Nonconvulsive epileptic seizures detection using multiway data analysis

Yissel Rodríguez Aldana, Borbála Hunyadi, Enrique J.Maranón Reyes, Valia Rodríguez Rodríguez, Sabine Van Huffel

Research output: Chapter in Book/Published conference outputConference publication


Nonconvulsive status epilepticus (NCSE) is observed when the patient undergoes a persistent electroencephalographic epileptic episode without physical symptoms. This condition is commonly found in critically ill patients from intensive care units and constitutes a medical emergency. This paper proposes a method to detect nonconvulsive epileptic seizures (NCES). To perform the NCES detection the electroencephalogram (EEG) is represented as a third order tensor with axes frequency × time × channels using Wavelet or Hilbert-Huang transform. The signatures obtained from the tensor decomposition are used to train five classifiers to separate between the normal and seizure EEG. Classification is performed in two ways: (1) with each signature of the different modes separately, (2) with all signatures assembled. The algorithm is tested on a database containing 139 nonconvulsive seizures. From all performed analysis, Hilbert-Huang Tensors Space and assembled signatures demonstrate to be the best features to classify between seizure and non-seizure EEG.

Original languageEnglish
Title of host publication25th European Signal Processing Conference, EUSIPCO 2017
Number of pages5
ISBN (Electronic)9780992862671
Publication statusPublished - 26 Oct 2017
Event25th European Signal Processing Conference, EUSIPCO 2017 - Kos, Greece
Duration: 28 Aug 20172 Sept 2017

Publication series

Name2017 25th European Signal Processing Conference (EUSIPCO)
ISSN (Print)2076-1465


Conference25th European Signal Processing Conference, EUSIPCO 2017


Dive into the research topics of 'Nonconvulsive epileptic seizures detection using multiway data analysis'. Together they form a unique fingerprint.

Cite this