Abstract:
Brain functioning is severely affected in long-term alcoholics. This degradation is reflected in Electroencephalographic signals(EEG) which are electrical signals in the ...Show MoreMetadata
Abstract:
Brain functioning is severely affected in long-term alcoholics. This degradation is reflected in Electroencephalographic signals(EEG) which are electrical signals in the brain generated due to the firing of neurons. These signals can be used to understand the changes in the brain of an alcoholic. In this work, Riemann geometry based classification framework is used to study changes in interdependencies across various brain regions in alcoholics. Publicly available data of 50 subjects(25 alcoholics, 25 control) with 10 trials each are used in this work. Spatial covariance matrices for empirically chosen channels are input to two classification scenarios. In the first scenario, covariance matrices are used as features to ”Minimum Distance to Mean classifier with geodesic filtering(fgMDM)” on the manifold. The highest mean accuracy obtained is 82.8% for the channel set of AF2 & P6. In the second scenario, the covariance matrices are mapped to tangent space and the resultant tangent vectors are used as features for Support Vector Machine with Radial Basis Function kernel. In this scenario, the highest mean accuracy obtained is 87.6% for the channel set FP1 & PO1. Both scenarios indicate significant changes across frontal lobe in comparison to the posterior lobes of the brain, in alcoholics. Changes in covariance matrices for the EEG, when the same stimulus is provided, indicate changes in brain functioning, consistent with alcoholism. Hence, Riemann geometry is a promising framework to study changes in brain region inter-dependencies, for subjects exposed to different brain-altering situations.
Date of Conference: 02-06 September 2019
Date Added to IEEE Xplore: 18 November 2019
ISBN Information: