Title :
An SFFS technique for EEG feature classification to identify sub-groups
Author :
Baker, Mary C. ; Kerr, Andy S. ; Hames, Elizabeth ; Akrofi, Kwaku
Author_Institution :
Dept. of Electr. & Comput. Eng., Texas Tech Univ., Lubbock, TX, USA
Abstract :
Pattern recognition techniques can be applied to problems in medicine to aid diagnostic accuracy and uncover patterns associated with disease states that are not always obvious to the clinician. In this work, a sequential forward floating search technique (SFFS) was applied to the problem of classification of patients with Alzheimer´s disease (AD), mild cognitive impairment (MCI) and normal controls. The technique resulted in superior classification rates over statistical methods, as described in the paper. The advantage of SFFS may lie in the technique´s ability to identify subgroups within diagnostic categories, and to correctly select features that identify those sub-groups.
Keywords :
electroencephalography; medical signal processing; statistical analysis; AD; Alzheimer´s disease; EEG feature classification; MCI; SFFS technique; mild cognitive impairment; pattern recognition techniques; sequential forward floating search technique; statistical methods; superior classification rates; Alzheimer´s disease; Classification algorithms; Coherence; Electroencephalography; Optical character recognition software; Support vector machine classification;
Conference_Titel :
Computer-Based Medical Systems (CBMS), 2012 25th International Symposium on
Conference_Location :
Rome
Print_ISBN :
978-1-4673-2049-8
DOI :
10.1109/CBMS.2012.6266361