|
|
|
| Feature Extraction and Recognition of Motor Imagery EEG Based on EMD-Multiscale Entropy and Extreme Learning Machine |
1 Institute of Electrical Engineering, Yanshan University, Qinhuangdao 066004, China
2 Department of Rehabilitation, Qinhuangdao People's Hospital, Qinhuangdao 066000, China |
|
|
|
|
Abstract Brain electrical rhythms features of motor imagery are an important basis to recognize the movement patterns and realize the biofeedbackbased rehabilitation therapy. Based on the recognition method of contralateral motion imagery EEG, the feature extraction method for unilateral motion imagery EEG in different patterns was studied in this paper. A new method based on EMD-multiscale entropy (MSE) was proposed to quantitatively describe the EEG transient feature, and a movement pattern recognition model based on extreme learning machine was designed. Furthermore, the present method was tested with the EEG data from 10 healthy subjects performing the flexion and extension motion of unilateral arm, and the validity of the proposed method was verified by the analysis of EEG feature extraction and movement recognition, and the recognition rate was higher than 90%. It is revealed that the EMD-MSE method can quantitatively describe the EEG transient feature under different patterns, and furthermore, the ELM based on feed forward neural network can recognize the movement patterns.
|
|
|
|
|
|
［1］高上凯.浅谈脑-机接口的发展现状与挑战 ［J］. 中国生物医学工程学报, 2007, 26(6): 801-803.
［2］Kamiya J. Biofeedback training in voluntary control of EEG alpha rhythms ［J］. California Medicine, 1971, 115(3): 44.
［3］Geng T, Gan JQ. Motor prediction in braincomputer interfaces for controlling mobile robots ［C］ // 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS'08). Vancouver: IEEE, 2008: 634-637.
［4］Shindo K, Kawashima K, Ushiba J, et al. Effects of neurofeedback training with an electroencephalogrambased braincomputer interface for hand paralysis in patients with chronic stroke: a preliminary case series study ［J］. J Rehabil Med, 2011, 43(10): 951-957.
［5］Murgrialday AR, Aggarwal Vikram, Chatterjee A. et al. Braincomputer interface for a prosthetic hand using local control and haptic feedback. Proceedings of the 2007 IEEE 10th international conference on rehabilitation robotics, 2007, 6(12-15): 609-613.
［6］徐宝国, 彭思, 宋爱国. 基于运动想象脑电的上肢康复机器人 ［J］. 机器人, 2011, 85(1): 52-66.
［7］Pfurtscheller G, Lopes da Silva FH. Eventrelated EEG/MEG synchronization and desynchronization: basic principles ［J］. Clin Neurophysiol, 1999, 110(11): 1842-1857.
［8］Muralidharan A, Chae J, Taylor DM. Extracting attempted hand movements from EEGs in people with complete hand paralysis following stroke ［J］. Front Neurosci, 2011, 5(25): 1-7.
［9］Andrea Biasiucci, Ricardo Chavrriaga, Benjamin Hammer et al. Combining discriminant and topographic information in BCI: preliminary results on stroke patients ［C］ // 5th International IEEE/EMBS Conference on Neural Engineering (NER 2011). Cancun: IEEE, 2011: 290-293.
［10］Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications ［J］. Neurocomputing, 2006, 70(1-3): 489-501.
［11］Huang GB, Zhu QY, Siew CK. Extreme learning machine: A new learning scheme of feedforward neural networks ［C］ // 2004 IEEE International Joint Conference on Neural Networks. Budapest: IEEE, 2004: 985-990.
［12］梁振虎. EEG熵算法及麻醉状态监测应用研究 ［D］. 秦皇岛: 燕山大学, 2012.
［13］Huang NE, Shen Z, Long SR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time series analysis ［J］. Proceedings of the Royal Society of London, Series A: Mathematical, Physical and Engineering Sciences, 1998, 454(1971): 903-995.
［14］蔡艳平, 李艾华, 王涛, 等. 基于EMDWignerVille的内燃机振动时频分析 ［J］. 振动工程学报, 2010, 23(4): 430-437.
［15］李小俚, 崔素媛. 基于希尔伯特黄熵的麻醉深度估计 ［J］. 中国生物医学工程学报, 2008, 27(5): 689-694.
|
|
|
|
