Similar articles

Abstract: Classifying single-trial electroencephalogram (EEG) based motor imagery (MI) tasks is extensively used to control brain-computer interface (BCI) applications, as a communication bridge between humans and computers. However, the low signal-to-noise ratio and individual differences of EEG can affect the classification results negatively. In this paper, we propose an improved common spatial pattern (B-CSP) method to extract features for alleviating these adverse effects. First, for different subjects, the method of Bhattacharyya distance is used to select the optimal frequency band of each electrode including strong event-related desynchronization (ERD) and event-related synchronization (ERS) patterns; then the signals of the optimal frequency band are decomposed into spatial patterns, and the features that can describe the maximum differences of two classes of MI are extracted from the EEG data. The proposed method is applied to the public data set and experimental data set to extract features which are input into a back propagation neural network (BPNN) classifier to classify single-trial MI EEG. Another two conventional feature extraction methods, original common spatial pattern (CSP) and autoregressive (AR), are used for comparison. An improved classification performance for both data sets (public data set: 91.25%±1.77% for left hand vs. foot and 84.50%±5.42%for left hand vs. right hand; experimental data set: 90.43%±4.26% for left hand vs. foot) verifies the advantages of the B-CSP method over conventional methods. The results demonstrate that our proposed B-CSP method can classify EEG-based MI tasks effectively, and this study provides practical and theoretical approaches to BCI applications.

面向脑机接口基于改进的共同空间模式方法的单次运动想象脑电分类

[1]Ang KK, Guan CT, Chua KSG, et al., 2010. Clinical study of neurorehabilitation in stroke using EEG-based motor imagery brain-computer interface with robotic feedback. Annual Int Conf of the IEEE Engineering in Medicine and Biology, p.5549-5552.

[2]Bai O, Lin P, Vorbach S, et al., 2007. A high performance sensorimotor beta rhythm-based brain-computer interface associated with human natural motor behavior. J Neur Eng, 5(1):24-35.

[3]Cassim F, Szurhaj W, Sediri H, et al., 2000. Brief and sustained movements: differences in event-related (de)synchronization (ERD/ERS) patterns. Clin Neurophysiol, 111(11):2032-2039.

[4]Franaszczuk PJ, Bergey GK, 1999. An autoregressive method for the measurement of synchronization of interictal and ictal EEG signals. Biol Cybern, 81(1):3-9.

[5]Gaur P, Pachori RB, Wang H, et al., 2018. A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry. Exp Syst Appl, 95:201-211.

[6]Gomarus HK, Althaus M, Wijers AA, et al., 2006. The effects of memory load and stimulus relevance on the EEG during a visual selective memory search task: an ERP and ERD/ERS study. Clin Neurophysiol, 117(4):871-884.

[7]Graimann B, Huggins JE, Levine SP, et al., 2002. Visualization of significant ERD/ERS patterns in multichannel EEG and ECoG data. Clin Neurophysiol, 113(1):43-47.

[8]Kevric J, Subasi A, 2017. Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system. Biomed Signal Process Contr, 31:398-406.

[9]Kumar S, Sharma R, Sharma A, et al., 2016. Decimation filter with common spatial pattern and Fishers discriminant analysis for motor imagery classification. Int Joint Conf on Neural Networks, p.2090-2095.

[10]Kumar S, Mamun K, Sharma A, 2017a. CSP-TSM: optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI. Comput Biol Med, 91:231-242.

[11]Kumar S, Sharma A, Tsunoda T, 2017b. An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information. BMC Bioinform, 18(S16), Article 125.

[12]Lemm S, Blankertz B, Curio G, et al., 2005. Spatio-spectral filters for improving the classification of single trial EEG. IEEE Trans Biomed Eng, 52(9):1541-1548.

[13]Lotte F, Congedo M, Lécuyer A, et al., 2007. A review of classification algorithms for EEG-based brain-computer interfaces. J Neural Eng, 4(2):R1-R13.

[14]Moghimi S, Kushki A, Marie Guerguerian A, et al., 2013. A review of EEG-based brain-computer interfaces as access pathways for individuals with severe disabilities. Assist Technol, 25(2):99-110.

[15]Müller-Gerking J, Pfurtscheller G, Flyvbjerg H, 1999. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin Neurophysiol, 110(5): 787-798.

[16]Nam CS, Jeon Y, Kim YJ, et al., 2011. Movement imagery-related lateralization of event-related (de)synchronization (ERD/ERS): motor-imagery duration effects. Clin Neurophysiol, 122(3):567-577.

[17]Neuper C, Wörtz M, Pfurtscheller G, 2006. ERD/ERS patterns reflecting sensorimotor activation and deactivation. Prog Brain Res, 159:211-222.

[18]Nicolas-Alonso LF, Gomez-Gil J, 2012. Brain computer interfaces, a review. Sensors, 12(2):1211-1279.

[19]Oldfield RC, 1971. The assessment and analysis of handedness: the Edinburgh inventory. Neuropsychologia, 9(1):97-113.

[20]Pfurtscheller G, 2001. Functional brain imaging based on ERD/ERS. Vis Res, 41(10-11):1257-1260.

[21]Pfurtscheller G, da Silva FHL, 1999. Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol, 110(11):1842-1857.

[22]Pfurtscheller G, Neuper C, 1997. Motor imagery activates primary sensorimotor area in humans. Neurosci Lett, 239(2-3):65-68.

[23]Pfurtscheller G, Neuper C, 2006. Future prospects of ERD/ERS in the context of brain-computer interface (BCI) developments. Prog Brain Res, 159:433-437.

[24]Pfurtscheller G, Neuper C, Flotzinger D, et al., 1997. EEG-based discrimination between imagination of right and left hand movement. Electroencephalogr Clin Neurophysiol, 103(6):642-651.[doi:10.1016/S0013-4694(97)00080-1]

[25]Pfurtscheller G, Neuper C, Schlogl A, et al., 1998. Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. IEEE Trans Rehabil Eng, 6(3):316-325.

[26]Qaraqe M, Ismail M, Serpedin E, 2015. Band-sensitive seizure onset detection via CSP-enhanced EEG features. Epilep Behav, 50:77-87.

[27]Ramoser H, Muller-Gerking J, Pfurtscheller G, 2000. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans Rehabil Eng, 8(4):441-446.

[28]Robinson N, Vinod AP, Ang KK, et al., 2013. EEG-based classification of fast and slow hand movements using wavelet-CSP algorithm. IEEE Trans Biomed Eng, 60(8):2123-2132.

[29]Salisbury DB, Parsons TD, Monden KR, et al., 2016. Brain-computer interface for individuals after spinal cord injury. Rehabil Psychol, 61(4):435-441.

[30]Subasi A, 2005. Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients. Exp Syst Appl, 28(4):701-711.

[31]Tangermann M, Müller KR, Aertsen A, et al., 2012. Review of the BCI competition IV. Front Neurosci, 6, Article 55.

[32]Wolpaw JR, Birbaumer N, McFarland DJ, et al., 2002. Brain-computer interfaces for communication and control. Clin Neurophysiol, 113(6):767-791.

[33]Wu W, Chen Z, Gao XR, et al., 2015. Probabilistic common spatial patterns for multichannel EEG analysis. IEEE Trans Patt Anal Mach Intell, 37(3):639-653.

[34]Yang HJ, Guan CT, Wang CC, et al., 2015. Detection of motor imagery of brisk walking from electroencephalogram. J Neurosci Methods, 244:33-44.

[35]Yuksel A, Olmez T, 2015. A neural network-based optimal spatial filter design method for motor imagery classification. PLoS ONE, 10(5):e0125039.

[36]Zhang HH, Yang HJ, Guan CT, 2013. Bayesian learning for spatial filtering in an EEG-based brain-computer interface. IEEE Trans Neur Netw Learn Syst, 24(7):1049-1060.

[37]Zhang Y, Liu B, Ji XM, et al., 2017. Classification of EEG signals based on autoregressive model and wavelet packet decomposition. Neur Process Lett, 45(2):365-378.