DocumentCode :
139928
Title :
Optimal EEG feature selection from average distance between events and non-events
Author :
LaRocco, John ; Innes, Carrie R. H. ; Bones, Philip J. ; Weddell, Stephen ; Jones, Richard D.
Author_Institution :
UC Dept. of Electr. & Comput. Eng., New Zealand Brain Res. Inst., Christchurch, New Zealand
fYear :
2014
fDate :
26-30 Aug. 2014
Firstpage :
2641
Lastpage :
2644
Abstract :
Biosignal classification systems often have to deal with extraneous features, highly imbalanced datasets, and a low SNR. A robust feature selection/reduction method is a crucial step in this process. Sets of artificial data were generated to test a prototype EEG-based microsleep detection system, consisting of a combination of EEG and 2-s bursts of 15-Hz sinusoids of varied signal-to-noise ratios (SNRs) ranging from 16 to 0.03. The balance between events and non-events was varied between evenly balanced and highly imbalanced (e.g., events occurring only 2% of the time). Features were spectral estimates of various EEG bands (e.g., alpha band power) or ratios between them. A total of 34 features for each of the 16 channels yielded a total of 544 features. Five minutes of EEG from a total of eight subjects were used in the generation of the artificial data. Several feature reduction and classifier structures were investigated. Taking only a single feature corresponding to the maximum of average distance between events and non-events (ADEN) on unbalanced data yielded a phi correlation of 0.94 on the mock data with an SNR of 0.3, compared with a phi coefficient of 0.00 for principal component analysis (PCA). ADEN consistently outperformed alternative system configurations, independent of the classifier utilized. While ADEN´s high performance may be due to the nature of the artificial dataset, this simulation has demonstrated strong potential compared to other feature selection/reduction methods.
Keywords :
bioelectric potentials; electroencephalography; feature selection; medical signal detection; medical signal processing; neurophysiology; noise; principal component analysis; signal classification; sleep; biosignal classification systems; frequency 15 Hz; optimal EEG feature reduction methods; optimal EEG feature selection methods; principal component analysis; prototype EEG-based microsleep detection system; signal-to-noise ratio variation; time 2 s; time 5 min; Classification algorithms; Electroencephalography; Electronic mail; Feature extraction; Pattern recognition; Principal component analysis; Signal to noise ratio;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2014 36th Annual International Conference of the IEEE
Conference_Location :
Chicago, IL
ISSN :
1557-170X
Type :
conf
DOI :
10.1109/EMBC.2014.6944165
Filename :
6944165
Link To Document :
بازگشت