基于文化算法的表面肌电信号特征选择

被引:1
作者
许璇 [1 ]
谢洪波 [1 ]
黄虎 [1 ]
杨瑞凯 [2 ]
机构
[1] 江苏大学电气信息工程学院
[2] 茌平县供电公司
关键词
表面肌电信号; 文化算法; 特征选择; 遗传算法; 模式识别;
D O I
暂无
中图分类号
TN911.7 [信号处理];
学科分类号
0711 ; 080401 ; 080402 ;
摘要
为了提高假肢控制系统肌电信号的分类准确率,提出一种新的基于文化算法的特征选择方法,通过该方法选择出最佳特征向量,然后用线性分类器检验其分类性能。利用表面差分电极从人体上肢四块肌肉采集四通道的肌电信号,对十个健康受试者进行八个动作的肌电信号模式分类实验,并同时用标准遗传算法来与文化算法作比较。实验结果表明,文化算法与遗传算法相比,特征维数更小,分类准确度更高。
引用
收藏
页码:910 / 912
页数:3
相关论文
共 9 条
[1]  
Multi-objective cultural algorithms. REYNOLDS R,LIU Da-peng. Proc of IEEE Congress on Evolutionary Computation . 2011
[2]  
A wavelet-basedcontinuous classification scheme for multifunction myoelectric control. ENGLEHART K,HUDGINS B,PARKER P A. IEEE Transactions on Biomedical Engineering . 2001
[3]  
A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control. Chu, J -U.,I. Moon,Y.-J. Lee. IEEE ASME Transactions on Mechatronics . 2007
[4]  
Aneural network model for reconstructing EMG signals from eight shoul-der muscles:consequences for rehabilitation robotics and biofeedback. RITTENHOUSE D M,ABDULLAH H A,RUNCIMAN R J,et al. Journal of Biomechanics . 2006
[5]   肌电信号的特征分析方法及其应用 [J].
许栋岳 ;
李克勇 .
现代生物医学进展, 2010, 10 (13) :2593-2596
[6]  
Cultural algorithms:modeling of howcultures learn to solve problems. REYNOLDS R G,PENG Bin. Proc of the 16th IEEE Interna-tioanl Conference on Tools with Artificial Intelligence . 2004
[7]  
A heuristic fuzzy logic approach to EMGpattern recognition for multifunctional prosthesis control. AJIBOYE A B,WEIR R F. IEEETrans on Neural Systems and Rehabilitation Engineering . 2005
[8]  
Boosting cultural al-gorithms with an incongruous layered social fabric influence function. ALI M Z,SALHIEH A,SNANIEH R T A,et al. Proc of IEEE Congress on Evolutionary Computation . 2011
[9]  
Classification of surface EMG signal using relative wavelet packet energy. Xiao Hu,Zhizhong Wang,Xiaomei Ren. Computer Methods . 2005