Yes/no discrimination with spatio-temporal characteristics of EEG

Author

Kim, Min-Joon ; Shin, Seung-Chul ; Song, Yoonseon ; Ryu, Chang Su

Author_Institution

Electron. & Telecommun. Res. Inst., Taejon, South Korea

Volume

2

fYear

2001

fDate

2001

Firstpage

2009

Abstract

Yes/No discrimination using spatio-temporal characteristics of EEG is investigated. For the correlation between EEG signals, we introduce two new representations useful in time domain calculation, synchronization rate and polarity. Using synchronization rate, average polarity, polarity fluctuation, and normalized cross-correlation, we study possibility of Yes/No discrimination with linear decision function. Overall, normalized cross-correlation exhibits the best results and the others also show affirmative prospects.

Keywords

correlation methods; decision theory; electroencephalography; feature extraction; medical signal processing; signal classification; signal representation; synchronisation; time-domain analysis; EEG spatiotemporal characteristics; artifact-filtering; average polarity; brain computer interface; feature extraction; linear decision function; normalized cross-correlation; polarity fluctuation; synchronization rate; time domain calculation; yes/no discrimination; zero time delay; Band pass filters; Decision making; Delay effects; Electrodes; Electroencephalography; Fluctuations; Frequency synchronization; Monitoring; Pressing; Sampling methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1020625

Filename

1020625