An efficient P300-based brain–computer interface for disabled subjects

• Published in: Journal of neuroscience methods Vol. 167; no. 1; pp. 115 - 125
• Main Authors: Hoffmann, Ulrich, Vesin, Jean-Marc, Ebrahimi, Touradj, Diserens, Karin
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.01.2008
• Subjects: Adult; Bayesian linear discriminant analysis; Brain - physiopathology; Brain Diseases - physiopathology; Brain Mapping; Brain–computer interface; Disabled Persons; Disabled subjects; Electroencephalography; Event-Related Potentials, P300; Female; Fisher's linear discriminant analysis; Humans; Male; Middle Aged; Numerical Analysis, Computer-Assisted; P300; Photic Stimulation - methods; Reaction Time; User-Computer Interface; Disabled subjects; Bayesian linear discriminant analysis; P300; Fisher's linear discriminant analysis; Brain–computer interface
• ISSN: 0165-0270; 1872-678X
• DOI: 10.1016/j.jneumeth.2007.03.005

A brain–computer interface (BCI) is a communication system that translates brain-activity into commands for a computer or other devices. In other words, a BCI allows users to act on their environment by using only brain-activity, without using peripheral nerves and muscles. In this paper, we present a BCI that achieves high classification accuracy and high bitrates for both disabled and able-bodied subjects. The system is based on the P300 evoked potential and is tested with five severely disabled and four able-bodied subjects. For four of the disabled subjects classification accuracies of 100% are obtained. The bitrates obtained for the disabled subjects range between 10 and 25 bits/min. The effect of different electrode configurations and machine learning algorithms on classification accuracy is tested. Further factors that are possibly important for obtaining good classification accuracy in P300-based BCI systems for disabled subjects are discussed.