nantong Univ, Sch Mech Engn, Jiangsu Prov 226001 China, Nantong, Peoples R China;[3]Shanghai Univ Engn Sci, Sch Mech & Automot Engn, Shanghai 201620, Peoples R China

年份：2023

卷号：79

外文期刊名：BIOMEDICAL SIGNAL PROCESSING AND CONTROL

收录：;EI(收录号：20223412607909);WOS:【SCI-EXPANDED(收录号:WOS:000848346800007)】；

语种：英文

外文关键词：Upper limb rehabilitation action; Mechanomyography; Non -identical distribution; Incremental learning; Deep neural network

摘要：Aiming at the problem that the traditional mechanomyography (MMG) pattern recognition model for upper limb rehabilitation action has poor recognition effect on non-identical distribution test data, this research proposes an incremental learning method for deep learning based on MMG. By collecting 8-channels of MMG of 4 types of hand movements (wrist flexion, wrist extension, wrist ulnar flexion, and wrist radial flexion), after signal pre-processing, feature extraction and dimensionality reduction, 12 groups of non-identical distributed data were obtained. The model was trained by using deep neural network (DNN), and five commonly used machine learning algorithms were used as comparison for incremental training. Finally, the recognition rate of DNN was 88.25%, and the final recognition rates of Passive Aggressive (PA), Incremental Support Vector Machine (ISVM), Perceptron, Bernoulli Naive Bayes (BNB) and Multinomial Naive Bayes (MNB) were 85.94%, 84.82%, 81.01%, 73.07% and 61.20% respectively. Among them, both DNN and PA had better upward trends, and DNN had the highest final recognition rate. By comparing the confusion matrices before and after DNN incremental learning, it could be seen that DNN incremental training can significantly improve the accuracy and precision in confusion matrix. The experimental results demonstrate that the method of incremental learning can not only achieve the recognition of non-identically distributed test data, but also improve the recognition rates and the generalization performance of the model.