Enabling computer decisions based on EEG input

Author

Culpepper, Benjamin J. ; Keller, Robert M.

Author_Institution

Neuro Eng. Laboratory, NASA Ames Res. Center, Moffett Field, CA, USA

Volume

11

Issue

4

fYear

2003

Firstpage

354

Lastpage

360

Abstract

Multilayer neural networks were successfully trained to classify segments of 12-channel electroencephalogram (EEG) data into one of five classes corresponding to five cognitive tasks performed by a subject. Independent component analysis (ICA) was used to segregate obvious artifact EEG components from other sources, and a frequency-band representation was used to represent the sources computed by ICA. Examples of results include an 85% accuracy rate on differentiation between two tasks, using a segment of EEG only 0.05 s long and a 95% accuracy rate using a 0.5-s-long segment.

Keywords

cognition; electroencephalography; feedforward neural nets; independent component analysis; user interfaces; 0.5 s; 12-channel electroencephalogram; EEG input; brain-computer interface; cognitive tasks; computer decisions; independent component analysis; multilayer neural networks; Decoding; Electroencephalography; Encoding; Humans; Independent component analysis; Keyboards; Mice; Neural networks; Physics computing; Signal processing; Adolescent; Algorithms; Artificial Intelligence; Brain; Cognition; Electroencephalography; Evoked Potentials; Humans; Male; Neural Networks (Computer); Principal Component Analysis; Reproducibility of Results; Sensitivity and Specificity; User-Computer Interface;

fLanguage

English

Journal_Title

Neural Systems and Rehabilitation Engineering, IEEE Transactions on

Publisher

ieee

ISSN

1534-4320

Type

jour

DOI

10.1109/TNSRE.2003.819788

Filename

1261745