Developing a tunable Q-factor wavelet transform based algorithm for epileptic EEG feature extraction
Paper
Paper/Presentation Title | Developing a tunable Q-factor wavelet transform based algorithm for epileptic EEG feature extraction |
---|---|
Presentation Type | Paper |
Authors | Al Ghayab, Hadi Ratham (Author), Li, Yan (Author), Siuly, Siuly (Author), Abdulla, Shahab (Author) and Wen, Paul (Author) |
Editors | Siuly, Siuly, Huang, Zhisheng, Aickelin, Uwe, Zhou, Rui, Wang, Hua, Zhang, Yanchun and Klimenko, Stanislav |
Journal or Proceedings Title | Proceedings of the 6th International Conference on Health Information Science: Health Information Science (HIS 2017) |
ERA Conference ID | 73271 |
Journal Citation | 10594, pp. 45-55 |
Number of Pages | 11 |
Year | 2017 |
Place of Publication | Germany |
ISBN | 9783319691817 |
9783319691824 | |
Digital Object Identifier (DOI) | https://doi.org/10.1007/978-3-319-69182-4_6 |
Web Address (URL) of Paper | https://link.springer.com/chapter/10.1007%2F978-3-319-69182-4_6#citeas |
Conference/Event | 6th International Conference on Health Information Science: Health Information Science (HIS 2017) |
International Conference on Health Information Science (HIS) | |
Event Details | 6th International Conference on Health Information Science: Health Information Science (HIS 2017) Event Date 07 to end of 09 Oct 2017 Event Location Moscow, Russian Federation |
Event Details | International Conference on Health Information Science (HIS) HIS |
Abstract | Brain signals refer to electroencephalogram (EEG) data that contain the most important information in the human brain, which are non-stationary and nonlinear in nature. EEG signals are a mixture of sustained oscillation and non-oscillatory transients that are difficult to deal with by linear methods. This paper proposes a new technique based on a tunable Q-factor wavelet transform (TQWT) and statis-tical method (SM), denoted as TQWT-SM, to analyze epileptic EEG recordings. Firstly, EEG signals are decomposed into different sub-bands by the TWQT method, which is parameterized by its Q-factor and redundancy. This approach depends on the resonance of signals, instead of frequency or scales as the Fourier and wavelet transforms do. Secondly, each type of the sub-band vector is divided into n windows, and 10 statistical features from each window are extracted. Finally all the obtained statistical features are forwarded to a k nearest neighbor (k-NN) classifier to evaluate the performance of the proposed TQWT-SM method. The TQWT-SM features extraction method achieves good experimental results for the seven different epileptic EEG binary-categories by the k-NN classifier, in terms of accuracy (Acc), Matthew’s correlation coefficient (MCC), and F score (F1). The outcomes of the proposed technique can assist the experts to detect epi-leptic seizures. |
Keywords | electroencephalography (EEG), tunable Q-factor wavelet transform, statistical method, k nearest neighbour |
ANZSRC Field of Research 2020 | 400399. Biomedical engineering not elsewhere classified |
461399. Theory of computation not elsewhere classified | |
460905. Information systems development methodologies and practice | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | Faculty of Health, Engineering and Sciences |
Department of Mathematics and Computing | |
Victoria University | |
Open Access College | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q473y/developing-a-tunable-q-factor-wavelet-transform-based-algorithm-for-epileptic-eeg-feature-extraction
743
total views15
total downloads0
views this month0
downloads this month