Volume 17, Issue 2 (March & April- In press 2026)
BCN 2026, 17(2): 0-0 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Salehzehi S, Hosseini P, koohian Mohammad abadi A, Lashkari S, Kobravi H R, Mazrooei Rad E. Epileptic Seizure Detection using Convolutional Neural Network and Recurrence Plots of EEG Signals in Animal Models. BCN 2026; 17 (2)
URL: http://bcn.iums.ac.ir/article-1-3391-en.html
URL: http://bcn.iums.ac.ir/article-1-3391-en.html
Shahed Salehzehi1 
, Parisa Hosseini1 , Ali Koohian Mohammad abadi2 , Saleh Lashkari3 , Hamid Reza Kobravi4 , Elias Mazrooei Rad *5
, Parisa Hosseini1 , Ali Koohian Mohammad abadi2 , Saleh Lashkari3 , Hamid Reza Kobravi4 , Elias Mazrooei Rad *5
1- Department of Research Center of Biomedical Engineering, Ma.C. Islamic Azad University of Mashhad , Iran.
2- Department of Research Center of Biomedical Engineering, Ma.C. Islamic Azad University of Mashhad , Iran.
3- Department of Biomedical Engineering, Imam Reza International University , Mashhad, Iran.
4- Research Center of Biomedical Engineering, Ma.C. Islamic Azad University of Mashhad, Iran.
5- Department of Biomedical Engineering, Khavaran Institute of Higher Education, Mashhad, Iran.
2- Department of Research Center of Biomedical Engineering, Ma.C. Islamic Azad University of Mashhad , Iran.
3- Department of Biomedical Engineering, Imam Reza International University , Mashhad, Iran.
4- Research Center of Biomedical Engineering, Ma.C. Islamic Azad University of Mashhad, Iran.
5- Department of Biomedical Engineering, Khavaran Institute of Higher Education, Mashhad, Iran.
Abstract:
Epilepsy is a neurological disorder characterized by abnormal electrical activity in the brain that leads to recurrent seizures. Many aspects of the analysis of epileptic seizures are still at the pre-clinical animal study phase. Electroencephalogram (EEG) is widely used in epileptic seizures diagnosis, but visual inspection of EEG analysis is often difficult and time-consuming. Therefore, the use of signal processing approaches and feature extraction from EEG signals for automatic epilepsy diagnosis is of great importance. Among all signal processing approaches, deep learning approaches offer a promising way to effectively identify EEG signal features in order to minimize the detection error and accelerate signal processing. This study aims to propose a novel CNN-based model to diagnose epileptic events from recurrence plots (RPs) rodent models. First, RPs were extracted using optimized phase-space parameters. Then, a convolutional neural network (CNN) model was designed to detect eoileptic events. Accuracy, Precision, Recall, F1 Score and specificity were also used to evaluate model. The results showed that the proposed method achieved promising classification accuracy of 98.2% and Precision, Recall, and F1 score above 0.80 (80%), which was suitable for seizure detection. The findings of this study demonstrate the effectiveness of the proposed CNN-based model for diagnosing epileptic events from RPs. The model's promising performance suggests that it could significantly aid in the automated diagnosis of epilepsy in animal models. It has the potential to reduce the time and effort required for manual analysis while maintaining high accuracy in pre-clinical research.
Type of Study: Original |
Subject:
Cognitive Neuroscience
Received: 2025/10/28 | Accepted: 2026/04/22 | Published: 2026/05/9
Received: 2025/10/28 | Accepted: 2026/04/22 | Published: 2026/05/9
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
Copyright © The Author(s);
This is an open access article distributed under the terms of the Creative Commons Attribution License (CC-By-NC), which permits use, distribution, and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.
Contact Information
