|
|
|
Feature extraction and classification of four-class
motor imagery EEG data |
| SHI Jin-he, SHENG Ji-zhong, WANG Pan |
| Institution of Electronic Circuit&Information System, Zhejiang University, Hangzhou 310027, China |
|
|
|
Abstract Due to the low information transfer rate and low recognition accuracy in brain computer interface (BCI), feature extraction and classification of multi-channel four-class motor imagery for electroencephalogram(EEG)-based BCI was investigated. Optimum filtering band was obtained for power spectral analysis of four-class motor imagery and resting EEG. Then, the PW-CSP, Hilbert transformation and normalization were used to extract the feature of EEG data. Classification was divided into two steps, the first step was arithmetic summation and threshold comparison, Secondly a single support vector machine (SVM) was applied if the first step failed. The algorithm was simpler than combined SVM, which provided the foundation for online application. The experimental results show that the algorithm produces high classification accuracy and less time consumption, moreover, classification result can be further improved at the expense of algorithmic complexity by adjust the threshold.
|
|
Published: 20 March 2012
|
|
|
四类运动想象脑电信号特征提取与分类算法
针对脑机接口(BCI)系统中存在的信息传输速率较慢和脑电信号识别正确率较低的问题,对多通道四类运动想象脑电信号进行研究.通过对4种运动想象及休息状态脑电信号进行功率谱分析,合理确定预处理滤波器的最佳滤波频段,然后使用PW-CSP,Hilbert变换及归一化处理的方法,对四类运动想象脑电信号进行特征提取,分类算法分为特征信号算术求和与阈值比较的预分类过程及包含单个支持向量机(SVM)的细分类过程,算法复杂度明显比采用多个SVM组合的多类分类算法要低,为实现算法的在线应用打下基础.仿真结果表明,该算法分类正确率高,时间开销小,并且可以通过调节阈值,在正确率与算法复杂度之间获得平衡.
|
|
| ［1］ WOLPAW J R, BIRBAUMER N, HEETDERKS W J, et al. Braincomputer interface technology: a review of the first international meeting ［J］. IEEE Transactions on rehabilitation Engineering, 2000, 8(2): 164-173.
［2］ HU Jianfeng, XIAO Dan, MU Zhengdong. Application of entropy in motor imagery EEG classification ［J］. International Journal of Digital Content Technology and its Applications, 2009, 3(2): 83-90.
［3］ GHANBARI A A, KOUSARRIZI M R N, TESHNEHLAB M, et al. Wavelet and hilbert transformbased brain computer interface ［C］∥ Proceedings of the International Conference on Advances in Computational Tools for Engineering Applications. Beirut: IEEE, 2009: 438-442.
［4］ WAN Baikun, LIU Yangang, MING Dong, et al. Feature recognition of multiclass imaginary movements in braincomputer interface ［C］∥ Proceedings of the International Conference on Virtual Environments, HumanComputer Interfaces and Measurements Systems. Hong Kong: IEEE, 2009: 250-254.
［5］ PFURTSCHELLER G, DA SILVA F H L. Eventrelated EEG/EMG synchronization and desynchronization: basic principles ［J］. Clinical Neurophysiology, 1999, 110(10): 1842-1857.
［6］ MCFARLAND D J, ANDERSON C W, MLLER K R, et al. BCI meeting 2005workshop on BCI signal processing: feature extraction and translation ［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2): 135-138.
［7］ BASHASHATI A, FATOURECHI M, WARD R K, et al. A survey of signal processing algorithms in braincomputer interfaces based on electrical brain signals ［J］. Journal of Neural Engineering, 2007, 4: 32-57.
［8］ DORNHEGE G, BLANKERTZ B, CURIO G, et al. Increase information transfer rates in BCI by CSP extension to multiclass ［C］∥ Advances in Neural Information Processing Systems. Canada: MIT Press, 2004: 733-740.
［9］ DORNHEGE G, BLANKERTZ B, CURIO G, et al. Boosting bit rates in noninvasive EEG singletrial classifications by feature combination and multiclass paradigms ［J］. IEEE Transactions on Biomedical Engineering, 2004, 51(6): 993-1002.
［10］ WILSON J A, MELLINGER J, SCHALK G, et al. A procedure for measuring latencies in braincomputer interfaces ［J］. IEEE Transactions on Biomedical Engineering, 2010, 57(7): 1785-1797.
［11］ BCI competition III ［DB/OL］. ［2010628］. http:∥www.bbci.de/competition/iii/.
［12］ ANG K K, CHIN Z Y, ZHANG H H, et al. Filter bank common spatial pattern (FBCSP) in braincomputer interface ［C］∥ Proceedings of the International Joint Conference on Neural Network. Hong Kong: IEEE, 2008: 2390-2397.
［13］ TANG Yan, TANG Jingtian, GONG Andong. Multiclass EEG classification for brain computer interface based on CSP ［C］∥ Proceedings of the Inernational Conference on Biomedical Engineering and Informatics. Sanya: IEEE, 2008: 469-472.
［14］ THOMAS K P, GUAN C, LAU C T, et al. A new discriminative common spatial pattern method for motor imagery braincomputer interfaces ［J］. IEEE Transactions on Biomedical Engineering, 2009, 56(11): 2730-2733.
［15］ WU Wei, GAO Xiaorong, GAO Shangkai. Oneversustherest (OVR) algorithm: an extension of common spatial patterns (CSP) algorithm to multiclass case ［C］∥ Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Shanghai: IEEE 2005: 2387-2390.
［16］ CHIN Z Y, ANG K K, WANG C, et al. Multiclass filter bank common spatial pattern for fourclass motor imagery BCI ［C］∥ Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Minnesota: IEEE 2009: 571-574.
［17］ 王璐,吴小培,高湘萍.四类运动想象任务的脑电特征分析及分类［J］.计算机技术与发展,2008,18(10): 23-26.
WANG Lu, WU Xiaopei, GAO Xiangping. Analysis and classification of fourclass motor imagery EEG data ［J］. Computer Technology and Development, 2008, 18(10): 23-26.
［18］ VAPNIK V N, Statistical learning theory ［M］. New York: John Wiley&Sons Press, 1998.
［19］ SCHLOGL A, LEE F, BISCHOF H, et al. Characterization of fourclass motor imagery EEG data for the BCIcompetition 2005 ［J］. Journal of Neural Engineering, 2005, 2(4): L14-22.
［20］ WANG Yijun, GAO Shangkai, GAO Xiaorong. Common spatial pattern method for channel selection in motor imagery based braincomputer interface ［C］∥ Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Shanghai: IEEE 2005: 5392-5395.
［21］ 李明爱,刘净瑜,郝冬梅.基于改进CSP算法的运动想象脑电信号识别方法［J］.中国生物医学工程学报,2009,28(2): 161-165.
LI Mingai, LIU Jingyu, HAO Dongmei. EEG recognition of motor imagery based on improved CSP algorithm［J］. Chinese Journal of Biomedical Engineering, 2009, 28(2): 161-165.
［22］ RAMOSER H, MULLERGERKING J, PFURTSCHELLER G. Optimal spatial filtering of single trial EEG during imagined hand movement ［J］. IEEE Transactions on Rehabilitation Engineering, 2000, 8(4): 441-446.
［23］ WANG Lei, XU Guizhi, WANG Jiang, et al. Application of hilberthuang transform for the study of motor imagery tasks ［C］∥ IEEE Engineering in Medicine and Biology Society Conference Proceedings. Canada: IEEE, 2008: 3848-385. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
