Information Technology Reference
In-Depth Information
Chapter 3
Methodological Framework for EEG Feature
Selection Based on Spectral and Temporal
Profiles
Vangelis Sakkalis and Michalis Zervakis
Abstract
Among the various frameworks in which EEG signal analysis has been tra-
ditionally formulated, the most widely studied is employing power spectrum mea-
sures as functions of certain brain pathologies or increased cerebral engagement.
Such measures may form signal features capable of characterizing and differentiat-
ing the underlying neural activity. The objective of this chapter is to validate the use
of wavelets in extracting such features in the time-scale domain and evaluate them
in a simulated environment assuming two tasks (control and target) that resemble
widely used scenarios of assessing and quantifying complex cognitive functions or
pathologies. The motivation for this work stems from the ability of time-frequency
features to encapsulate significant power alteration of EEG in time, thus character-
izing the brain response in terms of both spectral and temporal activation. In the
presented algorithmic scenario, brain areas' electrodes of significant activation dur-
ing the target task are extracted using time-averaged wavelet power spectrum esti-
mation. Then, a refinement step makes use of statistical significance-based criteria
for comparing wavelet power spectra between the target task and the control con-
dition. The results indicate the ability of the proposed methodological framework
to correctly identify and select the most prominent channels in terms of “activity
encapsulation,” which are thought to be the most significant ones.
