ISSN 0869-6632 (Print)
ISSN 2542-1905 (Online)

For citation:

Nazarikov S. I. Mathematical model for epileptic seizures detection on an EEG recording. Izvestiya VUZ. Applied Nonlinear Dynamics, 2023, vol. 31, iss. 5, pp. 628-642. DOI: 10.18500/0869-6632-003065, EDN: ZMFWFL

This is an open access article distributed under the terms of Creative Commons Attribution 4.0 International License (CC-BY 4.0).
Full text PDF(Ru):
Full text PDF(En):
(downloads: 8)
Article type: 

Mathematical model for epileptic seizures detection on an EEG recording

Nazarikov Sergei Igorevich, Immanuel Kant Baltic Federal University

Purpose of this study — analysis of the possibility of using convolutional neural networks as a model for detecting epileptic seizures on real EEG data.

Methods. In this paper, wavelet analysis is used for time-frequency analysis. To localize epileptic discharges, the task of detecting them was reduced to the classification task and the ResNet18 architecture of neural network was used. Techniques were used to augment and balance the biomedical data dataset under consideration. Wavelet analysis is used for time-frequency analysis. To localize epileptic discharges, the problem of their detection was reduced to the classification task, and the ResNet18 neural network architecture was used. Techniques were used to augment and balance the considered biomedical dataset.

Results. Convolutional neural network can be successfully used to detect epileptic seizures, a method of postprocessing the results of primary detection is proposed to improve the quality of the model. It is shown that the developed model demonstrates high accuracy in comparison with other methods based on classical machine learning algorithms. The value of the F1-score metric reaches 0.44, which is a high value for classification of the real biological data.

Conclusion. The presented model based on a convolutional neural network for detecting epileptic seizures on an EEG recording can become the main one in medical decision support systems for epileptologist.

This work was supported by the Priority 2030 program of the Immanual Kant Baltic Federal University of the Ministry of Education and Science of the Russian Federation
  1. Megiddo I, Colson A, Chisholm D, Dua T, Nandi A, Laxminarayan R. Health and economic benefits of public financing of epilepsy treatment in India: An agent-based simulation model. Epilepsia. 2016;57(3):464–474. DOI: 10.1111/epi.13294.
  2. Sander JW. The use of antiepileptic drugs–principles and practice. Epilepsia. 2004;45(s6):28–34. DOI: 10.1111/j.0013-9580.2004.455005.x.
  3. Ghosh S, Sinha JK, Khan T, Devaraju KS, Singh P, Vaibhav K, Gaur P. Pharmacological and therapeutic approaches in the treatment of epilepsy. Biomedicines. 2021;9(5):470. DOI: 10.3390/ biomedicines9050470.
  4. Tatum WO, Mani J, Jin K, Halford JJ, Gloss D, Fahoum F, Maillard L, Mothersill I, Beniczky S. Minimum standards for inpatient long-term video-EEG monitoring: A clinical practice guideline of the international league against epilepsy and international federation of clinical neurophysiology. Clinical Neurophysiology. 2022;134:111–128. DOI: 10.1016/j.clinph.2021.07.016.
  5. Karpov OE, Hramov AE. Information Technology, Computing Systems and Artificial Intelligence in Medicine. Moscow: DPK Press; 2022. 480 p. (in Russian).
  6. Sutton RT, Pincock D, Baumgart DC, Sadowski DC, Fedorak RN, Kroeker KI. An overview of clinical decision support systems: benefits, risks, and strategies for success. npj Digital Medicine. 2020;3:17. DOI: 10.1038/s41746-020-0221-y.
  7. Roy Y, Banville H, Albuquerque I, Gramfort A, Falk TH, Faubert J. Deep learning-based electroencephalography analysis: a systematic review. Journal of Neural Engineering. 2019;16(5): 051001. DOI: 10.1088/1741-2552/ab260c.
  8. Chen Z, Lu G, Xie Z, Shang W. A unified framework and method for EEG-based early epileptic seizure detection and epilepsy diagnosis. IEEE Access. 2020;8:20080–20092. DOI: 10.1109/ ACCESS.2020.2969055.
  9. Mousavi SR, Niknazar M, Vahdat BV. Epileptic seizure detection using AR model on EEG signals. In: 2008 Cairo International Biomedical Engineering Conference. 18-20 December 2008, Cairo, Egypt. New York: IEEE; 2009. P. 1–4. DOI: 10.1109/CIBEC.2008.4786067.
  10. Wang D, Miao D, Xie C. Best basis-based wavelet packet entropy feature extraction and hierarchical EEG classification for epileptic detection. Expert Systems with Applications. 2011; 38(11):14314–14320. DOI: 10.1016/j.eswa.2011.05.096.
  11. Vanabelle P, Handschutter PD, Tahry RE, Benjelloun M, Boukhebouze M. Epileptic seizure detection using EEG signals and extreme gradient boosting. The Journal of Biomedical Research. 2020;34(3):228–239. DOI: 10.7555/JBR.33.20190016.
  12. Karpov OE, Khoymov MS, Maksimenko VA, Grubov VV, Utyashev N, Andrikov DA, Kurkin SA, Hramov AE. Evaluation of unsupervised anomaly detection techniques in labelling epileptic seizures on human EEG. Applied Sciences. 2023;13(9):5655. DOI: 10.3390/app13095655.
  13. Zhao W, Zhao W, Wang W, Jiang X, Zhang X, Peng Y, Zhang B, Zhang G. A novel deep neural network for robust detection of seizures using EEG signals. Computational and Mathematical Methods in Medicine. 2020;2020:9689821. DOI: 10.1155/2020/9689821.
  14. Asif U, Roy S, Tang J, Harrer S. SeizureNet: Multi-spectral deep feature learning for seizure type classification. In: Kia SM, Mohy-ud-Din H, Abdulkadir A, Bass C, Habes M, Rondina JM, Tax C, Wang H, Wolfers T, Rathore S, Ingalhalikar M, editors. Machine Learning in Clinical Neuroimaging and Radiogenomics in Neuro-oncology. MLCN RNO-AI 2020 2020. Vol. 12449 of Lecture Notes in Computer Science. Cham: Springer; 2020. P. 77–87. DOI: 10.1007/978-3-030- 66843-3_8.
  15. Andrzejak RG, Schindler K, Rummel C. Nonrandomness, nonlinear dependence, and nonstationarity of electroencephalographic recordings from epilepsy patients. Phys. Rev. E. 2012;86(4):046206. DOI: 10.1103/PhysRevE.86.046206.
  16. Shoeb AH. Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. PhD Thesis. Massachusetts: Massachusetts Institute of Technology; 2009. 162 p.
  17. Hwang S, Park S, Kim D, Lee J, Byun H. Mitigating inter-subject brain signal variability FOR EEG-based driver fatigue state classification. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 06-11 June 2021, Toronto, ON, Canada. New York: IEEE; 2021. P. 990–994. DOI: 10.1109/ICASSP39728.2021.9414613.
  18. Homan RW. The 10-20 electrode system and cerebral location. American Journal of EEG Technology. 1988;28(4):269–279. DOI: 10.1080/00029238.1988.11080272.
  19. Hramov AE, Koronovskii AA, Makarov VA, Maximenko VA, Pavlov AN, Sitnikova E. Wavelets in Neuroscience. Cham: Springer; 2021. 384 p. DOI: 10.1007/978-3-030-75992-6.
  20. Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems 25. NIPS; 2012. P. 1097–1105.
  21. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. 20-25 June 2009, Miami, FL, USA. New York: IEEE; 2009. P. 248–255. DOI: 10.1109/CVPR.2009.5206848.
  22. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 27-30 June 2016, Las Vegas, NV, USA. New York: IEEE; 2016. P. 770–778. DOI: 10.1109/CVPR.2016.90.
  23. Hendrycks D, Lee K, Mazeika M. Using pre-training can improve model robustness and uncertainty. In: Proceedings of the 36th International Conference on Machine Learning. Vol. 97. Long Beach, California. PMLR; 2019. P. 2712–2721.
  24. Zhang H, Cisse M, Dauphin YN, Lopez-Paz D. mixup: Beyond empirical risk minimization. In: 6th International Conference on Learning Representations. 30 Apr-3 May 2018, Vancouver, BC, Canada. ICLR (Poster); 2018. P. 1–13.
  25. Park DS, Chan W, Zhang Y, Chiu CC, Zoph B, Cubuk ED, Le QV. SpecAugment: A simple data augmentation method for automatic speech recognition. In: Proc. Interspeech 2019. 15-19 September 2019, Graz, Austria. Interspeech; 2019. P. 2613–2617. DOI: 10.21437/Interspeech.2019- 2680.
  26. Karpov OE, Afinogenov S, Grubov VV, Maksimenko V, Korchagin S, Utyashev N, Hramov AE. Detecting epileptic seizures using machine learning and interpretable features of human EEG. The European Physical Journal Special Topics. 2023;232(5):673–682. DOI: 10.1140/epjs/s11734-022- 00714-3.
  27. Karpov OE, Grubov VV, Maksimenko VA, Kurkin SA, Smirnov NM, Utyashev NP, Andrikov DA, Shusharina NN, Hramov AE. Extreme value theory inspires explainable machine learning approach for seizure detection. Scientific Reports. 2022;12(1):11474. DOI: 10.1038/s41598-022-15675-9.
  28. Cortes C, Vapnik V. Support-vector networks. Machine Learning. 1995;20(3):273–297. DOI: 10.1007/BF00994018.
  29. Hramov AE, Maksimenko VA, Pisarchik AN. Physical principles of brain–computer interfaces and their applications for rehabilitation, robotics and control of human brain states. Physics Reports. 2021;918:1–133. DOI: 10.1016/j.physrep.2021.03.002.
  30. Pisarchik AN, Maksimenko VA, Hramov AE. From novel technology to novel applications: Comment on “An integrated brain-machine interface platform with thousands of channels” by Elon Musk and Neuralink. Journal of Medical Internet Research. 2019;21(10):e16356. DOI: 10.2196/16356.
  31. Maksimenko VA, van Heukelum S, Makarov VV, Kelderhuis J, Luttjohann A, Koronovskii AA, Hramov AE, Luijtelaar G. Absence seizure control by a brain computer interface. Scientific Reports. 2017;7(1):2487. DOI: 10.1038/s41598-017-02626-y.
Available online: