Towards Zero Training for Brain-Computer Interfacing

Matthias Krauledat,Michael Tangermann,Benjamin Blankertz,Klaus-Robert Müller,Olaf Sporns

doi:10.1371/journal.pone.0002967

Abstract

Electroencephalogram (EEG) signals are highly subject-specific and vary considerably even between recording sessions of the same user within the same experimental paradigm. This challenges a stable operation of Brain-Computer Interface (BCI) systems. The classical approach is to train users by neurofeedback to produce fixed stereotypical patterns of brain activity. In the machine learning approach, a widely adapted method for dealing with those variances is to record a so called calibration measurement on the beginning of each session in order to optimize spatial filters and classifiers specifically for each subject and each day. This adaptation of the system to the individual brain signature of each user relieves from the need of extensive user training. In this paper we suggest a new method that overcomes the requirement of these time-consuming calibration recordings for long-term BCI users. The method takes advantage of knowledge collected in previous sessions: By a novel technique, prototypical spatial filters are determined which have better generalization properties compared to single-session filters. In particular, they can be used in follow-up sessions without the need to recalibrate the system. This way the calibration periods can be dramatically shortened or even completely omitted for these ‘experienced’ BCI users. The feasibility of our novel approach is demonstrated with a series of online BCI experiments. Although performed without any calibration measurement at all, no loss of classification performance was observed.

Highlights

A Brain-Computer Interface (BCI) based on electroencephalogram (EEG) signals provides a direct communication channel for healthy or disabled users from the brain to a technical device
One classical approach to establish EEGbased control is to set up a system that is controlled by a specific EEG feature which is known to be susceptible to conditioning and to let the subjects learn the voluntary control of that feature in a learning process that can last several weeks
Feedback Performance The first three runs of feedback showed that all subjects under study were able to operate the BCI with the pre-computed classifier at a high accuracy

Summary

Introduction

A Brain-Computer Interface (BCI) based on electroencephalogram (EEG) signals provides a direct communication channel for healthy or disabled users from the brain to a technical device. In the machine learning approach to BCI [1,2] a statistical analysis of a calibration measurement which is recorded at the beginning of each session is used to adapt the system to the specificities of the user’s current brain signals. This approach allows for an effective performance from the first session on without user training [3,2]. As the signals vary between sessions even for the same user, machine learning based BCI systems rely on the calibration procedure for optimal performance (machine training)

Objectives

Methods

Results

Conclusion