Online Adaptation of a c-VEP Brain-Computer Interface(BCI) Based on Error-Related Potentials and Unsupervised Learning

TLDR

Brain‑computer interfaces aim to control computers using brain activity, and code‑modulated visual evoked potentials (c‑VEPs) have recently shown promise for high‑performance communication. This study introduces a c‑VEP BCI that adapts its classifier online to shorten calibration and boost performance. The system compares an unsupervised adaptation method with one that leverages error‑related potential detection for online classifier updates. Online adaptation using error‑related potentials achieved 96% accuracy, a 144‑bit/min information transfer rate—the highest for non‑invasive BCIs—and enabled free‑spelling at 21.3 error‑free letters per minute, while also demonstrating that calibration can rely solely on error detection without true labels.

Abstract

The goal of a Brain-Computer Interface (BCI) is to control a computer by pure brain activity. Recently, BCIs based on code-modulated visual evoked potentials (c-VEPs) have shown great potential to establish high-performance communication. In this paper we present a c-VEP BCI that uses online adaptation of the classifier to reduce calibration time and increase performance. We compare two different approaches for online adaptation of the system: an unsupervised method and a method that uses the detection of error-related potentials. Both approaches were tested in an online study, in which an average accuracy of 96% was achieved with adaptation based on error-related potentials. This accuracy corresponds to an average information transfer rate of 144 bit/min, which is the highest bitrate reported so far for a non-invasive BCI. In a free-spelling mode, the subjects were able to write with an average of 21.3 error-free letters per minute, which shows the feasibility of the BCI system in a normal-use scenario. In addition we show that a calibration of the BCI system solely based on the detection of error-related potentials is possible, without knowing the true class labels.