P300 Detection with Brain–Computer Interface Application Using PCA and Ensemble of Weighted SVMs

ABSTRACT

Brain–computer interface (BCI) P300 speller can be used as a powerful aid for severely disabled people in their everyday life. The character recognition using P300 speller involves two stages for classification. First stage is to detect the P300 signal and second one is to determine the right character from the detected P300. Features are important for classification, but large feature dimension is a problem for P300 classification as computational complexity increase due to more number of features. In this work, principal component analysis (PCA) based ensemble of weighted support vector machine (PCA-EWSVM) is used for character recognition. The proposed method includes PCA for feature extraction and an ensemble of weighted SVM (EWSVM) for classification. PCA is used to reduce the redundant features and ensemble of weighted classifier for minimizing the classifier variability. The proposed algorithm has been evaluated on data-set of the BCI Competition II and data-set II of the BCI Competition III.

KEYWORDS:

• Brain–computer interface (BCI)
• Electroencephalogram (EEG)
• Ensemble of weighted support vector machine (EWSVM)
• Principle component analysis (PCA)
• P300

ACKNOWLEDGEMENTS

The authors would like to thank A. Rakotomamonjy for his help towards the ESVM method. This work is supported by the Young Faculty Research Fellowship under Visvesvaraya PhD scheme for Electronics & IT, DeitY, India.

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Funding

Young Faculty Research Fellowship under Visvesvaraya PhD scheme for Electronics & IT, DeitY, India [grant number PhD-MLA/4(13)/2015-16].

Notes on contributors

Sourav Kundu

Sourav Kundu received his BTech degree in electronics and communication engineering in the year 2011. He received his MTech degree from IIEST, Shibpur in Mechatronics in the year 2014. He is currently pursuing his PhD degree in signal processing at National Institute of Technology, Rourkela, in the Department of Electronics and Communication Engineering.

E-mail: [email protected]

Samit Ari

Samit Ari received BTech degree in electronics and tele-communication engineering from University of Kalyani and MTech degree in instrumentation engineering from Calcutta University. He completed his PhD degree in electronics and electrical communication engineering from Indian Institute of Technology, Kharagpur. He joined National Institute of Technology (NIT) Rourkela as a faculty member in 2009, where he presently holds the position of Assistant Professor in the Department of Electronics and Communication Engineering.

E-mail: [email protected]