Epileptic Seizures Detection Based on Non-linear Characteristics Coupled with Machine Learning Techniques

Miften, Firas Sabar and Diykh, Mohammed and Abdulla, Shahab ORCID: https://orcid.org/0000-0002-1193-6969 and Green, Jonathan H. ORCID: https://orcid.org/0000-0003-1468-1970 (2020) Epileptic Seizures Detection Based on Non-linear Characteristics Coupled with Machine Learning Techniques. In: Frontiers in Clinical Drug Research: CNS and Neurological Disorders. Frontiers in Clinical Drug Research, 7. Bentham Science Publishers Ltd., Sharjah, United Arab Emirates, pp. 23-39. ISBN 9789811447501


The use of transformation techniques (such as a wavelet transform, Fourier transform, or hybrid transform) to detect epileptic seizures by means of EEG signals is not adequate because these signals have a nonstationary and nonlinear nature. This paper reports on the design of a novel technique based, instead, on the domain of graphs. The dimensionality of each single EEG channel is reduced using a segmentation technique, and each EEG channel is then mapped onto an undirected weighted graph. A set of structural and topological graph characteristics is extracted and investigated, and several machine learning techniques are utilized to categorize the graph’s attributes. The results demonstrate that the use of graphs improves the quality of epileptic seizure detection. The proposed method can identify EEG abnormities that are difficult to detect accurately using other transformation techniques, especially when dealing with EEG big data.

Statistics for USQ ePrint 38741
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Faculty/School / Institute/Centre: Historic - Open Access College (1 Jul 2013 - 7 Jun 2020)
Faculty/School / Institute/Centre: Current - Faculty of Business, Education, Law and Arts - School of Education (1 Jul 2019 -)
Date Deposited: 25 Aug 2020 01:27
Last Modified: 14 Sep 2020 05:17
Uncontrolled Keywords: Epileptic Seizures; Epileptic EEG Signals; Graphs; Modularity; Multi-Channel; Statistical Features
Fields of Research (2008): 11 Medical and Health Sciences > 1199 Other Medical and Health Sciences > 119999 Medical and Health Sciences not elsewhere classified
Fields of Research (2020): 42 HEALTH SCIENCES > 4299 Other health sciences > 429999 Other health sciences not elsewhere classified
Socio-Economic Objectives (2008): C Society > 92 Health > 9299 Other Health > 929999 Health not elsewhere classified
Identification Number or DOI: https://doi.org/10.2174/97898114475251200701
URI: http://eprints.usq.edu.au/id/eprint/38741

Actions (login required)

View Item Archive Repository Staff Only