DOI: 10.1101/19000430Jun 25, 2019Paper

Predicting epileptic seizures using nonnegative matrix factorization

MedRxiv : the Preprint Server for Health Sciences
Olivera Stojanović, Gordon Pipa

Abstract

This paper presents a procedure for the patient-specific prediction of epileptic seizures. To this end, a combination of nonnegative matrix factorization (NMF) and smooth basis functions with robust regression is applied to power spectra of intracranial electroencephalographic (iEEG) signals. The resulting time and frequency components capture the dominant information from power spectra, while removing outliers and noise. This makes it possible to detect structure in preictal states, which is used for classification. Linear support vector machines (SVM) with L1 regularization are used to select and weigh the contributions from different number of not equally informative channels among patients. Due to class imbalance in data, synthetic minority over-sampling technique (SMOTE) is applied. The resulting method yields a computationally and conceptually simple, interpretable model of EEG signals of preictal and interictal states, which shows a good performance for the task of seizure prediction.

Related Concepts

Related Feeds

BioRxiv & MedRxiv Preprints

BioRxiv and MedRxiv are the preprint servers for biology and health sciences respectively, operated by Cold Spring Harbor Laboratory. Here are the latest preprint articles (which are not peer-reviewed) from BioRxiv and MedRxiv.

Related Papers

Journal of Bioinformatics and Computational Biology
Belhassen BayarRoman Shterenberg
Computational Intelligence and Neuroscience
Andrzej CichockiR Zdunek
Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Gaoxiang OuyangHuihua Wu
© 2021 Meta ULC. All rights reserved