A hybrid approach for artifact detection in EEG data

Authors:
Jacqueline Fairley;George Georgoulas;Chrysostomos Stylios;David Rye
Affiliations:
Emory University, School of Medicine, Dept. of Neurology, Atlanta, Georgia;Laboratory of Knowledge and Intelligent Computing, Dept. of Informatics and Communications Technology, TEI of Epirus, Kostakioi, Artas;Laboratory of Knowledge and Intelligent Computing, Dept. of Informatics and Communications Technology, TEI of Epirus, Kostakioi, Artas;Emory University, School of Medicine, Dept. of Neurology, Atlanta, Georgia
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Year:
2010

Citing 3
Cited 0

Polysomnography: a systematic review

Technology and Health Care
An introduction to variable and feature selection

The Journal of Machine Learning Research
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a hybrid approach for extreme artifact detection in electroencephalogram (EEG) data, recorded as part of the polysomnogram (psg). The approach is based on the selection of an "optimal" set of features guided by an evolutionary algorithm and a novelty detector based on Parzen window estimation, whose kernel parameter h is also selected by the evolutionary algorithm. The results here suggest that this approach could be very helpful in cases of absence of artifacts during the training process.