Paper Info
Title
The Effect of Multiscale PCA De-noising in Epileptic Seizure Detection
Abstract
In this paper we describe the effect of Multiscale Principal Component Analysis (MSPCA) de-noising method in terms of epileptic seizure detection. In addition, we developed a patient-independent seizure detection algorithm using Freiburg EEG database. Each patient contains datasets called "ictal" and "interictal". Window length of 16 s was applied to extract EEG segments from datasets of each patient. Furthermore, Power Spectral Density (PSD) of each EEG segment was estimated using different spectral analysis methods. Afterwards, these values were fed as input to different machine learning methods that were responsible for seizure detection. We also applied MSPCA de-noising method to EEG segments prior to PSD estimation to determine if MSPCA can further enhance the classifiers' performance. The MSPCA drastically improved both the sensitivity and the specificity, increasing the overall accuracy of all three classifiers up to 20 %. The best overall detection accuracy (99.59 %) was achieved when Eigenvector analysis was used for frequency estimation, and C4.5 as a classifier. The experiment results show that MSPCA is an effective de-noising method for improving the classification performance in epileptic seizure detection.
Year
DOI
Venue
2014
10.1007/s10916-014-0131-0
Journal of Medical Systems
Keywords
Field
DocType
k nearest neighbor,multiscale pca,electroencephalogram,multilayer perceptron,spectral analysis,epileptic seizure detection,machine learning,decision tree
Seizure detection,Pattern recognition,Computer science,Speech recognition,Epileptic seizure,Spectral density,Artificial intelligence,Spectral analysis,Classifier (linguistics),Electroencephalography,Principal component analysis,Ictal
Journal
Volume
Issue
ISSN
38
10
1573-689X
Citations 
PageRank 
References 
82
0.95
22
Authors
2
Name
Order
Citations
PageRank
Jasmin Kevric11627.27
Abdulhamit Subasi2134981.18