Non-linear classifiers applied to EEG analysis for epilepsy seizure detection
Centre for Secure Information Technologies, School of EEECS, Queens University Belfast, BT3 9DT, UK
j.martinez-del-rincon@qub.ac.uk
Computer Architecture and Networks Group, University of Castilla-La Mancha, Paseo de la Universidad, 4, Ciudad Real, Spain
mariajose.santofimia@uclm.es
Institute of Energy Research and Industrial Applications, University of Castilla-La Mancha, Ciudad Real, Spain
xavier.deltoro@uclm.es
Computer Architecture and Networks Group, University of Castilla-La Mancha, Paseo de la Universidad, 4, Ciudad Real, Spain
jesus.barba@uclm.es
Hospital Regional Universitario Carlos Haya, Av. de Carlos Haya s/n, Málaga 29010, Spain
franciscaromerocrespo@gmail.com
Hospital Regional Universitario Carlos Haya, Av. de Carlos Haya s/n, Málaga 29010, Spain
patricianavas@gmail.com
Computer Architecture and Networks Group, University of Castilla-La Mancha, Paseo de la Universidad, 4, Ciudad Real, Spain
juancarlos.lopez@uclm.es
JOURNAL — Expert Sstems with Applications
PAGES — 99-112
ISSN — 0957-4174
VOLUME — 86
PUBLISHER — Elsevier
YEAR — 2017
Jesus Martinez-del-Rincon, Maria J. Santofimia, Xavier del Toro, Jesus Barba, Francisca Romero, Patricia Navas, Juan C. Lopez, Non-linear classifiers applied to EEG analysis for epilepsy seizure detection, In Expert Systems with Applications, Volume 86, 2017, Pages 99-112, ISSN 0957-4174.
@article{MARTINEZDELRINCON201799,
title = "Non-linear classifiers applied to EEG analysis for epilepsy seizure detection",
journal = "Expert Systems with Applications",
volume = "86",
number = "Supplement C",
pages = "99 - 112",
year = "2017",
issn = "0957-4174",
doi = "https://doi.org/10.1016/j.eswa.2017.05.052",
url = "http://www.sciencedirect.com/science/article/pii/S0957417417303743",
author = "Jesus Martinez-del-Rincon and Maria J. Santofimia and Xavier del Toro and Jesus Barba and Francisca Romero and Patricia Navas and Juan C. Lopez",
keywords = "Classification algorithms, Non-linear classifiers, SVM, Bag of words, Wavelet, Epilepsy"
}
Abstract
This work presents a novel approach for automatic epilepsy seizure detection based on EEG analysis that exploits the underlying non-linear nature of EEG data. In this paper, two main contributions are presented and validated: the use of non-linear classifiers through the so-called kernel trick and the proposal of a Bag-of-Words model for extracting a non-linear feature representation of the input data in an unsupervised manner. The performance of the resulting system is validated with public datasets, previously processed to remove artifacts or external disturbances, but also with private datasets recorded under realistic and non-ideal operating conditions. The use of public datasets caters for comparison purposes whereas the private one shows the performance of the system under realistic circumstances of noise, artifacts, and signals of different amplitudes. Moreover, the proposed solution has been compared to state-of-the-art works not only for pre-processed and public datasets but also with the private datasets. The mean F1-measure shows a 10% improvement over the second-best ranked method including cross-dataset experiments. The obtained results prove the robustness of the proposed solution to more realistic and variable conditions.