10.57647/mjee.2026.2002.14

Interpretable Epileptic Seizure Detection Using Entropy and Gram Matrix Features in Beta–Gamma Bands

PDF
  • Shiva Rasaei Salari1,
  • Hamed Erfankhah*1,
  1. Department of Electrical and Biomedical Engineering, Ur.C., Islamic Azad University, Urmia, Iran

Received: 2025-07-30

Revised: 2025-09-06

Accepted: 2025-12-20

Published in Issue 2026-06-30

Published Online: 2026-04-21

Copyright (c) 2026 Shiva Rasaei Salari, Hamed Erfankhah (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Rasaei Salari, S., & Erfankhah, H. (2026). Interpretable Epileptic Seizure Detection Using Entropy and Gram Matrix Features in Beta–Gamma Bands. Majlesi Journal of Electrical Engineering, 20(2 (June 2026). https://doi.org/10.57647/mjee.2026.2002.14
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 48

Abstract

Epileptic seizure detection using EEG is vital for clinical diagnosis. This paper proposes a novel, interpretable framework for automated seizure classification based on entropy features from Beta (12–30 Hz) and Gamma (30–60 Hz) bands. The Discrete Legendre Transform (DLT) decomposes EEG signals, enabling extraction of four entropy measures: Approximate, Permutation, Sample, and Fuzzy Entropy. To capture inter-feature dependencies, Gram Matrix modeling is applied, yielding four global descriptors (trace, Frobenius norm, max eigenvalue, determinant), fused into a 12-dimensional feature vector. Evaluated with SVM and ProCRC classifiers on two datasets, Bonn (interictal D vs. ictal E) and independent Hauz Khas (HK, interictal vs. ictal), the method achieves 100% accuracy on Bonn and 97.5% on HK under 60–40 stratified split, and 99.5% (Bonn) and 97% (HK) under 10-fold cross-validation. Performance surpasses multiple state-of-the-art methods, including deep and hybrid models, while remaining fully interpretable, lightweight, and free of deep learning, image conversion, or GPU dependency. The framework’s transparency, computational frugality, and cross-dataset robustness make it highly suitable for portable, real-world clinical deployment in resource-limited settings. This work confirms that high diagnostic accuracy and interpretability are not mutually exclusive in seizure detection.

Keywords

  • Epileptic seizure detection,
  • Electroencephalographic signal analysis,
  • Gamma and Beta band entropy,
  • Gram matrix modeling,
  • Probabilistic collaborative representation
PDF

References

  1. Khaksar M, Golrou A, and Rahati-Ghuchani S. “Automatic recognition of sleep spindles based on two-stage classifier with artificial neural net-works and support vector machines.” Majlesi Journal of Electrical Engineering 2009; 2:83–90. doi: 10.1234/mjee.v2i1.45.
  2. Vaezi M and Nasri M. “Sleep stage classification using Laplacian score feature selection method by single channel EEG.” Majlesi Journal of Electrical Engineering 2020; 14. doi: 10.29252/mjee. 14.4.11
  3. Tobieha A, Behzadfar N, Yousefi MR, Mahdavi-Nasab H, and Shahgholian G. “Analysis of the changes in the distinguishing features in v signal processing for heroin addicts.” Majlesi Journal of Electrical Engineering 2025; 19:1–13. doi: 10.57647/j.mjee.2025.1901.14
  4. Mabrouk M. “Non-invasive EEG-based BCI system for left or right hand movement.” Majlesi Journal of Electrical Engineering 2024; 18. Available from: https://oiccpress.com/mjee/article/ view/5180
  5. Wirrell E, Tinuper P, Perucca E, and Moshe´ SL. “Introduction to the epilepsy syndrome papers.” Epilepsy Research 2022 :1330–1332. doi: 10.1111/epi.17262
  6. Baumgartner C, Baumgartner J, Lang C, Lisy T, and Koren JP. “Seizure detection devices.” Journal of Clinical Medicine 2025; 14:863. doi: 10.3390/ jcm14030863
  7. Rasoulzadeh V, Erkus E, Yogurt T, Ulusoy I, and Zergerog˘lu SA. “A comparative stationarity anal-ysis of eeg signals.” Annals of Operations Research 2017; 258:133–157. doi: 10.1007/s10479-016-2187-3
  8. Baghaie-Anaraki P, Yazdchi M, and Karimian A. “EEG pattern recognition to diagnose epilepsy using wavelet and chaos transformations.” Majlesi Journal of Electrical Engineering 2008; 2:51–59. doi: 10.1234/mjee.v2i1.41.
  9. Kannathal N, Choo ML, Acharya UR, and Sadasivan P. “Entropies for detection of epilepsy in EEG.” Computer Methods and Programs in Biomedicine 2005; 80:187–194. doi: 10.1016/j. cmpb.2005.06.012
  10. Zhang Y, Wang L, and Chen H. “A low-complexity seizure detection algorithm for ultra-low power wearable devices. ” IEEE Transactions on Biomedical Circuits and Systems 2023; 17:230–239. doi: 10.1109/ACCESS.2023.3235913
  11. Nanthini BS and Santhi B. “Electroencephalogram signal classification for automated epileptic seizure detection using genetic algorithm.” Journal of Natural Science, Biology, and Medicine 2017; 8:159. doi: 10.4103/jnsbm.jnsbm28516
  12. S¸ engu¨ r A, Guo Y, and Akbulut Y. “Time–frequency texture descriptors of EEG signals for efficient detection of epileptic seizure.” Brain Informatics 2016; 3:101–108. doi: 10.1007/s40708-015-0029-8
  13. Sairamya N, George ST, Ponraj DN, and Subathra M. “Automated detection of epileptic seizure using histogram of oriented gradients for analysing time frequency images of eeg signals.” Smart and Innovative Trends in Next Generation Computing Technologies: Third International Conference, NGCT, Dehradun, India 2018; Springer:932–943. doi: 10.1007/978-981-10-8660-171.
  14. Yusaf M, Nawaz R, and Iqbal J. “Robust seizure detection in EEG using 2D DWT of time-frequency distributions.” Electronics Letters 2016; 52:902–903. doi: 10.1049/el.2016.0630
  15. Mutersbaugh J, Lam V, Linguraur MG, and An-war SM. “Epileptic seizure classification using multidimensional EEG spectrograms.” 19th International Symposium on Medical Information Processing and Analysis (SIPAIM) 2023 :1–4. doi: 10.1109/SIPAIM56729.2023.10373429.
  16. Zeng W, Shan L, Su B, and Du S. “Epileptic seizure detection with deep EEG features by convolutional neural network and shallow classifiers.” Frontiers in Neuroscience 2023; 17:1145526. doi: 10.3389/fnins.2023.1145526
  17. Xin Q, Hu S, Liu S, Zhao L, and Zhang YD. “An attention-based wavelet convolution neural network for epilepsy EEG classification.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 2022; 30:957–966. doi: 10.1109/ TNSRE.2022.3166181
  18. Boran E, Sarnthein J, Krayenbu¨ hl N, Ramantani G, and Fedele T. “High-frequency oscillations in scalp EEG mirror seizure frequency in pediatric focal epilepsy.” Scientific Reports 2019; 9:16560. doi: 10.1038/s41598-019-52700-w
  19. Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, and Elger CE. “Indications of nonlinear deterministic and finite-dimensional v in time series of brain electrical v: Dependence on recording region and brain state.” Physical Review E 2001; 64:061907. doi: 10.1103/PhysRevE.64.061907
  20. Sharma R, Gupta PK, and Verma MK. “EEG Epilepsy datasets.” ResearchGate 2016. doi: 10. 13140/RG.2.2.14280.32006
  21. Nkengfack LCD, Tchiotsop D, Atangana R, Louis-Door V, and Wolf D. “EEG signals analysis for epileptic seizures detection using polynomial transforms, linear discriminant analysis and support vector machines. ” Biomedical Signal Processing and Control 2020; 62:102141. doi: 10.1016/j.bspc.2020.102141
  22. Pincus SM. “Approximate entropy as a measure of system complexity.” Proceedings of the National Academy of Sciences 1991; 88:2297–301. doi: 10.1073/pnas.88.6.2297
  23. Bandt C and Pompe B. “Permutation entropy: a natural complexity measure for time series.” Physical Review E 2002; 66:025701. doi: 10.1103/ PhysRevLett.88.174102
  24. Richman JS and Moorman JR. “Sample entropy. ” American Journal of Physiology-Heart and Circulatory Physiology 2004; 286:H2503–H2508. doi: 10.1016/S0076-6879(04)84011-4
  25. Al-Sharhan S, Karray F, Gueaieb W, and Basir O. “Fuzzy entropy: a brief survey.” 10th IEEE International Conference on Fuzzy Systems 2001; 3:1135–9. doi: 10.1109/FUZZ.2001.1008855
  26. Gatys LA, Ecker AS, and Bethge M. “A neural algorithm of artistic style.” 2015; arXiv preprint arXiv:1508.06576. doi: 10.48550/arXiv.1508.06576
  27. Hearst MA, Dumais ST, Osuna E, Platt J, and Scho¨lkopf B. “Support vector machines.” IEEE Intell. Syst. 1998; 13:18–28. doi: 10.1109/5254.708428
  28. Chang CC and Lin CJ. “Libsvm: A library for support vector machines.” ACM Transactions on Intelligent Systems and Technology 2011; 2:1–39. doi: 10.1145/1961189.1961199
  29. Cai S, Zhang L, Zuo W, and Feng X. “A probabilistic collaborative representation-based approach for pattern classification.” IEEE Conference on Computer Vision and Pattern Recognition 2016:2950–2959. doi: 10.1109%2FCVPR.2016.322.
  30. Alzamili SL, Baawi SS, Kadhim MN, Al-Shammary D, and Ibaida A. “Efficient feature selection based on ruzicka similarity for eeg diagnosis. ” International Journal of Information Technology
  31. Aayesha, Qureshi MB, Afzaal M, Qureshi MS, and Fayaz M. “Machine learning-based EEG signals classification model for epileptic seizure detection.” Multimedia Tools and Applications 2021; 80:849–77. doi: 10.1007/s11042-021-10597-6
  32. Kunekar P, Gupta MK, and Gaur P. “Detection of epileptic seizure in eeg signals using machine learning and deep learning techniques.” Journal of Engineering and Applied Science 2024; 71:21. doi: 10.1186/s44147-023-00353-y
  33. Malekzadeh A, Zare A, Yaghoobi M, Kobravi HR, and Alizadehsani R. “Epileptic seizures detection in EEG signals using fusion handcrafted and deep learning features.” Sensors 2021; 21:7710. doi: 10.3390/s21227710
  34. Malekzadeh A, Zare A, Yaghoobi M, and Alizadehsani R. “Automatic diagnosis of epileptic seizures in EEG signals using fractal dimension features and convolutional autoencoder method.” Big Data and Cognitive Computing 2021; 5:78
  35. Wang L, Xue W, Li Y, Luo M, Huang J, Cui W, and Huang C. “Automatic epileptic seizure detection in EEG signals using multi-domain feature extraction and nonlinear analysis.” Entropy 2017; 19:222. doi: 10.3390/e19060222
  36. Hassan AR, Subasi A, and Zhang Y. “Epilepsy seizure detection using complete ensemble empirical mode decomposition with adaptive noise. ” Knowledge-Based Systems 2020; 191:105333. doi: 10.1016/j.knosys.2019.105333
  37. Molla MKI, Hassan KM, Islam MR, and Tanaka T. “Graph eigen decomposition-based feature-selection method for epileptic seizure detection using electroencephalography.” Sensors 2020; 20:4639. doi: 10.3390/s20164639
  38. Wang B, Xu Y, Peng S, Wang H, and Li F. “Detection method of epileptic seizures using a neural network model based on multimodal dual-stream networks.” Sensors 2024; 24:3360. doi: 10.3390/s24113360
  39. Panda S, Das A, Mishra S, and Mohanty MN. “Epileptic seizure detection using deep v network with empirical wavelet transform.” Measurement Science Review 2021; 21:110–116. doi: 10.2478/msr-2021-0016
  40. Dash DP, Kolekar MH, and Jha K. “Surface EEG based epileptic seizure detection using wavelet based features and dynamic mode decomposition power along with KNN classifier.” Multimedia Tools and Applications 2022; 81:42057–42077. doi: 10.1007/s11042-021-11487-7
  41. Sheng G, Hu X, Wu H, Zhu J, and Shi P. “Deep knowledge-driven TSK fuzzy classifier for EEG-based epilepsy diagnosis.” J. Mech. Med. Biol. 2025; 25:2540072. doi: 10 . 1142 / S021951942540072X
  42. Gupta A, Singh P, and Karlekar M. “A novel signal modeling approach for classification of seizure and seizure-free EEG signals.” IEEE Transactions on Neural Systems and Rehabilitation Engineering 2018; 26:925–935. doi: 10.1109/ TNSRE.2018.2818123
  43. Jebaraj GS and Elango K. “EEG seizure classification with temporal spiking neural networks and mutual information-based feature selection.” Journal of Engineering and Applied Science 2025; 72:218. doi: 10.1186/s44147-025-00796-5