The BCI competition III: validating alternative approaches to actual BCI problems

TLDR

A brain‑computer interface (BCI) enables users to control external devices with brain activity, yet reliably translating intent into commands remains a major challenge that requires adaptive interaction between the user’s brain and the BCI system; many labs explore signal analysis techniques and machine learning algorithms that show promising offline results, but evaluating their relative value for online use is difficult, prompting the organization of BCI data competitions to objectively assess alternative methods. The authors organized the third BCI Competition to tackle the most difficult and important analysis problems in BCI research. The competition was structured to provide objective, formal evaluations of alternative methods for these problems. The paper presents the datasets used in the competition and summarizes the participants’ results.

Abstract

A brain-computer interface (BCI) is a system that allows its users to control external devices with brain activity. Although the proof-of-concept was given decades ago, the reliable translation of user intent into device control commands is still a major challenge. Success requires the effective interaction of two adaptive controllers: the user's brain, which produces brain activity that encodes intent, and the BCI system, which translates that activity into device control commands. In order to facilitate this interaction, many laboratories are exploring a variety of signal analysis techniques to improve the adaptation of the BCI system to the user. In the literature, many machine learning and pattern classification algorithms have been reported to give impressive results when applied to BCI data in offline analyses. However, it is more difficult to evaluate their relative value for actual online use. BCI data competitions have been organized to provide objective formal evaluations of alternative methods. Prompted by the great interest in the first two BCI Competitions, we organized the third BCI Competition to address several of the most difficult and important analysis problems in BCI research. The paper describes the data sets that were provided to the competitors and gives an overview of the results.