Abstract：Pattern recognition is one of the hot researches in the braincomputer interface technology. In order to solve the problems in BCI, such as movement pattern singleness and low recognition rate, a hBCIbased strategy fusioning the features of EEG and EMG was proposed to realize the classification of different motor patterns with unilateral limb. In the present study, the eventrelated desynchronization features and intergrated electromyogram features were abstracted based on the EEG over brain scope and EMG from flexor carpi ulnaris and extensor carpi radialis longus under wrist flexion or extension in 9 healthy subjects. Secondly, the pattern recognition model fusioning the features of EEG and EMG, based on the theories of support vector machine and particle swarm optimization, was designed to classify optimally by adjusting the feature fusion coefficient. Furthermore, the proposed method was verified based on the EMG signals of patients or healthy subjects under fatigue state, which were simulated by descending the EMG amplitude of healthy subjects. Results showed that the recognition rate based on the fusion of EEG and EMG (98%) improved 25% compared to sole EEG feature under natural condition (73%); the recognition rate reached a stable level above 80% and improved 14% compared to sole EMG feature under fatigue state. It is revealed that the fusion of EEG and EMG feature contributed to improve the accuracy of pattern recognition and stability of movement, and provided the basis for the application of hybrid braincomputer interface.
［1］Wolpaw JR, Birbaumer N, McFarland WJ, et al. Braincomputer interface technology: A review of the first international meeting ［J］. IEEE Trans Rehabil Eng, 2000, 8(2): 164-173.
［2］Pfurtscheller G, Flotzinger D, Kalcher J. Braincomputer interfacea new communication device for handicapped persons ［J］. Journal of Microcomputer Applications, 1993, 16(3): 293-299.
［3］Blankertz B, Dornhege G, Krauledat M, et al. The Berlin braincomputer interface presents the novel mental typewriter HexoSpell ［C］// Proceedings of the 3rd International BrainComputer Interface Workshop and Training Course. Graz: Verlag der Technischen Universitt Graz, 2006: 108-109.
［4］Brunner C, Allison BZ, Krusienski DJ, et al. Improved signal processing approaches in an offline simulation of a hybrid braincomputer interface ［J］. Journal of Neuroscience Methods, 2010, 188(1): 165-173.
［5］Scherer R, MüllerPutz GR, Pfurtscheller G. Selfinitiation of EEGbased braincomputer communication using the heart rate response ［J］. Journal of Neural Engineering, 2007, 4(4): L23-L29.
［6］李翔, 高小榕, 高上凯. 一种基于两种不同范式的混合型脑-机接口系统 ［J］. 中国生物医学工程学报, 2012, 31(3): 326-330.
［7］Leeb R, Sagha H, Chavarriaga R, et al. A hybrid braincomputer interface based on the fusion of electroencephalographic and electromyographic activities ［J］. Journal of neural engineering, 2011, 8(2): 1-5.
［8］罗志增, 李亚飞, 孟明. 用于手部动作识别的脑电和肌电信号混沌特征融合方法 ［P］. 中国专利: 101732110, 2012-11-07.
［9］Pfurtscheller G, Lopes da Silva FH. Eventrelated EEG/MEG synchronization and desynchronization: basic principles ［J］. Clin Neurophysiolo, 1999, 110(11): 1842-1857.
［10］Graimann B, Pfurtscheller G. Quantification and visualization of eventrelated changes in oscillatory brain activity in the timefrequency domain ［J］. Progr Brain Res, 2006, 159: 79-97.
［11］Kalcher J, Pfurtscheller G. Discrimination between phaselocked and nonphaselocked eventrelated EEG activity ［J］. Electroencephalography and Clinical Neurophysiology, 1995, 94(5): 381-384.
［12］Tangwiriyasakul C, Verhagen R, van Putten MJAM, et al. Importance of baseline in eventrelated desynchronization during a combination task of motor imagery and motor observation ［J］. Journal of Neural Engineering, 2013, 10(2): 1-9.
［13］Dimitrova NA, Dimitrov GV. Interpretation of EMG changes with fatigue: facts, pitfalls and fallacies ［J］. Electromyogr Kinesiol, 2003, 13(1): 13-36.
［14］Conway BA, Halliday DM, Shahani U, et al. Common frequency components identified from correlations between magnetic recordings of cortical activity and the electromyogram in man ［J］. J Physiol, 1995, 483: 35.
［15］王勇. 数据融合技术综述 ［J］. 计算机测量与控制, 2002, 10(11): 706-709.
［16］Poli R, Kennedy J, Blackwell T. Particle swarm optimization ［J］. Swarm Intelligence, 2007, 1(1): 33-57.
［17］Pfurtscheller G, Neuper C. Motor imagery and direct brain computer communication ［J］. Proc IEEE, 2001, 89(7): 1123-1134．
［18］Nam CS, Jeon Y, Kim YJ, et al. Movement imageryrelated lateralization of eventrelated (de)synchronization (ERD/ERS): Motorimagery duration effects ［J］. Clin Neurophysiol, 2011, 122(3): 567-577.
［19］Salonikidis K, Amiridis I, Oxyzoglou N, et al. Wrist Flexors are Steadier than Extensors ［J］. Int J Sports Med, 2011, 32(10): 754-760.
［20］Little JW, Massagli TL. Spasticity and associated abnormalities of muscle tone ［C］ //DeLisa J, Gans B, eds. Rehabilitation Medicine Principles and Practice. Philadelphia: LippincotRaven Publishers, 1998: 997-1013.
［21］Yue GH, Liu JZ, Siemionow V, et al. Brain activation during human nger extension and exion movements ［J］. Brain Res, 2000, 856(1): 291-300.
［22］Divekar NV, John LR. Neurophysiological, behavioural and perceptual differences between wrist flexion and extension related to sensorimotor mooring as shown by corticomuscular coherence ［J］. Clinical Neurophysiology, 2013, 124(1): 136-147.
［23］谢平, 陈晓玲, 苏玉萍，等. 基于EMD\|多尺度熵和ELM的运动想象脑电特征提取和模式识别 ［J］. 中国生物医学工程学报, 2013, 32(6): 641-648.