摘要
为提高对表面肌动作识别的准确性,提出一种小波变换与粒子群优化支持向量机(PSO-SVM)相结合的模式分类方法。通过虚拟仪器采集肱桡肌和尺侧腕屈肌的两路表面肌电信号,运用小波变换对其进行多尺度分解,提取小波系数最大值作为表面肌动作特征,采用支持向量机(SVM)进行特征分类,并在分类过程中引入粒子群算法对SVM的惩罚参数和核函数参数进行寻优。实验结果表明,采用此方法能成功地识别表面肌内翻、外翻、握拳、展拳4种动作,较传统SVM方法有更高的分类精度。
In order to improve the accuracy of surface electromyogram movement pattern classification, a newclassification method based on the combination of wavelet transform and particle swarm optimization-supportvector machine （PSO-SVM） was proposed. Firstly, two surface electromyography signals from channels ofbrachioradialis muscle and flexor carpi ulnaris were acquired with virtual instruments. Secondly, the wavelettransform was used to decompose the surface electromyography, and the maximum value of wavelet coefficientswas extracted as the feature vector of the surface electromyogram movement pattern. Finally, take the features asthe input, SVM classifier was employed to classify the surface electromyogram pattern, and in which PSOalgorithm was used to optimize the penalty parameter and kernel function of SVM. Experimental results show thatfour movement patterns of wrist down, wrist up, hand grasps, hand extension are successfully classified with theproposed pattern classification method, which has higher classification accuracy than that of traditional one.
出处
《安徽工业大学学报（自然科学版）》
CAS
2016年第3期272-277,共6页
Journal of Anhui University of Technology（Natural Science）
基金
国家自然科学基金项目(61375068)
安徽省高等学校自然科学研究重点项目(KJ2016A813
KJ2013A056)
关键词
表面肌电信号
小波变换
粒子群优化算法
支持向量机
surface electromyography
wavelet transform
particle swarm optimization algorithm （PSO）
supportvector machine （SVM）
