Recognizing Hand Motions Based on Fault-tolerant Classification with EMG Signals
DING Qichuan1,2, ZHAO Xingang1, HAN Jianda1
1. State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China
In view of the fault/missing data problem caused by disconnected/damaged electrodes and data-transmission interrupting in myoelectric-interface systems, an EMG (electromyography) fault-tolerant classification method based on Gaussian mixture model is proposed, with which an incomplete-data sample can be classified via marginalizing or conditional-mean imputation of the fault/missing data in the EMG feature sample. The proposed method is applied to recognizing five kinds of hand motion. Experimental results show that the proposed method can provide higher motion-recognition accuracy than that by the traditional zero and mean imputation methods. Finally, a myoelectric-hand platform is developed by involving the fault-tolerant classification mechanism, and the online experiments show that the proposed method can effectively improve the robustness of myoelectric-interface systems.
[1] Pons J L. Wearable robots: Biomechatronic exoskeletons[M]. Hoboken, USA: Wiley, 2008.[2] 杨大鹏,赵京东,李楠,等.基于预抓取模式识别的假手肌电控制方法[J].机械工程学报,2012,48(15):1-8.// Yang D P, Zhao J D, Li N, et al. Recognition of hand grasp preshaping patterns applied to prosthetic hand electromyography control[J]. Journal of Mechanical Engineering, 2012, 48(15): 1-8.[3] 罗志增,杨广映.基于触觉和肌电信号的假手模糊控制方法研究[J].机器人,2006,28(2):224-228.// Luo Z Z, Yang G Y. Prosthetic hand fuzzy control based on touch and myoelectric signal[J]. Robot, 2006, 28(2): 224-228.[4] Chu J U, Moon I, Lee Y J, et al. A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control[J]. IEEE/ASME Transactions on Mechatronics, 2007, 12(3): 282-290. [5] Al-Timemy A H, Bugmann G, Escudero J, et al. Classification of finger movements for the dexterous hand prosthesis control with surface electromyography[J]. IEEE Journal of Biomedical and Health Informatics, 2013, 17(3): 608-618. [6] Cavallaro E E, Rosen J, Perry J C, et al. Real-time myoprocessors for a neural controlled powered exoskeleton arm[J]. IEEE Transactions on Biomedical Engineering, 2006, 53(11): 2387-2396. [7] Zhang F, Li P F, Hou Z G, et al. sEMG-based continuous estimation of joint angles of human legs by using BP neural network[J]. Neurocomputing, 2012, 78(1): 139-148. [8] Sankai Y. HAL: Hybrid assistive limb based on cybernics [M]//13th International Symposium on Robotics Research. Berlin, Germany: Springer, 2011: 25-34.[9] Fleischer C, Hommel G. A human-exoskeleton interface utilizing electromyography[J]. IEEE Transactions on Robotics, 2008, 24(4): 872-882. [10] Ahsan M R, Ibrahimy M I, Khalifa O O. EMG signal classification for human computer interaction: A review[J]. European Journal of Scientific Research, 2009, 33(3): 480-501.[11] 张启忠,席旭刚,罗志增.基于非线性特征的表面肌电信号模式识别方法[J].电子与信息学报,2013,35(9):2054-2058.// Zhang Q Z, Xi X G, Luo Z Z. A pattern recognition method for surface electromyography based on nonlinear features[J]. Journal of Electronics & Information Technology, 2013, 35(9): 2054-2058.[12] Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification[J]. Expert Systems with Applications, 2012, 39(8): 7420-7431. [13] 许璇,谢洪波,黄虎,等.基于文化算法的表面肌电信号特征选择[J].计算机应用研究,2012,29(3):910-912.// Xu X, Xie H B, Huang H, et al. Feature selection for surface electromyography signal using cultural algorithm[J]. Application Research of Computers, 2012, 29(3): 910-912.[14] Young A J, Smith L H, Rouse E J, et al. Classification of simultaneous movements using surface EMG pattern recognition[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(5): 1250-1258. [15] Tkach D, Huang H, Kuiken T A. Study of stability of time-domain features for electromyographic pattern recognition[J]. Journal of NeuroEngineering and Rehabilitation, 2010, 7: No.21.[16] Katmeoka H, Nishimoto T, Sagayama S. Separation of harmonic structures based on tied Gaussian mixture model and information criterion for concurrent sounds[C]//IEEE International Conference on Acoustics, Speech, and Signal Processing, Piscataway, USA: IEEE, 2004: 297-300.[17] Bishop C M. Pattern recognition and machine learning[M]. New York, USA: Springer, 2006.
