A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals
Properly determining the discriminative fea-tures which characterize the inherent behaviors of electro-encephalography (EEG) signals remains a great challenge for epileptic seizure detection. In this present study, a novel feature selection scheme based on the discrete wavelet packet decomposition a...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer International Publishing
2017
|
Subjects: | |
Online Access: | http://eprints.uthm.edu.my/5123/1/AJ%202017%20%28274%29%20Development%20of%20new%20all-optical%20signal.pdf http://eprints.uthm.edu.my/5123/ http://dx.doi.org/10.1007/s10044-017-0642-7 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Tun Hussein Onn Malaysia |
Language: | English |
id |
my.uthm.eprints.5123 |
---|---|
record_format |
eprints |
spelling |
my.uthm.eprints.51232022-01-06T01:47:42Z http://eprints.uthm.edu.my/5123/ A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals Ong, Pauline Zainuddin, Zarita Kee, Huong Lai TJ Mechanical engineering and machinery Properly determining the discriminative fea-tures which characterize the inherent behaviors of electro-encephalography (EEG) signals remains a great challenge for epileptic seizure detection. In this present study, a novel feature selection scheme based on the discrete wavelet packet decomposition and cuckoo search algorithm (CSA) was proposed. The normal as well as epileptic EEG record-ings were first decomposed into various frequency bands by means of wavelet packet decomposition, and subsequently, statistical features at all developed nodes in the wavelet packet decomposition tree were derived. Instead of using the complete set of the extracted features to construct a wavelet neural networks-based classifier, an optimal feature subset that maximizes the predictive competence of the classifier was selected by using the CSA. Experimental results on the publicly available benchmarks demonstrated that the pro-posed feature subset selection scheme achieved promising recognition accuracies of 98.43–100%, and the results were statistically significant using z-test with p value <0.0001. Springer International Publishing 2017 Article PeerReviewed text en http://eprints.uthm.edu.my/5123/1/AJ%202017%20%28274%29%20Development%20of%20new%20all-optical%20signal.pdf Ong, Pauline and Zainuddin, Zarita and Kee, Huong Lai (2017) A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals. Pattern Anal Application. pp. 1-13. http://dx.doi.org/10.1007/s10044-017-0642-7 |
institution |
Universiti Tun Hussein Onn Malaysia |
building |
UTHM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tun Hussein Onn Malaysia |
content_source |
UTHM Institutional Repository |
url_provider |
http://eprints.uthm.edu.my/ |
language |
English |
topic |
TJ Mechanical engineering and machinery |
spellingShingle |
TJ Mechanical engineering and machinery Ong, Pauline Zainuddin, Zarita Kee, Huong Lai A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
description |
Properly determining the discriminative fea-tures which characterize the inherent behaviors of electro-encephalography (EEG) signals remains a great challenge for epileptic seizure detection. In this present study, a novel feature selection scheme based on the discrete wavelet packet decomposition and cuckoo search algorithm (CSA) was proposed. The normal as well as epileptic EEG record-ings were first decomposed into various frequency bands by means of wavelet packet decomposition, and subsequently, statistical features at all developed nodes in the wavelet packet decomposition tree were derived. Instead of using the complete set of the extracted features to construct a wavelet neural networks-based classifier, an optimal feature subset that maximizes the predictive competence of the classifier was selected by using the CSA. Experimental results on the publicly available benchmarks demonstrated that the pro-posed feature subset selection scheme achieved promising recognition accuracies of 98.43–100%, and the results were statistically significant using z-test with p value <0.0001. |
format |
Article |
author |
Ong, Pauline Zainuddin, Zarita Kee, Huong Lai |
author_facet |
Ong, Pauline Zainuddin, Zarita Kee, Huong Lai |
author_sort |
Ong, Pauline |
title |
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
title_short |
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
title_full |
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
title_fullStr |
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
title_full_unstemmed |
A novel selection of optimal statistical features in the DWPT domain for discrimination of ictal and seizure‑free electroencephalography signals |
title_sort |
novel selection of optimal statistical features in the dwpt domain for discrimination of ictal and seizure‑free electroencephalography signals |
publisher |
Springer International Publishing |
publishDate |
2017 |
url |
http://eprints.uthm.edu.my/5123/1/AJ%202017%20%28274%29%20Development%20of%20new%20all-optical%20signal.pdf http://eprints.uthm.edu.my/5123/ http://dx.doi.org/10.1007/s10044-017-0642-7 |
_version_ |
1738581340223176704 |