Detection of paroxysmal EEG discharges using multitaper blind signal source separation

Authors:
Jonathan J. Halford
Affiliations:
Medical University of South Carolina, Department of Neuroscience, Adult Neurology Division, Charleston, SC
Venue:
ICA'07 Proceedings of the 7th international conference on Independent component analysis and signal separation
Year:
2007

Citing 2
Cited 0

An information-maximization approach to blind separation and blind deconvolution

Neural Computation
The Cocktail Party Problem

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The routine electroencephalogram (rEEG) is a useful diagnostic test for neurologists. But this test is frequently misinterpreted by neurologists due to a lack of systematic understanding of paroxysmal electroencephalographic discharges (PEDs), one of the most important features of EEG. A heuristic algorithm is described which uses conventional blind signal source separation (BSSS) algorithms to detect PEDs in a routine EEG recording. This algorithm treats BSSS as a 'black box' and applies it in a computationally-intensive multitaper algorithm in order to detect PEDs without a pre-specification of signal morphology or scalp distribution. The algorithm also attempts to overcome some of the limitations of conventional BSSS as applied to the study of neurophysiology datasets, specifically the 'over-completeness problem' and the 'non-stationarity problem'.