中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 重庆绿色智能技术研究院
  3. 中国科学院重庆绿色智能技术研究院
Identification of finger movements from forearm surface EMG using an augmented probabilistic neural network

文献类型：会议论文

作者Fu, Jianting1,2; Xiong, Liang1,2; Song, Xiaoying1,2; Yan, Zhuo1,2; Xie, Yi1,2
出版日期2018
会议日期December 11, 2017 - December 14, 2017
会议地点Taipei, Taiwan
DOI10.1109/SII.2017.8279278
页码547-552
英文摘要Surface Electromyography (sEMG) is a cumulated bioelectrical signal that represents the level of contraction in the musculature. The major muscles control the wrist and finger movements reside in the forearm. The surface EMG of the forearm muscles indicates the movement of wrist and fingers and leads to many applications, such as intelligent prostheses and exoskeletons. Wireless acquisition system has been recently used to collect the sEMG signal from the subject's forearm. In this study, raw EMG data is processed by a Time-Domain Auto-Regressive (TD-AR) model to extract its spatial features. We apply the Principal Component Analysis (PCA) method to reduce the dimensionality and then normalize the feature matrix. A Probabilistic Neural Network (PNN) model has been utilized to train the hand gesture predictor. Total 8 gestures from 5 subjects were selected to train and evaluate the model. The proposed identification model uses 6 channels and achieves stable recognition accuracy, including finger swinging motion. The average success rate of hand gestures identification is 92.2%. In order to visualize the experiment and simulate the control system, a finite state machine is built, which can be used to drive virtual hand or intelligent prostheses for future studies. © 2017 IEEE.
会议录2017 IEEE/SICE International Symposium on System Integration, SII 2017
语种英语
源URL[http://119.78.100.138/handle/2HOD01W0/7978]  
专题中国科学院重庆绿色智能技术研究院
作者单位1.Chongqing Institutes of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China;
2.University of Chinese Academy of Sciences, Beijing, China
推荐引用方式
GB/T 7714		 Fu, Jianting,Xiong, Liang,Song, Xiaoying,et al. Identification of finger movements from forearm surface EMG using an augmented probabilistic neural network[C]. 见:. Taipei, Taiwan. December 11, 2017 - December 14, 2017.

入库方式： OAI收割

来源：重庆绿色智能技术研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。