Preliminary Results on a New Algorithm for Blink Correction Adaptive to Inter- and Intra-Subject Variability

Abstract

This paper presents a new preprocessing method to correct blinking artifacts in Electroencephalography (EEG) based Brain-Computer Interfaces (BCIs). This Algorithm for Blink Correction (ABC) directly corrects the signal in the time domain without the need for additional Electrooculogram (EOG) electrodes. The main idea is to automatically adapt to the blink's inter- and intra-subject variability by considering the blink's amplitude as a parameter. A simple Minimum Distance to Riemannian Mean (MDRM) is applied as the classification algorithm. Preliminary results on three subjects show a mean classification accuracy increase of 13.7% using ABC.