Citation: Al-Hadeethi, H.; Abdulla,
S.; Diykh, M.; Green, J.H.
Determinant of Covariance Matrix
Model Coupled with AdaBoost
Classification Algorithm for EEG
Seizure Detection. Diagnostics 2022,
12, 74. https://doi.org/10.3390/
diagnostics12010074
Academic Editors: Keun Ho Ryu
and Nipon Theera-Umpon
Received: 28 November 2021
Accepted: 25 December 2021
Published: 29 December 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Determinant of Covariance Matrix Model Coupled with
AdaBoost Classification Algorithm for EEG Seizure Detection
Hanan Al-Hadeethi
1
, Shahab Abdulla
2,
*, Mohammed Diykh
3,4,
* and Jonathan H. Green
2,5,
*
1
School of Sciences, University of Southern Queensland, Toowoomba, QLD 4300, Australia;
Hananalihamood.alhadeethi@usq.edu.au
2
USQ College, University of Southern Queensland, Toowoomba, QLD 4300, Australia
3
College of Education for Pure Science, University of Thi-Qar, Nasiriyah 64001, Iraq
4
Information and Communication Technology Research Group, Scientific Research Centre, Al-Ayen University,
Nasiriyah 64001, Iraq
5
Faculty of the Humanities, University of the Free State, Bloemfontein 9301, South Africa
* Correspondence: Shahab.Abdulla@usq.edu.au (S.A.); mohammed.diykh@usq.edu.au or
mohammed.diykh@utq.edu.iq (M.D.); Jonathan.Green@usq.edu.au (J.H.G.)
Abstract:
Experts usually inspect electroencephalogram (EEG) recordings page-by-page in order to
identify epileptic seizures, which leads to heavy workloads and is time consuming. However, the
efficient extraction and effective selection of informative EEG features is crucial in assisting clinicians
to diagnose epilepsy accurately. In this paper, a determinant of covariance matrix (Cov–Det) model is
suggested for reducing EEG dimensionality. First, EEG signals are segmented into intervals using
a sliding window technique. Then, Cov–Det is applied to each interval. To construct a features
vector, a set of statistical features are extracted from each interval. To eliminate redundant features,
the Kolmogorov–Smirnov (KST) and Mann–Whitney U (MWUT) tests are integrated, the extracted
features ranked based on KST and MWUT metrics, and arithmetic operators are adopted to construe
the most pertinent classified features for each pair in the EEG signal group. The selected features are
then fed into the proposed AdaBoost Back-Propagation neural network (AB_BP_NN) to effectively
classify EEG signals into seizure and free seizure segments. Finally, the AB_BP_NN is compared with
several classical machine learning techniques; the results demonstrate that the proposed mode of
AB_BP_NN provides insignificant false positive rates, simpler design, and robustness in classifying
epileptic signals. Two datasets, the Bern–Barcelona and Bonn datasets, are used for performance
evaluation. The proposed technique achieved an average accuracy of 100% and 98.86%, respectively,
for the Bern–Barcelona and Bonn datasets, which is considered a noteworthy improvement compared
to the current state-of-the-art methods.
Keywords: Electroencephalography; Cov–Det; epileptic AB_BP_NN; KST; MWUT
1. Introduction
Epilepsy is a brain disorder characterized by abnormal discharge of neurons and by
seizures that can lead to cognitive, psychological and social consequences [
1
–
7
]. Based on
the latest report on epilepsy released by the World Health Organization (WHO), more than
50 million people worldwide have this disease [
8
,
9
]. The number of people with epilepsy
is expected to increase further thanks to increasing life expectancy and the higher ratio of
people surviving birth trauma, traumatic brain injury, infections of the brain, and stroke,
which often lead to epilepsy [
8
,
9
]. Thus, it is crucial to diagnose epilepsy correctly and to
provide the correct treatment to patients. The problem of detecting epileptic seizures by
EEG can be resolved by deep analysis of EEG epileptic signals investigating non-linear and
linear features through analysing their features using innovative classification techniques
to obtain an efficient detection rate [
10
–
14
]. In this paper, we develop an expert model to
analyse epileptic EEG signals and obtain an excellent recognition rate.
Diagnostics 2022, 12, 74. https://doi.org/10.3390/diagnostics12010074 https://www.mdpi.com/journal/diagnostics
