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

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.

A high-ITR SSVEP-based BCI speller

“…Another future research direction will be to assess the performance of our speller with free-spelling in a real world scenario. [46] In the free-spelling condition, the external cue is eliminated. The subjects could spell whatever they want and they are only instructed to delete the misspelled character by choosing the 'backspace' key.…”

Eye-Controlled Interfaces for Multimedia Interaction

“…Furthermore, we examine error related potential (ErrP), which offers a natural way to detect errors for automatic error correction (AEC) with the EEG sensor. ErrPs have been used for AEC in BCIs (such as to correct misspellings in P300 or cVEP-based spellers 15 ) but not in combination with eye-controlled interfaces. At first, our focus will be to correct misspellings, which will be activated when an ErrP signal is detected.…”

Brain-controlled applications using dynamic P300 speller matrices

“…Using hierarchical menus most applications designed for P300 BCIs can also be controlled with SMRs [65]. Visually evoked potential (VEP) based BCIs allow retaining the matrix based control scheme [66].…”