Classification of EEG Motor Imagery Multi Class Signals Based on Cross Correlation

Abstract Many techniques are developed for improving the classification performance of motor imagery (MI) signals used in Brain computer interfacing (BCI). Still there is scope for improvement of performance using various techniques. In this paper, cross correlation (CC) technique has been used for features extraction from EEG signal and the final classification was done based on voting method which selects the best classifier among the five classifiers used for classification. Our approach was tested on public data set 2a from BCI competition IV. The results proved that our approach outperformed already existing approaches with 29.82% improvement in kappa values.

[1]  A. Berthoz,et al.  Mental representations of movements. Brain potentials associated with imagination of eye movements , 1999, Clinical Neurophysiology.

[2]  José del R. Millán,et al.  Non-Invasive Brain-Actuated Control of a Mobile Robot , 2003, IJCAI.

[3]  Michitaka Hirose,et al.  Brain-Computer Interfaces, Virtual Reality, and Videogames , 2008, Computer.

[4]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[5]  R. J. Schimheimer.  Dutch society for clinical neurophysiology Utrecht, October 18, 1996 , 1997 .

[6]  José del R. Millán,et al.  Noninvasive brain-actuated control of a mobile robot by human EEG , 2004, IEEE Transactions on Biomedical Engineering.

[7]  M. Jeannerod.  Mental imagery in the motor context , 1995, Neuropsychologia.

[8]  R. Ward,et al.  EMG and EOG artifacts in brain computer interface systems: A survey , 2007, Clinical Neurophysiology.

[9]  Jianjun Meng,et al.  Automated selecting subset of channels based on CSP in motor imagery brain-computer interface system , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[10]  Yan Li,et al.  Improving the Separability of Motor Imagery EEG Signals Using a Cross Correlation-Based Least Square Support Vector Machine for Brain–Computer Interface , 2012, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[11]  G. Pfurtscheller,et al.  EEG-based discrimination between imagination of right and left hand movement. , 1997, Electroencephalography and clinical neurophysiology.

[12]  J. Wolpaw,et al.  EEG correlates of P300-based brain–computer interface (BCI) performance in people with amyotrophic lateral sclerosis , 2012, Journal of neural engineering.

[13]  J. Wolpaw,et al.  Clinical Applications of Brain-Computer Interfaces: Current State and Future Prospects , 2009, IEEE Reviews in Biomedical Engineering.

[14]  Jonathan R Wolpaw,et al.  EEG correlates of P 300-based brain – computer interface ( BCI ) performance in people with amyotrophic lateral sclerosis , 2012 .

[15]  A. Berthoz,et al.  Mental representations of movements. Brain potentials associated with imagination of hand movements. , 1995, Electroencephalography and clinical neurophysiology.

[16]  Xiaorong Gao,et al.  Design and implementation of a brain-computer interface with high transfer rates , 2002, IEEE Transactions on Biomedical Engineering.

[17]  Christian Kothe,et al.  Towards passive brain–computer interfaces: applying brain–computer interface technology to human–machine systems in general , 2011, Journal of neural engineering.

[18]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.