Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks
Abstract
Detecting an epileptic seizure with the help of electroencephalogram (EEG) signals is difficult due to the absence of classified data or complexity. The conventional GAN-based data augmentation methods suffer from instability and inadequate learning of dependencies, which limits their efficiency despite increasing the diversity of data. An LSTM method is proposed for binary seizure classification with the WGAN-GP-LSTM scheme to overcome the previous issues. The generator and the discriminator of the system proposed in this paper use LSTM units, which differentiate it from other previously proposed systems. The system can produce acceptable EEG signals. This also helps in the correlations being learned over time for seizure classification. Through this system, EEG datasets that contain signals with and without supplements are publicly available. Results indicate that using synthetic data augmentation will enhance the WGAN-GP-LSTM model’s performance. Consequently, this model outperforms WGAN-GP and other prior works on the overall score, which are 0.96, 0.875, 0.82, and 0.923, respectively, for overall accuracy, sensitivity, specificity, and F1 score. WGAN-GP, with an FID score of 3.07 is poorer than WGAN-GP with a score of 1.42. The WGAN-GP-LSTM model displaces adversarial sequence generation and classification, helping to overcome challenges of data scarcity and the temporal dependence of EEG signals for seizure detection. A different approach to computer -assistance in neurodiagnostics has been introduced.
Cite this article
P., Hema, and Vanithamani R.. "Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks." Journal of Innovative Image Processing 8, no. 1 (2026): 354-371. doi: 10.36548/jiip.2026.1.019
Copy Citation
P., H., & R., V. (2026). Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks. Journal of Innovative Image Processing, 8(1), 354-371. https://doi.org/10.36548/jiip.2026.1.019
Copy Citation
P., Hema, et al. "Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks." Journal of Innovative Image Processing, vol. 8, no. 1, 2026, pp. 354-371. DOI: 10.36548/jiip.2026.1.019.
Copy Citation
P. H, R. V. Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks. Journal of Innovative Image Processing. 2026;8(1):354-371. doi: 10.36548/jiip.2026.1.019
Copy Citation
H. P., and V. R., "Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks," Journal of Innovative Image Processing, vol. 8, no. 1, pp. 354-371, Mar. 2026, doi: 10.36548/jiip.2026.1.019.
Copy Citation
P., H. and R., V. (2026) 'Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks', Journal of Innovative Image Processing, vol. 8, no. 1, pp. 354-371. Available at: https://doi.org/10.36548/jiip.2026.1.019.
Copy Citation
@article{p.2026,
author = {Hema P. and Vanithamani R.},
title = {{Adversarial Temporal Modeling for Seizure Classification Using WGAN-GP-LSTM Networks}},
journal = {Journal of Innovative Image Processing},
volume = {8},
number = {1},
pages = {354-371},
year = {2026},
publisher = {IRO Journals},
doi = {10.36548/jiip.2026.1.019},
url = {https://doi.org/10.36548/jiip.2026.1.019}
}
Copy Citation
Keywords
Electroencephalography
Epileptic Seizure Detection
Generative Adversarial Networks
Long Short-Term Memory Networks
Deep Learning
References
- Hasan, Nowshad, Md Maskat Sharif, Miskatur Rahman, Md Saiful Islam, Md Tohedur Rahaman Khan, MD Jiabul Hoque, and Anamul Bahar. "Epileptic Seizure Prediction Using a Deep Hybrid CNN-GAN Model on EEG Data." In 2024 IEEE 3rd International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON), IEEE, 2024, 270-275.
- Pascual, Damian, Amir Aminifar, David Atienza, Philippe Ryvlin, and Roger Wattenhofer. "Synthetic Epileptic Brain Activities Using Generative Adversarial Networks." arXiv preprint arXiv:1907.10518 (2019).
- Yu, Tian, Boyuan Cui, Yaqian Xu, and Xilin Liu. "Refine EEG Spectrogram Synthesized by Generative Adversarial Network for Improving the Prediction of Epileptic Seizures." In 2023 11th International IEEE/EMBS Conference on Neural Engineering (NER), IEEE, 2023, 1-4.
- Goodfellow, Ian J., Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. "Generative Adversarial Nets." Advances in neural information processing systems 27 (2014).
- AlAmir, Manal, and Manal AlGhamdi. "The Role of Generative Adversarial Network in Medical Image Analysis: An In-Depth Survey." ACM Computing Surveys 55, no. 5 (2022): 1-36.
- Abou-Abbas, Lina, Khadidja Henni, Imene Jemal, and Neila Mezghani. "Generative AI with WGAN-GP for Boosting Seizure Detection Accuracy." Frontiers in Artificial Intelligence 7 (2024): 1437315.
- P., Indurani & Sundaram, Veni. (2023). Improving Deep Learning for Seizure Detection using GAN with Cramer Distance and a Temporal-Spatial-Frequency Loss Function. International Journal on Recent and Innovation Trends in Computing and Communication. 11. 424-432. 10.17762/ijritcc.v11i6s.6949.
- Öcal, Abdurrahman, and Lale Özbakır. "Supervised Deep Convolutional Generative Adversarial Networks." Neurocomputing 449 (2021): 389-398.
- Radford, Alec, Luke Metz, and Soumith Chintala. "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks." arXiv preprint arXiv:1511.06434 (2015).
- Heusel, Martin, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. "Gans Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium." Advances in neural information processing systems 30 (2017).
- Maind, Sonali B., and Priyanka Wankar. "Research Paper on Basic of Artificial Neural Network." International Journal on Recent and Innovation Trends in Computing and Communication 2, no. 1 (2014): 96-100.
- Goodfellow, Ian. "Nips 2016 Tutorial: Generative Adversarial Networks." arXiv preprint arXiv:1701.00160 (2016).
- Kazeminia, Salome, Christoph Baur, Arjan Kuijper, Bram Van Ginneken, Nassir Navab, Shadi Albarqouni, and Anirban Mukhopadhyay. "GANs for Medical Image Analysis." Artificial intelligence in medicine 109 (2020): 101938.
- Salimans, Tim, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. "Improved Techniques for Training Gans." Advances in neural information processing systems 29 (2016).
- Gulrajani, Ishaan, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C. Courville. "Improved Training of Wasserstein Gans." Advances in neural information processing systems 30 (2017).
- Hochreiter, Sepp, and Jürgen Schmidhuber. "Long Short-Term Memory." Neural computation 9, no. 8 (1997): 1735-1780.
- Qu, Hao, and Jean Gotman. "A Patient-Specific Algorithm for the Detection of Seizure Onset in Long-Term EEG Monitoring: possible use as a warning device." IEEE transactions on biomedical engineering 44, no. 2 (1997): 115-122.
- J. Guttag, “CHB-MIT Scalp EEG Database,” Physionet.org, Jun. 09, 2010. http://www.physionet.org/physiobank/database/chbmit (accessed Dec. 10, 2024).
- Abou-Abbas, Lina, Khadidja Henni, Imene Jemal, and Neila Mezghani. "Generative AI with WGAN-GP for Boosting Seizure Detection Accuracy." Frontiers in Artificial Intelligence 7 (2024): 1437315.
- Elmawazini, Noura, Megan Boucher-Routhier, Gatete Queen Olea Umulinga, and Jean-Philippe Thivierge. "A Generative Adversarial Network for Data Augmentation of Ictal Waves from Multi-Electrode Brain Activity." In 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS), IEEE, 2025, 1715-1721.
- Geng, David, Ayham Alkhachroum, Manuel A. Melo Bicchi, Jonathan R. Jagid, Iahn Cajigas, and Zhe Sage Chen. "Deep Learning for Robust Detection of Interictal Epileptiform Discharges." Journal of neural engineering 18, no. 5 (2021): 056015.
