Title :
Combination of continuous and discrete wavelet coefficients in single-trial P300 detection
Author :
Motlagh, F.E. ; Tang, S.H. ; Motlagh, O.
Author_Institution :
ITMA, Univ. Putra Malaysia, Serdang, Malaysia
Abstract :
Single trail detection of P300 from EEG signals is the main challenge of ERP-based BCI systems. In this article, combination of CWT and DWT in feature extraction achieved up to 98% of accuracy in single trial P300 detection. Two steps of feature extraction once by using DWT and second by CWT prepare effective P300 component features. Three major features of DWT and T-CWT transform have been selected. Multi-dimensional SVM classifier has been used for classifying target and non-target EEG signals.
Keywords :
bioelectric potentials; brain-computer interfaces; discrete wavelet transforms; electroencephalography; feature extraction; medical signal detection; signal classification; support vector machines; DWT; ERP-based BCI systems; P300 component feature; T-CWT transform; brain computer interface; continuous wavelet coefficients; discrete wavelet coefficients; event-related potentials; feature extraction; multidimensional SVM classifier; nontarget EEG signals; single-trial P300 detection; target EEG signals; BCI; CWT; DWT; EEG; ERP; SVM; T-CWT;
Conference_Titel :
Biomedical Engineering and Sciences (IECBES), 2012 IEEE EMBS Conference on
Conference_Location :
Langkawi
Print_ISBN :
978-1-4673-1664-4
DOI :
10.1109/IECBES.2012.6498111
