SINGLE-TRIAL EEG CLASSIFICATION FOR BRAIN-COMPUTER INTERFACE USING WAVELET DECOMPOSITION (MonAmOR2)
Author(s) :
Anysia Yong (University College Dublin, Ireland)
Neil Hurley (University College Dublin, Ireland)
Abstract : A classification system for EEG signals using wavelet decomposition to form the feature vectors is developed. Single-trial analysis loses the benefit of averaging to remove non-task related brain activity and makes it more difficult to pick out key features determining the execution of a task. Wavelet analysis is used here to localise the BP of voluntary movement. Classification of a self-paced typing experiment was made using wavelets for the feature selection and SVMs for the classification of feature vectors. Results of up to 91\% classification accuracy were obtained, proving that wavelets are an effective tool, and the use of wavelets will be considered in more complex work.
Menu