Common spatial pattern-based feature extraction from the best time segment of BCI data

Feature extraction is one of the most crucial stages in the field of brain computer interface (BCI). Because of its ability to directly influence the performance of BCI systems, recent studies have generally investigated how to modify existing methods or develop novel techniques. One of the most successful and well-known methods in BCI applications is the common spatial pattern (CSP). In existing CSP-based methods, the spatial filters were extracted either by using the whole data trial or by dividing the trials into a number of overlapping/nonoverlapping time segments. In this paper, we developed a CSP-based moving window technique to obtain the most distinguishable CSP features and increase the classifier performance by finding the best time segment of electroencephalogram trials. The extracted features were tested by using support vector machines (SVMs). The performance of the classifier was measured in terms of classification accuracy and kappa coefficient (κ). The proposed method was successfully applied to the two-dimensional cursor movement imagery data sets, which were acquired from three healthy human subjects in two sessions on different days. The experiments proved that instead of using the whole data length of EEG trials, extracting CSP features from the best time segment provides higher classification accuracy and κ rates.

PDF

___

[1] McFarland DJ, Sarnacki WA, Wolpaw JR. Electroencephalographic (EEG) control of three-dimensional movement. J Neural Eng 2010; 7: 1-21.
[2] Daly JJ, Wolpaw JR. Braincomputer interfaces in neurological rehabilitation. Lancet Neurol 2008; 7: 1032-1043.
[3] Gao X, Xu D, Cheng M, Gao S. A BCI-based environmental controller for the motion-disabled. IEEE T Neur Syst Reh 2003; 11: 137-140.
[4] Zhao Q, Zhang L, Cichocki A. EEG-based asynchronous BCI control of a car in 3D virtual reality environments. Chinese Sci Bull 2009; 54: 78-87.
[5] Menon C, de Negueruela C, Mill´an JDR, Tonet O, Carpi F, Broschart M, De Rossi D. Prospects of brainmachine interfaces for space system control. Acta Astronaut 2009; 64: 448-456.
[6] Kayikcioglu T, Aydemir O. A polynomial fitting and k -NN based approach for improving classification of motor imagery BCI data. Pattern Recogn Lett 2010; 31: 1207-1215.
[7] Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE T Rehabil Eng 2000; 8: 441-446.
[8] Kang H, Nam Y, Choi S. Composite common spatial pattern for subject-to-subject transfer. IEEE Signal Proc Lett 2009; 16: 683-686.
[9] Wang Y, Veluvolu KC, Lee M. Time-frequency analysis of band-limited EEG with BMFLC and Kalman filter for BCI applications. J Neuroeng Rehabil 2013; 10: 109-125.
[10] Aydemir O, Kayikcioglu T. Decision tree structure based classification of EEG signals recorded during two dimensional cursor movement imagery. J Neurosci Meth 2014; 229: 68-75.
[11] Trejo LJ, Rosipal R, Matthews B. Brain-computer interfaces for 1-D and 2-D cursor control: designs using volitional control of the EEG spectrum or steady-state visual evoked potentials. IEEE T Neur Sys Reh 2006; 14: 225-229.
[12] Li Y, Long J, Yu T, Yu Z, Wang C, Zhang H, Guan C. An EEG-based BCI system for 2-D cursor control by combining Mu/Beta rhythm and P300 potential. IEEE T Biomed Eng 2010; 57: 2495-2505.
[13] McFarland DJ, Miner LA, Vaughan TM, Wolpaw JR. Mu and beta rhythm topographies during motor imagery and actual movements. Brain Topogr 2000; 12: 177-186.
[14] Huan NJ, Palaniappan R. Neural network classification of autoregressive features from electroencephalogram signals for braincomputer interface design. J Neural Eng 2004; 1: 142-150.
[15] Garc´ıa-Laencina PJ, Rodr´ıguez-Bermudez G, Roca-Dorda J. Exploring dimensionality reduction of EEG features in motor imagery task classification. Expert Syst Appl 2014; 41: 5285-5295.
[16] Novi Q, Guan C, Dat TH, Xue P. Sub-band common spatial pattern (SBCSP) for brain-computer interface. In: IEEE/EMBS 2007 Conference on Neural Engineering; 25 May 2007; Kohala Coast, HI, USA. New York, NY, USA: IEEE. pp. 204-207.
[17] Ghaheri H, Ahmadyfard AR. Extracting common spatial patterns from EEG time segments for classifying motor imagery classes in a Brain Computer Interface (BCI). Sci Iran 2013; 20: 2061-2072.
[18] Asensio-Cubero J, Palaniappan R, Gan J. A study on temporal segmentation strategies for extracting common spatial patterns for brain computer interfacing. In: IEEE 2011 UK Workshop on Computational Intelligence; 79 September 2011; Manchester, UK. New York, NY, USA: IEEE. pp. 99-102.
[19] Halder S, Bensch M, Mellinger J, Bogdan M, K¨ubler A, Birbaumer N, Rosenstiel W. Online artifact removal for brain-computer interfaces using support vector machines and blind source separation. Comput Intel Neurosci 2007; Article ID 82069.
[20] Zeng H, Song A. Removal of EOG artifacts from EEG recordings using stationary subspace analysis. Sci World J 2014; Article ID 259121.
[21] Lee KY, Kim S. Designing discriminative spatial filter vectors in motor imagery brain-computer interface. Int J Imag Syst Tech 2013; 23: 147-151.
[22] Grosse-Wentrup M, Buss M. Multiclass common spatial patterns and information theoretic feature extraction. IEEE T Biomed Eng 2008; 55: 1991-2000.
[23] Aydemir O, Kayikcioglu T. Wavelet transform based classification of invasive brain computer interface data. Radioengineering 2011; 20: 31-38.