A Hybrid Approach for Artifact Detection in EEG Data

摘要

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.