Please use this identifier to cite or link to this item:
Title: Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods
Authors: Rasekhi, Jalil 
Mollaei, Mohammad Reza Karami 
Bandarabadi, Mojtaba 
Teixeira, Cesar A. 
Dourado, Antonio 
Keywords: Seizure prediction; Epilepsy; Classification; Features selection; Space reduction
Issue Date: 30-Jul-2013
Publisher: Elsevier
Citation: RASEKHI, Jalil [et. al] - Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods. "Journal of Neuroscience Methods". ISSN 0165-0270. Vol. 217 Nº. 1-2 (2013) p. 9-16
Serial title, monograph or event: Journal of Neuroscience Methods
Volume: 217
Issue: 1-2
Abstract: Combining multiple linear univariate features in one feature space and classifying the feature space using machine learning methods could predict epileptic seizures in patients suffering from refractory epilepsy. For each patient, a set of twenty-two linear univariate features were extracted from 6 electroencephalogram (EEG) signals to make a 132 dimensional feature space. Preprocessing and normalization methods of the features, which affect the output of the seizure prediction algorithm, were studied in terms of alarm sensitivity and false prediction rate (FPR). The problem of choosing an optimal preictal time was tackled using 4 distinct values of 10, 20, 30, and 40 min. The seizure prediction problem has traditionally been considered a two-class classification problem, which is also exercised here. These studies have been conducted on the features obtained from 10 patients. For each patient, 48 different combinations of methods are compared to find the best configuration. Normalization by dividing by the maximum and smoothing are found to be the best configuration in most of the patients. The results also indicate that applying machine learning methods on a multidimensional feature space of 22 univariate features predicted seizure onsets with high performance. On average, the seizures were predicted in 73.9% of the cases (34 out of 46 in 737.9 h of test data), with a FPR of 0.15 h−1.
ISSN: 0165-0270
DOI: 10.1016/j.jneumeth.2013.03.019
Rights: openAccess
Appears in Collections:I&D CISUC - Artigos em Revistas Internacionais
FCTUC Eng.Informática - Artigos em Revistas Internacionais

Files in This Item:
File Description SizeFormat
Preprocessing effects of 22 linear univariate features.pdf493.55 kBAdobe PDFView/Open
Show full item record


checked on May 29, 2020

Citations 5

checked on Jun 2, 2021

Page view(s) 20

checked on Jun 9, 2021

Download(s) 20

checked on Jun 9, 2021

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.