Computational and Mathematical Methods in Medicine
Volume 2013 (2013), Article ID 243257, 10 pages
Research Article

Evaluation of EEG Features in Decoding Individual Finger Movements from One Hand

Ran Xiao1 and Lei Ding1,2

1School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA
2Center for Biomedical Engineering, University of Oklahoma, Norman, OK 73019, USA

Received 4 February 2013; Accepted 3 April 2013

Academic Editor: Yiwen Wang

Copyright © 2013 Ran Xiao and Lei Ding. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


With the advancements in modern signal processing techniques, the field of brain-computer interface (BCI) is progressing fast towards noninvasiveness. One challenge still impeding these developments is the limited number of features, especially movement-related features, available to generate control signals for noninvasive BCIs. A few recent studies investigated several movement-related features, such as spectral features in electrocorticography (ECoG) data obtained through a spectral principal component analysis (PCA) and direct use of EEG temporal data, and demonstrated the decoding of individual fingers. The present paper evaluated multiple movement-related features under the same task, that is, discriminating individual fingers from one hand using noninvasive EEG. The present results demonstrate the existence of a broadband feature in EEG to discriminate individual fingers, which has only been identified previously in ECoG. It further shows that multiple spectral features obtained from the spectral PCA yield an average decoding accuracy of 45.2%, which is significantly higher than the guess level ( ) and other features investigated ( ), including EEG spectral power changes in alpha and beta bands and EEG temporal data. The decoding of individual fingers using noninvasive EEG is promising to improve number of features for control, which can facilitate the development of noninvasive BCI applications with rich complexity.