Parallel man-machine training in development of EEG-based cursor control

Author

Kostov, Aleksander ; Polak, Mark

Author_Institution

Fac. of Rehabilitation Med., Alberta Univ., Edmonton, Alta., Canada

Volume

8

Issue

2

fYear

2000

fDate

6/1/2000 12:00:00 AM

Firstpage

203

Lastpage

205

Abstract

A new parallel man-machine training approach to brain-computer interface (BCI) succeeded through a unique application of machine learning methods. The BCI system could train users to control an animated cursor on the computer screen by voluntary electroencephalogram (EEG) modulation. The authors´ BCI system requires only two to four electrodes, and has a relatively short training time for both the user and the machine. Moving the cursor in one dimension, the authors´ subjects were able to hit 100% of randomly selected targets, while in two dimensions, accuracies of approximately 63% and 76% was achieved with the authors´ two subjects

Keywords

computer based training; electroencephalography; handicapped aids; learning (artificial intelligence); EEG-based cursor control development; computer screen animated cursor control; machine learning methods; parallel man-machine training; randomly selected targets; severe neuromuscular disability; training time; voluntary electroencephalogram modulation; Application software; Biomedical imaging; Brain modeling; Computer interfaces; Control systems; Electroencephalography; Graphical user interfaces; Learning systems; Machine learning; Man machine systems;

fLanguage

English

Journal_Title

Rehabilitation Engineering, IEEE Transactions on

Publisher

ieee

ISSN

1063-6528

Type

jour

DOI

10.1109/86.847816

Filename

847816