Epileptic Seizures Detection Based on Non-linear Characteristics Coupled with Machine Learning Techniques
Edited book (chapter)
Chapter Title | Epileptic Seizures Detection Based on Non-linear Characteristics Coupled with Machine Learning Techniques |
---|---|
Book Chapter Category | Edited book (chapter) |
ERA Publisher ID | 1317 |
Book Title | Frontiers in Clinical Drug Research: CNS and Neurological Disorders |
Authors | Miften, Firas Sabar (Author), Diykh, Mohammed (Author), Abdulla, Shahab (Author) and Green, Jonathan H. (Author) |
Editors | Rahman, Atta-ur- and Amtul, Zareen |
Volume | 7 |
Page Range | 23-39 |
Series | Frontiers in Clinical Drug Research |
Chapter Number | 2 |
Number of Pages | 17 |
Year | 2020 |
Publisher | Bentham Science Publishers |
Place of Publication | Sharjah, United Arab Emirates |
ISBN | 9789811447501 |
9789811447525 | |
ISSN | 2451-8883 |
2214-7527 | |
Digital Object Identifier (DOI) | https://doi.org/10.2174/97898114475251200701 |
Web Address (URL) | https://benthambooks.com/book/9789811447525/chapter/181761/ |
Abstract | 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. |
Keywords | Epileptic Seizures; Epileptic EEG Signals; Graphs; Modularity; Multi-Channel; Statistical Features |
ANZSRC Field of Research 2020 | 429999. Other health sciences not elsewhere classified |
Byline Affiliations | University of Thi-Qar, Iraq |
Faculty of Health, Engineering and Sciences | |
USQ College | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q5vq6/epileptic-seizures-detection-based-on-non-linear-characteristics-coupled-with-machine-learning-techniques
247
total views8
total downloads8
views this month0
downloads this month