中国组织工程研究

中国组织工程研究 ›› 2010, Vol. 14 ›› Issue (4): 645-648.doi: 10.3969/j.issn.1673-8225.2010.04.017

• 数字化骨科 digital orthopedics • 上一篇    下一篇

基于双谱分析表面肌电信号特征的提取与模式识别

邱青菊，朱向阳   

  1. 上海交通大学，上海市  200030
  • 出版日期:2010-01-22 发布日期:2010-01-22
  • 作者简介:邱青菊，主要从事机械方面的研究。 changeily@163.com
  • 基金资助:

    国家杰出青年科学基金资助项目(50525517) *；上海市重点基础研究项目(05jc140 27)*

Feature extraction and pattern recognization of surface electromyography signal based on bispectrum analysis

Qiu Qing-ju, Zhu Xiang-yang   

  1. Shanghai Jiao Tong University, Shanghai  200030, China
  • Online:2010-01-22 Published:2010-01-22
  • About author:Qiu Qing-ju, Shanghai Jiao Tong University, Shanghai 200030, China changeily@163.com
  • Supported by:

    the National Science Funds for Distinguished Young Scholar, No. 50525517*; Key Program for Basic Research of Shanghai, No. 05jc14027*

PDF

724

被引次数

42

摘要：

背景：肌电信号在本质上是一种具有非平稳、非高斯特性的生理信号。目前基于高阶累积量的高阶谱技术广泛应用于非高斯、非平稳、非线性等问题。
目的：基于非高斯AR参数模型，将双谱分析和fisher线性判别分析方法相结合进行表面肌电信号特征提取。
方法：针对表面肌电信号特点，从信号高阶统计处理角度，基于“非高斯AR参数模型”进行双谱分析，提取有效特征，用fisher线性判别分析降维方法构造特征向量，然后利用支持向量机实现不同动作模式的准确分类。并与多种常用表面肌电信号特征的识别准确率进行对比研究。
结果与结论：利用多类支持向量机分类器对8种前臂动作进行分类，8种动作的平均识别率达到97.6%以上。通过比较发现，基于短数据的双谱特征在分类性能上优于AR模型系数、小波包系数等构造的特征，能够提高肌电假肢的实时控制的性能。

关键词: 肌电信号, 双谱, 非高斯AR模型, 模式识别, 数字化医学

Abstract:

BACKGROUND: Electromyography is a non-stationary and non-Gaussian physiological signal. Currently, the high-order spectral technique, which based on higher-order cumulant, has been widely used in solving problems such as non-Gaussian, non-stationary and nonlinearity.
OBJECTIVE: To propose a feature extraction method for surface electromyography (SEMG) signals based on a non-Gaussian AR model parameterized bispectrum estimation and fisher linear discriminant analysis.
METHODS: Aim at features of SEMG, from point of high statistics, and based on a non-Gaussian AR model, bispectrum analysis was performed to extract effective features, followed by constructing characteristic vector by fisher linear discriminant analysis dimension reduction, then the support vector machine was used to classify the movement patterns. The differences of recognition rates between AR+BIS+LDA and other features extracted by different methods were compared. 
RESULTS AND CONCLUSION: Experimental results showed that the eight forearm movement patterns could be well identified after training by multi-class support vector machine and its average recognition rate reached above 97.6%. For short data sets, bispectrum’s feature had a better pattern recognition rate than other features such as AR model coefficients, wavelet packet transformation coefficients. That improved the performance of real-time control of prosthesis.

中图分类号: