Title: Influence of stimuli colour on feature classification for BCI applications

Authors: Rajesh Kumar Singla; Arun Khosla; R. Jha

Addresses: Department of Instrumentation and Control Engineering, National Institute of Technology Jalandhar, Jalandhar 144011, Punjab, India ' Department of Electronics and Communication Engineering, National Institute of Technology Jalandhar, Jalandhar 144011, Punjab, India ' IET Bhaddal, Ropar 140108, Punjab, India

Abstract: One of the key points of Brain Computer Interface (BCI) system is how different Electroencephalogram (EEG) features are abstracted and distinguished. Therefore, EEG signal processing method is the focus of BCI. In this study, four different flickering frequencies in low-frequency region were used to elicit the SSVEPs and were displayed on a Liquid Crystal Display (LCD) monitor using LabVIEW. Four stimuli colours, green, red, blue and violet, were used in this study to investigate the influence of colour on SSVEPs. The EEG signals recorded from the occipital region were segmented into 1 second windows and features were extracted by using wavelet transform. Support Vector Machines (SVMs) are used for classification. In colour comparison, SSVEP with the violet colour showed higher accuracy than that with other stimuli.

Keywords: BCI; brain computer interface; EEG; electroencephalography; wavelet transform; steady-state visual evoked potential; SSVEP; SVM; support vector machines; stimuli colours; feature classification; signal processing; liquid crystal display; LCD monitors; feature extraction; flickering frequencies.

DOI: 10.1504/IJBET.2014.060993

International Journal of Biomedical Engineering and Technology, 2014 Vol.15 No.1, pp.82 - 93

Received: 30 Nov 2013
Accepted: 30 Apr 2014
Published online: 21 Oct 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article