| 基于sEMG的特征包络线提取与动作识别研究 |
| |
| 引用本文： | 高峰,杨彬,鲍官军,王志恒.基于sEMG的特征包络线提取与动作识别研究[J].应用声学,2017,25(3):213-216. |
| |
| 作者姓名： | 高峰 杨彬 鲍官军 王志恒 |
| |
| 作者单位： | 浙江工业大学 特种装备制造与先进加工技术教育部省重点实验室,杭州 310014,浙江工业大学 特种装备制造与先进加工技术教育部省重点实验室,杭州 310014,浙江工业大学 特种装备制造与先进加工技术教育部省重点实验室,杭州 310014,浙江工业大学 特种装备制造与先进加工技术教育部省重点实验室,杭州 310014 |
| |
| 基金项目： | 国家自然科学基金(51405441)；浙江省重点科技创新团队项目(2011R50011)；浙江省自然科学基金(Q15E050025)。 |
| |
| 摘 要： | 针对表面肌电信号模式识别在康复器械以及智能假肢中的应用问题,通过平方调解法来提取多通道sEMG特征包络线,以提高手指动作识别速率与正确率；首先将手指动作采集实验获取的表面肌电信号进行平方处理,再经低通滤波形成包络线；利用幅值乘方法对不同的动作类型的包络线进行处理并形成学习用的教师样本标签,最后通过BP神经网络完成动作的识别分类；实验结果显示,屈拇指、屈食指、屈中指、屈无名指、屈小指和屈五指这6种动作的平均识别正确率为94.93%,每次动作识别的平均延时为50.7 ms。
|
| 关 键 词： | 表面肌电信号 特征包络线 平方调解法 样本标签 BP神经网络 |
| 收稿时间： | 2016/10/21 0:00:00 |
| 修稿时间： | 2016/11/24 0:00:00 |
Research on Feature Envelope Extraction and Motion Recognition Based on Surface Electromyographic Signals |
| |
| Gao Feng,Yang Bin,Bao Guanjun and Wang Zhiheng.Research on Feature Envelope Extraction and Motion Recognition Based on Surface Electromyographic Signals[J].Applied Acoustics,2017,25(3):213-216. |
| |
| Authors: | Gao Feng Yang Bin Bao Guanjun and Wang Zhiheng |
| |
| Institution: | Ministerial and Provincial Key Laboratory of E&M,Zhejiang University of Technology,Hangzhou 310014, China,Ministerial and Provincial Key Laboratory of E&M,Zhejiang University of Technology,Hangzhou 310014, China,Ministerial and Provincial Key Laboratory of E&M,Zhejiang University of Technology,Hangzhou 310014, China and Ministerial and Provincial Key Laboratory of E&M,Zhejiang University of Technology,Hangzhou 310014, China |
| |
| Abstract: | On study of surface electromyographic signals (sEMG) pattern recognition in rehabilitation equipment and intelligent prosthetic applications, a square-mediation method that extracts the envelope of multi-channel sEMG features is presented, with which the finger gesture recognition rate and accuracy rate is improved. In the process, the sEMG is squared by the finger movement acquisition experiment, and then the envelope was formed through the low-pass filtering. Using the amplitude-multiplication method, the envelope of different types of finger action is used to creat the teacher sample label. With these label, the BP neural network is used to accomplish the recognition and classification of the action. Experimental results show that the average correct rate of finger behavior recognition is 94.93% , including thumb, index finger, middle finger, ring finger, little finger and all finger flexion actions. The average time delay for each action recognition is 50.7 ms. |
| |
| Keywords: | Surface Electromyographic Signals (sEMG) feature envelope square-mediation method sample label BP neural network |
|
| 点击此处可从《应用声学》浏览原始摘要信息 |
| 点击此处可从《应用声学》下载免费的PDF全文 |
|
