Single trial EEG classification of observed wrist movements

Author

Lakany, H. ; Valsan, G. ; Conway, B.A.

Author_Institution

Dept. of Bioeng., Univ. of Strathclyde, Glasgow, UK

fYear

2009

fDate

April 29 2009-May 2 2009

Firstpage

359

Lastpage

362

Abstract

In this paper, we present the results of single trial EEG classification of observed wrist movements. This study is part of our endeavour to develop brain computer interfaces as an assistive device for people with severe motor disabilities. Our methods rely on a simple but robust algorithm that requires no subject training to modulate brain activity. We adopt a method based on extraction and selection of statistically significant time-frequency features using ANOVA and principal component analysis. Classification results achieved ~ 80% (plusmn12 %).

Keywords

biomechanics; brain-computer interfaces; electroencephalography; feature extraction; medical signal processing; principal component analysis; signal classification; statistical analysis; ANOVA; EEG; assistive device; brain activity; brain computer interfaces; principal component analysis; severe motor disabilities; single trial classification; time-frequency feature extraction; time-frequency feature selection; wrist movements; Brain computer interfaces; Data mining; Decoding; Electrodes; Electroencephalography; Humans; Neurons; Scalp; Time frequency analysis; Wrist; Brain computer interface; EEG; single trial classification; wrist movements;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering, 2009. NER '09. 4th International IEEE/EMBS Conference on

Conference_Location

Antalya

Print_ISBN

978-1-4244-2072-8

Electronic_ISBN

978-1-4244-2073-5

Type

conf

DOI

10.1109/NER.2009.5109307

Filename

5109307