北京生物医学工程

基于经验公式的连续手势动作表面肌电信号识别方法

Continuous hand gesture surface electromyography recognition method based on empirical formula

作者：朱旭鹏陈香李云赵璋炎

单位：中国科学技术大学（合肥 230027）

分类号：

出版年·卷·期（页码）：2012·31·2（117-124）

摘要：

目的实现连续手势动作表面肌电信号（surface electromyography，sEMG）的简单有效识别。方法首先推导出测试信号属于手势动作模板的概率密度经验公式，通过数据处理实验确定公式参数，最后设计连续手势识别实验以测试该经验公式用于动作sEMG识别的效果。结果推导出的经验公式在连续手势识别中获得了较好的识别结果，验证了该经验公式用于连续手势动作sEMG信号识别的有效性。结论基于经验公式的方法为实现基于sEMG信号的连续手势识别提供了一种可行的解决方案。

Objective To realize the continuous hand gesture recognition using surface electromyography(sEMG). Methods A method for continuous hand gesture recognition based on an empirical formula is proposed. This method consists of three steps. First，a formula to describe the probability of testing samples belonging to each hand gesture class is derived from the hand gesture features. Next，the empirical coefficients for the formula are determined by a data processing experiment. Finally，the performance of sEMG classification based on the proposed empirical formula is quantified via the experiment on continuous hand gesture recognition. Results The empirical coefficients for the formula are able to be determined by experimental method effectively，and promising results on the EMG-based continuous hand gesture recognition can be achieved through the proposed empirical formula. The experimental results demonstrate the effectiveness of applying such empirical formula on sEMG-based hand gesture recognition. Conclusions The proposed method using empirical formula provides a practical solution to sEMG-based real-time continuous hand gesture recognition.

参考文献：

［1］阮迪云，寿天德. 神经生理学［M］. 合肥：中国科学技术大学出版社，1992.
Ruan DY, Shou TD. Neurophysiology［M］. Hefei: University of Science and Technology of China Press, 1992.
［2］Oskoei MA，Hu HS. Myoelectric control systems-a survey［J］. Biom Sig Proc and Con， 2007，2(4)：275-294.
［3］Naik GR，Kumar DK, Jayadeva.Twin SVM for gesture classification using the surface electromyogram［J］. IEEE Trans on Infor Tech in Biom，2010，14(2)：301-308.
［4］何乐生. 基于肌电信号的人机接口技术的研究［D］.南京：东南大学,2006.
［5］涂有强，陈香，张旭，等.一种适用于手势动作sEMG 信号识别的改进型模糊推理分类器［J］. 北京生物医学工程，2008,27(4)：362-366，392.
Tu YQ, Chen X, Zhang X, et al. Review of finite element models used in neck injury caused by autombile accidents［J］. Beijing Biomedical Engineering, 2008,27(4): 362-366, 392.
［6］Zhao ZY， Chen X， Zhang X，et al. Study on online gesture sEMG recognition［J］. Intelligent Computing(ICIC 2007)，Lecture Note in Computer Science，2007，4681：1257-1265.
［7］Ju Z， Liu H. Empirical copula driven hand motion recognition via surface electromyography based templates［J］. Intelligent Robotics and Applications，Lecture Notes in Computer Science，2010，6424：71-80.
［8］ Li G，Li Y，Zhang Z，et al，Selection of sampling rate for EMG pattern recognition based prosthesis control［C］. Proc of IEEE EMBS，2010:5058-5061.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录