International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 18, No. 4, 8 Aug. 2026
Cover page and Table of Contents: PDF (size: 2411KB)
Implementing a Novel Framework for Focal and Generalized Epilepsy Classification using Adaptive VAE with Dense Bi-GRU through Multimodal Data-guided Feature Fusion
PDF (2411KB), PP.183-204
Views: 0 Downloads: 0
Author(s)
Maneesh Kumar
1,*
Rakesh Kumar
1
Santosh Kumar
2
Index Terms
Focal and Generalized Epilepsy Classification, Short-Time Fourier Transform, Multilevel Spatio Temporal Attention Fusion Network, Adaptive Variational autoencoders with Dense Bidirectional Gated Recurrent Unit, Fitness-based Football Optimization Algorithm
Abstract
One of the neurological conditions that affects the emotional and psychological condition of individuals is known as Epilepsy. Managing this disorder is very challenging as the focal seizures begin in specific brain regions and evolve into generalized forms. The fundamental method for seizure identification is the analysis of the ElectroEncephaloGram (EEG), yet its manual interpretation is prone to error. In addition, the process of automated seizure detection using EEG data suffers from variations between subjects and datasets distribution as they might result in inconsistencies. Moreover, the unequal proportion of seizure to non-seizure samples increases the detection challenge. Hence, developing classification approaches capable of distinguishing and predicting the focal and generalized seizures is important for effective treatment planning. Therefore, an efficient deep learning-based focal and generalized epilepsy classification is designed in this research by considering the multimodal data. Initially, essential signals used for the validation are sourced from publically available EEG datasets and they are converted into Short-Time Fourier Transform (STFT) images, which are considered as the feature set 1. Next, the Sensor data used for the validation are gathered from Kaggle (https://www.kaggle.com/datasets/datasetengineer/epilepsy-dataset) and it is considered as feature set 2. Next, the acquired two set of features are offered to the Multilevel Spatio Temporal Attention Fusion Network (MSTAFN) to execute the feature fusion process. Once the feature fusion procedure is completed, and then the fused features are given as the input to the focal and generalized epilepsy classification phase. In this phase, Adaptive Variational autoencoders with Dense Bidirectional Gated Recurrent Unit (AVDBiGRU) are employed to perform the classification process. Moreover, the focal and generalized epilepsy classification process is improved by optimizing the hyper parameters of AVDBiGRU through Fitness-based Football Optimization Algorithm (FFbOA). Finally, the focal and generalized epilepsy classified outcome is obtained from AVDBiGRU. Further, various experiments are carried out in the developed focal and generalized epilepsy classification model over the widely adopted deep learning architectures like LSTM, DCNN, InceptionV3 and BiGRU to verify their efficiency over different classes. The proposed model is evaluated on an EEG dataset containing the high-frequency oscillation (HFO) annotations from 30 pediatric patients with epilepsy and model performance is assessed by using the standard evaluation metrics that includes accuracy, sensitivity, specificity, and F1-score. The proposed model achieved 95.54% accuracy, 96.66 % specificity, 93.32% F1-score and 88.53 AUC.
Cite This Paper
Maneesh Kumar, Rakesh Kumar, Santosh Kumar, "Implementing a Novel Framework for Focal and Generalized Epilepsy Classification using Adaptive VAE with Dense Bi-GRU through Multimodal Data-guided Feature Fusion", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.4, pp.183-204, 2026. DOI:10.5815/ijisa.2026.04.10
Reference
[1]Najafi, T., Jaafar, R., Remli, R. and Wan Zaidi, W.A., "A classification model of EEG signals based on RNN-LSTM for diagnosing focal and generalized epilepsy", Sensors, vol.22, no.7269, 2022.
[2]Fan, D., Qi, L., Hou, S., Wang, Q. and Baier, G., "The seizure classification of focal epilepsy based on the network motif analysis", Brain Research Bulletin, vol.207, no.110879, 2024.
[3]Gill, T.S., Zaidi, S.S.H. and Shirazi, M.A., "Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures", Epilepsy & Behavior, vol.155, no.109732, 2024.
[4]Narin, A., "Detection of focal and non-focal epileptic seizure using continuous wavelet transform-based scalogram images and pre-trained deep neural networks", Irbm, vol.43, pp.22-31, 2022.
[5]Mahmoud O. Mokhiamar, Abdelrahman Mahmoud, Mohamed I. Eldagla, Yassine Aribi, and Ahmed M. Anter, "Blockchain-integrated multi-modal LSTM-CNN fusion for high-precision epileptic seizure detection from EEG signals," Knowledge-Based Systems, Vol. 323, pp. 113703, 19 July 2025.
[6]Tingxuan Hong, Desheng Li, Yuan Chang, Xiangqing Wang, Ziliang Cai, Rongfei Wang, Xiaochen Zhang, Xiaoya Liu, Chunxiao Yang, Shengyuan Yu, Shuang Liu, and Dong Ming, "MCAN: Cross-domain self-supervised attention network based on multiscale EEG feature learning for epileptic seizure detection," Knowledge-Based Systems, Vol. 327, pp. 114199, 9 October 2025.
[7]Qi Li, Wei Cao and Anyuan Zhang, "Multi-stream feature fusion of vision transformer and CNN for precise epileptic seizure detection from EEG signals," Journal of Translational Medicine, Vol. 23, no. 871, 2025.
[8]Xingyu Yi, "Energy-efficient EEG-based epileptic seizure detection: A deep learning-based spiking neural network approach," Procedia Computer Science, Vol. 266, pp. 908-915, 2025.
[9]Mehdi Hosseinzadeh; Parisa Khoshvaght; Samira Sadeghi, Parvaneh Asghari; Amirhossein Noroozi Varzeghani; Mokhtar Mohammadi, "A Model for Epileptic Seizure Diagnosis Using the Combination of Ensemble Learning and Deep Learning," IEEE Access, vol. 12, pp. 137132-137143, 2024.
[10]Christopher Lucasius; Vasily Grigorovsky; Hiroki Nariai; Aristea S. Galanopoulou; Jonathan Gursky; Solomon L. Moshé, "Biomimetic Deep Learning Networks With Applications to Epileptic Spasms and Seizure Prediction," IEEE Transactions on Biomedical Engineering, vol. 71, no. 3, pp. 1056-1067, March 2024.
[11]M. J. Rivera, J. Sanchis, O. Corcho, M. A. Teruel and J. Trujillo, "Evaluating CNN Methods for Epileptic Seizure Type Classification Using EEG Data," IEEE Access, vol. 12, pp. 75483-75495, 2024.
[12]V. V. Narayana and P. Kodali, "Hybrid LPF-LSTM Model for Enhanced Epileptic Seizure Detection in EEG Signals," IEEE Sensors Letters, vol. 9, no. 5, pp. 1-4, May 2025.
[13]Kiran Kumar Patro; Allam Jaya Prakash; Jaya Prakash Sahoo; Sidheswar Routray; Abdullah Baihan; Nagwan Abdel Samee, "SMARTSeiz: Deep Learning With Attention Mechanism for Accurate Seizure Recognition in IoT Healthcare Devices," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 7, pp. 3810-3818, July 2024.
[14]Y. Du, Y. Ren, N. Wong and E. C. H. Ngai, "Hyperdimensional Computing With Multiscale Local Binary Patterns for Scalp EEG-Based Epileptic Seizure Detection," IEEE Internet of Things Journal, vol. 11, no. 15, pp. 26046-26061, 1 Aug.1, 2024.
[15]T. Premavathi, M. Shukla and R. Jadeja, "Predicting Patient-Specific Epileptic Seizures From Scalp EEG Signals Using KNN Model With Transfer Learning," IEEE Access, vol. 12, pp. 196728-196739, 2024.
[16]A. D. Brabandere, C. Chatzichristos, W. Van Paesschen, M. De Vos and J. Davis, "Detecting Epileptic Seizures Using Hand-Crafted and Automatically Constructed EEG Features," IEEE Transactions on Biomedical Engineering, vol. 71, no. 1, pp. 318-325, Jan. 2024.
[17]K. Kamakshi and A. Rengaraj, "Early Detection of Stress and Anxiety Based Seizures in Position Data Augmented EEG Signal Using Hybrid Deep Learning Algorithms," IEEE Access, vol. 12, pp. 35351-35365, 2024.
[18]Y. Ma, J. Wang, J. Wang, W. Kang and X. Yang, "SyncLearnNet: Generalized Epileptic Seizure Detection Network Based on Brain Signals," IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 9, pp. 6565-6575, Sept. 2025.
[19]B. C. Sahoo, S. Mishra, S. K. Satapathy and S. Kumar, "Robust Seizure Prediction Model Using EEG Signal for Temporal Lobe Epilepsy Leveraging Deep Learning and Continual Learning," IEEE Access, vol. 13, pp. 138083-138094, 2025.
[20]S. Baghersalimi, T. Teijeiro, A. Aminifar and D. Atienza, "Decentralized Federated Learning for Epileptic Seizures Detection in Low-Power Wearable Systems," IEEE Transactions on Mobile Computing, vol. 23, no. 5, pp. 6392-6407, May 2024.
[21] Murariu, M.G., Dorobanțu, F.R. and Tărniceriu, D., "Enhanced Classification of Focal and Generalized Epilepsy Using EEMD and CEEMDAN Methods", Traitement du Signal, vol.41, no.1315, 2024.
[22]G. Amrani, A. Adadi and M. Berrada, "An Attention Mechanism-Based Interpretable Model for Epileptic Seizure Detection and Localization With Self-Supervised Pre-Training," IEEE Access, vol. 13, pp. 60213-60232, 2025.
[23]J. Xu, S. Yuan, J. Shang, J. Wang, K. Yan and Y. Yang, "Spatiotemporal Network Based on GCN and BiGRU for Seizure Detection," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 4, pp. 2037-2046, April 2024.
[24]P. Zhu, W. Zhou, C. Cao, G. Liu, Z. Liu and W. Shang, "A Novel SE-TCN-BiGRU Hybrid Network for Automatic Seizure Detection," IEEE Access, vol. 12, pp. 127328-127340, 2024.
[25]Bokyung Kim; Qijia Huang; Brady Taylor; Qilin Zheng; Jonathan Ku; Yiran Chen, "MulPi: A Multi-class and Patient-Independent Epileptic Seizure Classifier With Co-Designed Input-stationary Computing-in-SRAM," IEEE Transactions on Biomedical Circuits and Systems, vol. 19, no. 4, pp. 756-766, Aug. 2025.
[26]El-Sayed M. El-Kenawy, Faris H. Rizk, Ahmed Mohamed Zaki, Mahmoud Elshabrawy Mohamed, Abdelhameed Ibrahim, Abdelaziz A. Abdelhamid, Nima Khodadadi, Ehab M.Almetwally, and Marwa M. Eid, "Football Optimization Algorithm (FbOA): A Novel Metaheuristic Inspired by Team Strategy Dynamics," Journal of Artificial Intelligence and Metaheuristics (JAIM), Vol. 08, No. 01, PP. 21-38, 2024.
[27]Alomari, Saleh, Khalid Kaabneh, Ibraheem AbuFalahah, Saikat Gochhait, Irina Leonova, Zeinab Montazeri, and Mohammad Dehghani, "Carpet Weaver Optimization: A Novel Simple and Effective Human-Inspired Metaheuristic Algorithm," International Journal of Intelligent Engineering & Systems, vol. 17, no. 4, 2024.
[28]Dongyang Li, Shiyu Du, Yiming Zhang, and Meiting Zhao, "Dark Forest Algorithm: A Novel Metaheuristic Algorithm for Global Optimization Problems," Computers, Materials & Continua, vol. 75, no. 2, 2023.
[29]Liu, Jian, Rong Wang, Yonghong Deng, Xiaona Huang, and Zhibin Li, "Sharpbelly Fish Optimization Algorithm: A Bio-Inspired Metaheuristic for Complex Engineering," Biomimetics, vol. 10, no. 7, pp.445, 2025.
[30]Yun, Da Yo, and Hyo Seon Park, "Noise‐robust structural response estimation method using short‐time Fourier transform and long short‐term memory," Computer‐Aided Civil and Infrastructure Engineering, vol. 40, no. 7, pp859-878, 2025.
[31]Han, Zhu, Ce Zhang, Lianru Gao, Zhiqiang Zeng, Bing Zhang, and Peter M. Atkinson, "Spatio-temporal multi-level attention crop mapping method using time-series SAR imagery," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 206, pp.293-310, 2023.
[32]Isinkaye, Folasade Olubusola, Michael Olusoji Olusanya, and Ayobami Andronicus Akinyelu, "A multi-class hybrid variational autoencoder and vision transformer model for enhanced plant disease identification," Intelligent Systems with Applications, vol. 26, pp.200490, 2025.
[33]Mekruksavanich, Sakorn, and Anuchit Jitpattanakul, "Effective detection of epileptic seizures through EEG signals using deep learning approaches," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp.1937-1952, 2023.