A new method: To determine the applicability of linear ICA to a given problem. (High lighted by an EEG case study applied to epilepsy)

C. P. Unsworth*, J. J. Spowart, G. Lawson, J. K. Brown, B. Mulgrew, R. A. Minns, M. Clark

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A new method, in the form of a hypothesis test, is presented that compares the eigenvalues of a multi-channel data set to eigenvalues of a synthetic mixture. The synthetic mixture is created from a set of independent components (IC's) that have been demixed from the original data. The IC's are then repropagated from a fictitious source space to a set of fictitious sensors under ICA rules. The hypothesis is: if the real data has been formed in compliance to the ICA rules then its eigenvalues should be the same as the synthetic mixture formed from the repropagated IC's. The hypothesis test is a general method and can be applied to any ICA problem. Here four common cases of epileptic seizure from electroencephalogram (EEG) records are used to highlight the method for a real case study

Original languageEnglish
Title of host publication2004 Sensor Array and Multichannel Signal Processing Workshop
Pages182-185
Number of pages4
Publication statusPublished - 1 Dec 2004
Event2004 Sensor Array and Multichannel Signal Processing Workshop - Barcelona, Spain
Duration: 18 Jul 200421 Jul 2004

Conference

Conference2004 Sensor Array and Multichannel Signal Processing Workshop
Country/TerritorySpain
CityBarcelona
Period18/07/0421/07/04

Fingerprint

Dive into the research topics of 'A new method: To determine the applicability of linear ICA to a given problem. (High lighted by an EEG case study applied to epilepsy)'. Together they form a unique fingerprint.

Cite this