TechRxiv
Mobaien pERP-LDA.pdf (241.9 kB)
Download file

A new approach based on principal ERPs and LDA to improve P300 mind spellers

Download (241.9 kB)
preprint
posted on 06.12.2021, 20:48 by Ali MobaienAli Mobaien, Negar Kheirandish, Reza Boostani
Abstract—Visual P300 mind speller is a brain-computer interface that allows an individual to type through his mind. For this goal, the subject sits in front of a screen full of characters, and when his desired one is highlighted, there will be a P300 response (a positive deflection nearly 300ms after stimulus) in his brain signals. Due to the very low signal-to noise (SNR) of the P300 in the background activities of the brain, detection of this component is challenging. Principal ERP reduction (pERP-RED) is a newly developed method that can effectively extract the underlying templates of event-related potentials (ERPs), by employing a three-step spatial filtering procedure. In this research, we investigate the performance of pERP-RED in conjunction with linear discriminant analysis (LDA) to classify P300 data. The proposed method is examined on a real P300 dataset and compared to the state-of-the-art LDA and support vector machines. The results demonstrate that the proposed method achieves higher classification accuracy in low SNRs and low numbers of training data.

History

Email Address of Submitting Author

a.mobaien@shirazu.ac.ir

ORCID of Submitting Author

0000-0003-1874-4289

Submitting Author's Institution

Shiraz University

Submitting Author's Country

Iran