Information Technology Reference
In-Depth Information
Automatic and Semi-automatic Approaches for
Selecting Prominent Spatial Filters of CSP in BCI
Applications
Nakarin Suppakun and Songrit Maneewongvatana
Department of Computer Engineering, Faculty of Engineering,
King Mongkut's University of Technology Thonburi,
Bangkok, 10140, Thailand
nakarin_sup@hotmail.com, songrit@cpe.kmutt.ac.th
Abstract.
Common Spatial Patterns (CSP)
has become a popular approach for
feature extraction in
Brain Computer Interface (BCI)
research. This is because
it can provide a good discrimination between 2 motor imaginary tasks. In the-
ory, the first and the last spatial filters from CSP should exhibit the most dis-
criminate between 2 classes. But in practice, this is not always true, especially if
either of these 2 filters emphasizes on a channel that has high variability of
variance of sample matrices among trials. Such spatial filter is unstable on a
single class, and thus it is not appropriate to use for discrimination. Further-
more, one or both of these 2 spatial filters may not localize the brain area that
relates to motor imagery. The desired spatial filters may be at the second or at
an even greater order of sorted eigenvalue. In this work, we propose to find an
appropriate set of spatial filters of CSP projection matrix, which may provide
higher classification accuracy than using just 2 peak spatial filters. We present 2
selection approaches to select the set of prominent spatial filters: the first one is
automatic approach; the second one is semi-automatic approach requiring man-
ual analysis by human. We assessed both of our approaches on the data sets
from BCI Competition III and IV. The results show that both selection ap-
proaches can find the appropriated prominent spatial filters.
1 Introduction
Brain computer interface (BCI) is a technology that finds new communicative ways
of using only the brain to command machines. An electrode cap is placed on the head
of the user for measuring electroencephalography (EEG) signals. To command the
machine, the user imagines the specific task such as limb movement, composing
words. These tasks affect the pattern of EEG signal. Computer would detect and clas-
sify these patterns into different tasks in order to control the computer application
(such as cursor movement), or control the machine (e.g. wheelchair). In recent years,
Common Spatial Patterns (CSP) has become a popular technique for feature extrac-
tion in BCI research. This is due to its good feature extraction performance that can
be easily discriminated even by a simple classifier. Koles et al. introduced CSP to
analyze EEG signals for discriminating between normal and abnormal EEGs [1].
