Modeling and Classifying of sEMG Based on FFT Blind Identification
-
摘要: 针对表面肌电信号(Electromyographic signal,sEMG)产生原理复杂、易受人体自身及外界因素影响的特点,采用基于快速傅里叶变换(Fast Fourier transform,FFT)的盲辨识方法建立肌电信号模型.该方法通过计算即可确定信道阶次,无需人为凭借经验设定,且计算简单、易于实现、运算速度快.其利用输出信道间的相互关系特性,实现信号的频域盲辨识,建立数学模型.此方法适用于小样本信号建模,非常适合易受肌肉疲劳影响的表面肌电信号.将模型系数作为改进的BP神经网络的输入,实现多运动模式识别,与其他盲辨识方法比较,此方法识别效果较好.Abstract: In this paper, the FFT-based blind identification method is used to establish surface electromyographic signal (sEMG) in order to overcome the disadvantage of sEMG, which is susceptible to muscle fatigue and external factors. With no assumption on the precise knowledge of channel order, the FFT (fast Fourier transform)-based method is able to estimate the channel parameters as well as determine channel order. It extends the cross-relation principle to the frequency domain via the discrete Fourier transform, and performs better in small sample signal modeling, which is suitable for sEMG. The parameters of sEMG model are used as the input of the improved BP neural network to classify different movement patterns and a better recognition result is achieved compared with other blind identification methods.
-
[1] Li Y,Tian Y T,Chen W Z. Multi-pattern recognition of sEMG based on improved BP neural network algorithm. In:Proceedings of the 29th Chinese Control Conference. Beijing,China:IEEE,2010. 2867-2872[2] Xu G,Liu H,Tong L,Kailath T. A least-squares approach to blind channel identification. IEEE Transactions on Signal Processing,1995,43(12):2982-2993[3] Bai E W,Fu M Y. A blind approach to Hammerstein model identification. IEEE Transactions on Signal Processing,2002,50(7):1610-1619[4] Narasimhan S V,Hazarathaiah M,Giridhar P. Channel blind identification based on cyclostationarity and group delay. Signal Processing,2005,85(7):1275-1286[5] Fang J,Leymanb A R,Chew Y H,Duan H P. Some further results on blind identification of MIMO FIR channels via second-order statistics. Signal Processing,2007,87(6):1434-1447[6] Xu Xiao-Ping,Qian Fu-Cai,Wang Feng. New method for identification of Wiener-Hammerstein model. Control and Decision,2008,23(8):929-934(徐小平,钱富才,王峰. 一种辨识Wiener-Hammerstein模型的新方法. 控制与决策,2008,23(8):929-934)[7] Li Y,Tian Y T,Shang X J,Chen W Z. Modeling and classification of sEMG based on blind identification theory. In:Proceedings of the 8th International Symposium on Neural Networks. Guilin,China:Springer,2011. 340-347[8] Shang X J,Tian Y T,Li Y. Modeling and classification of sEMG based on instrumental variable identification. In:Proceedings of the 8th International Symposium on Neural Networks. Guilin,China:IEEE,2011. 331-339[9] Huang Y,Jacob B,Chen J. Using the Pearson correlation coefficient to develop an optimally weighted cross relation based SIMO identification algorithm. In:Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing. Taipei,China:IEEE,2009. 3153-3156[10] Chen Rong,Xu Yong-Mao,Lan Hong-Sen. Research on multilayered feedforward neural networks:genetic back propagation algorithm and structure optimization strategy. Acta Automatica Sinica,1997,23(1):43-49(陈荣,徐用懋,兰鸿森. 多层前向网络的研究---遗传BP算法和结构优化策略. 自动化学报,1997,23(1):43-49)[11] Yang Juan,Lu Yang,Huang Zhen-Jin,Wang Qiang. Hamming sphere dimple in binary neural networks and its linear separability. Acta Automatica Sinica,2011,37(6):737-745(杨娟,陆阳,黄镇谨,王强. 二进神经网络中的汉明球突及其线性可分性. 自动化学报,2011,37(6):737-745)[12] Wang Li-Fang,Zeng Jian-Chao. A cooperative evolutionary algorithm based on particle swarm optimization and simulated annealing algorithm. Acta Automatica Sinica,2006,32(4):630-635(王丽芳,曾建潮. 基于微粒群算法与模拟退火算法的协同进化方法. 自动化学报,2006,32(4):630-635)[13] Ban Xiao-Juan,Liu Hao,Xu Zhuo-Ran. An energy artificial neuron model based self-growing and self-organizing neural network. Acta Automatica Sinica,2011,37(5):615-622(班晓娟,刘浩,徐卓然. 一种基于能量人工神经元模型的自生长、自组织神经网络. 自动化学报,2011,37(5):615-622)
点击查看大图
计量
- 文章访问数: 2244
- HTML全文浏览量: 70
- PDF下载量: 944
- 被引次数: 0