基于分形维前臂动作表面肌电信号的分类(英文)

被引：6

作者：

胡晓

王志中

任小梅

机构：

[1] 上海交通大学生物医学工程系

[2] 上海交通大学生物医学工程系上海

[3] 上海

来源：

JournalofSoutheastUniversity(EnglishEdition) | 2005年 / 03期

关键词：

动作表面肌电信号; 分形维; 小波包变换; 模糊自相似性; Bayes决策;

D O I：

暂无

中图分类号：

R318.04 [生物信息、生物控制];

学科分类号：

0831 ;

摘要：

通过分形维对表面肌电信号进行识别分类.在30个健康志愿者做前臂内旋和外旋时,从他们的右前臂肌前群分别采集2类动作表面肌电信号.当原始动作表面肌电信号用小波包变换分解成几个子信号后,采用一种基于模糊自相似性的方法计算原始信号和4个子信号的分形维.结果表明:从频带0～125Hz的子信号求得的内旋和外旋动作表面肌电信号的分形维有各自的范围;通过该分形维进行Bayes决策时,错误识别率仅2·26%.因此,该分形维适合用来识别内旋和外旋动作表面肌电信号.

引用

页码：324 / 329

页数：6

共 12 条

[1]

Real-time implementation of electromyogram pattern recognition as a control command ofman-machine interface. Chang G C,KangW J,Luh J J,et al. Medical Engineering and Physics . 1996

[2]

Measurements of fractal dimension by box-counting: a critical analysis of data scatter. Buczkowski S,H ildgen P,Cartilier L. Physica A Statistical Mechanics and its Applications . 1998

[3]

Physiological measurement[P]. 英国专利:GB2009413A,1979-06-13

[4]

D igital filter design for peak detection of surface EMG. Xu Z Q,X iao S J. Journal ofElectromyography and Kinesiology . 2000

[5]

Measuring the strangeness of strange attractors. Grassberger P,Procaccia I. Physica D Nonlinear Phenomena . 1983

[6]

Characterization ofmedical time series using fuzzy sim ilarity-based fractal dimensions. SarkarM,Leong T Y. Artificial Intelligence . 2003

[7]

Detecting nonlinearity of action surface EMG signal. LeiM,W ang Z Z,Feng Z J. Physics Letters . 2001

[8]

Nonlinear dynam ics, delay times, and embedding windows. K im H S,Eykholt R,Salas J D. Physica D Nonlinear Phenomena . 1999

[9]

C lassification of the myoelectric signal using time-frequency based representations. Englehart K,Hudgins B,Parker P A,et al. Medical Engineering and Physics . 1999

[10]

Entropy-based algorithms for best basis selection. Coifman R R,W ickerhauserM V. IEEE Transactions on Information Theory . 1992

← 1 2 →