华中科技大学学报（自然科学版）Issue(z1)：74-77,4.DOI:10.13245/j.hust.15S1018
基于 DBN 的 sEMG 智能轮椅人机交互系统
Human-machine interaction system of sEMG based on DBN
摘要
Abstract
On the basis of intelligent wheelchair controlled by signals from sEMG (surface electromyo-graphy).Firstly,sEMG signals generated by the facial movements were collected and analyzed by u-sing a CyberLink device.DBN (deep belief network)was used to recognize different movement pat-terns of sEMG signal.An information accessibility HMI was designed to map facial movement pat-terns into corresponding control commands.Experiments show that compared to SVM (support vec-tor machine),DBN can effectively deal with a large number of sEMG signal samples,and the highest recognition rate can reach 95.25%,which effectively reduces the processing time of a large amount of data,enhances the real-time of the intelligent wheelchair,and improves recognition rate of the sEMG signal.关键词
人机交互/表面肌电信号/深度信任网络/支持向量机/智能轮椅Key words
human-machine interaction/sEMG/DBN/SVM/intelligent wheelchair分类
信息技术与安全科学引用本文复制引用
蔡军,李玉兰..基于 DBN 的 sEMG 智能轮椅人机交互系统[J].华中科技大学学报（自然科学版）,2015,(z1):74-77,4.基金项目
国家自然科学基金资助项目（60905066，51075420）；科技部国际合作项目（2010DFA12160）． （）
