• Snehal Dongare
• Dinesh Padole

Multi-channel EEG signal is mainly used in Brain signature categorization. Owing to the curse of dimensionality problem, the analysis and classification using several channels may lead to the undesired performance. Channel selection could be an effective way to improve EEG signal quality by removing those noisy, irrelevant channels. Selecting a lesser count of channels may lower down the system cost. Selecting the subject-specific, informative channels may help to identify the motor cortex that is correlated well with the performed motor imagery tasks. This paper provides the comparison of channel selection techniques for EEG signal. Two algorithms have been presented to identify subsets of channels which are capable of discriminating between samples of distinct classes. The CSP and Surface Laplacian algorithms are considered for channel selection. The performance of these methods in terms of accuracy is 82.9% and 76.24% respectively

EEG, Channel selection, MI, Performance

"COMPARISON OF METHODS FOR EEG CHANNEL SELECTION FOR MI TASK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 1, page no.a531-a536, January-2022, Available :http://www.jetir.org/papers/JETIR2201069.pdf

"COMPARISON OF METHODS FOR EEG CHANNEL SELECTION FOR MI TASK", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 1, page no. ppa531-a536, January-2022, Available at : http://www.jetir.org/papers/JETIR2201069.pdf