A Novel Features Selection Approach with Common Spatial Pattern for EEG Based Brain–Computer Interface Implementation

Abstract

This paper presents a novel method for the selection of spatial filters and features in electroencephalography (EEG) based motor imagery classification. The analyzing EEG data are divided into training and test sets. The training set is used to select appropriate spatial filters with dominant features. To accomplish such features, the EEG of training set is segmented again into two subsets termed as training subset and test subset. The features of both subsets are extracted using common spatial pattern. Then features of training subset are ranked using mutual information based approach. Besides, the features of test subset are also ranked according to the order of the training subset features. The initial classification performance using training and test subsets are obtained by using linear discriminant analysis. Then a grid search method is employed to select the effective number of spatial filter pairs as well as the discriminative features. Thus obtained spatial filter and features are used in actual classification accuracy of the test set of EEG. The experimental results show that the proposed approach yields comparatively superior classification performance compared to prevailing methods.

KEYWORDS:

• Brain–computer interface (BCI)
• Electroencephalography
• Common spatial pattern
• Grid search

ACKNOWLEDGEMENTS

The authors Md. Sujan Ali and Mst. Jannatul Ferdous are funded by the ICT Division of the Ministry of Post, Telecommunication and Information Technology of the Government of Bangladesh through a fellowship program. Therefore, the authors would like to acknowledge the State Ministry of Bangladesh.

Additional information

Notes on contributors

Sujan Ali

Md Sujan Ali received BSc and MSc degrees in electrical and electronic engineering from Islamic University, Kushtia, Bangladesh in 2002 and 2003, respectively. During 2006–2008, he was a lecturer in the Department of Information and Communication Technology, Metropolitan University, Bangladesh. After that, he joined as a lecturer in the Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Mymensingh, Bangladesh where he promoted as an assistant professor in 2011 and associate professor in 2016. He received his PhD degree from the faculty of Engineering, University of Rajshahi, Bangladesh in 2019. His research interest includes brain signal processing, brain–computer interface (BCI), biomedical signal and image processing. Email: [email protected]

Jannatul Ferdous

Mst Jannatul Ferdous achieved her BSc and MSc degrees in electrical and electronic engineering from Islamic University, Kushtia, Bangladesh in 2002 and 2003, respectively. She was a lecturer in the Department of Information and Communication Technology, Metropolitan University, Bangladesh. In 2010, she joined as a lecturer and promoted as an assistant professor in 2011 and associate professor in 2016 in the Department of Computer Science and Engineering, Jatiya Kabi Kazi Nazrul Islam University, Mymensingh, Bangladesh. She received her PhD degree from the faculty of Engineering, University of Rajshahi, Bangladesh in 2019. Her research interest includes digital signal processing, EEG signal enhancement, biomedical signal and image processing. Corresponding author. Email: [email protected]

Ekramul Hamid

Md Ekramul Hamid received his BSc and MSc degrees from the Department of Applied Physics and Electronics, Rajshahi University, Bangladesh. After that he obtained the masters in computer science from Pune University, India. He received his PhD degree from Shizuoka University, Japan. During 1997–2000, he was a lecturer in the Department of Computer Science and Engineering, Rajshahi University. Dr Hamid was working as assistant professor at the King Khalid University, Abha, KSA from 2009 to 2011. He is currently working as a professor in the Department of Computer Science and Engineering, University of Rajshahi. His research interests include digital signal processing, analysis and synthesis of speech signal, speech enhancement, and image processing. Email: [email protected]

Khademul Islam Molla

Md Khademul Islam Molla received his BSc and MSc degrees in electronics and computer science from Shahjalal University of Science and Technology, Sylhet, Bangladesh in 1995 and 1997, respectively. He joined at the same department as a lecturer in 1997. He obtained his PhD degree from the Department of Frontier Informatics under the Graduate School of Frontier Sciences, the University of Tokyo, Tokyo, Japan in 2006. He was working as lecturer and assistant professor in the Department of Computer Science and Engineering of the University of Rajshahi, Bangladesh up to August 2006. After completing his PhD, he joined in the same department as associate professor in August 2006, and he has been a professor since May 2012. From September 2006 to September 2008, he was working as JSPS postdoctoral research fellow in the Department of Information and Communication Engineering, The University of Tokyo, Tokyo, Japan. He was a research fellow at the University of Alberta, Canada, from Nov 2010 to Oct 2011. He visited several universities in Japan as guest researcher. Presently, he is a visiting scientist at the University of Tokyo, Japan. His research interests include audio signal processing, blind source separation, brain–computer interface (BCI), biomedical signal, and image processing. He is a member of the Institute of Electrical and Electronics Engineers (IEEE). In 2007, he received the Best Paper Award from the Research Institute of Signal Processing, Japan (RISP). Email: [email protected]