Transferring Shared Responses Across Electrode Montages for Facilitating Calibration in High-Speed Brain Spellers

Recent studies have shown that using the user's average steady-state visual evoked responses (SSVEPs) as the template to template-matching methods could significantly improve the accuracy and speed of the SSVEP-based brain-computer interface (BCI). However, collecting the pilot data for each individual can be time-consuming. To resolve this practical issue, this study aims to explore the feasibility of leveraging pre-recorded datasets from the same users by transferring common electroencephalogram (EEG) responses across different sessions with the same or different electrode montages. The proposed method employs spatial filtering techniques including response averaging, canonical correlation analysis (CCA), and task-related component analysis (TRCA) to project scalp EEG recordings onto a shared response domain. The transferability was evaluated by using 40-class SSVEPs recorded from eight subjects with nine electrodes on two different days. Three subsets of electrode montages were selected to simulate different scenarios such as identical, partly overlapped, and non-overlapped electrode placements across two sessions. The target identification accuracy of the proposed methods with transferred training data significantly outperformed a conventional training-free algorithm. The result suggests training data required in the BCI speller could be transferred from different EEG montages and/or headsets.

I. Introduction

Brain-computer interfaces (BCIs) have been attracting increasing attention as an alternative way to provide a direct communication channel between the human brain and external devices [1] . Among various applications, a BCI speller is especially valuable since it can help people with severe motor disabilities communicate with others. Many researchers have attempted to develop BCI spellers using electroencephalogram (EEG) by taking advantages of noninvasiveness, ease-of-use, and relatively low cost [2] –[4] . For instance, Farewell and Donchin first proposed a well-known P300 speller in the 1980s [2] . More recently, steady-state visual evoked potentials (SSVEPs), which are EEG responses to repetitive visual stimuli, have been successfully used in BCI spellers with high information transfer rates (ITRs). In two successful studies, Chen et al. and Nakanishi et al. demonstrated their 40-class SSVEP spellers with ITRs of 267 bits/min [3] and 325 bits/min [4] , respectively.