Detecting Epileptic Seizures from EEG Signals Using Machine Learning Techniques: A KNN andSVM Comparative Study
Keywords:
EEG, Epilepsy, Support Vector Machine SVM, Power Spectral Density, Seizure Detection, K Nearest NeighborsAbstract
Automated detection of epileptic seizures from electroencephalogram (EEG) recordings remains a clinically important but technically challenging problem. In this paper, we present and comparatively evaluate a machine-learning pipeline for seizure detection based on the CHB-MIT Scalp EEG Database, combining Butterworth band-pass filtering, Power Spectral Density (PSD) feature extraction via Welch’s method, and classification with k-Nearest Neighbors (KNN) and Support Vector Machines (SVM). On subsets of the CHB-MIT database ranging from one healthy and one epileptic subject up to twelve of each, KNN achieved a classification accuracy of 99.3%, while SVM achieved 98.47%, with both classifiers exceeding 98% accuracy at the largest tested sample size. A direct comparison between the two methods reveals that KNN marginally outperforms SVM under the evaluated conditions, while both demonstrate competitive and robust performance. These results corroborate prior evidence that lightweight, interpretable classifiers can achieve strong performance on scalp EEG seizure detection when paired with well-chosen spectral features, and provide a structured basis for selecting between KNN and SVM in clinical or embedded EEG applications.
References
[1] “EEG (electroencephalogram),” Mayo Clinic. [Online]. Available: https://www.mayoclinic.org/tests-procedures/eeg/about/pac-20393875. [Accessed: 14-Jan-2026].
[2] Y. Holler, E. Trinka, and J. Jacobs, “Epilepsy grand challenge 2025,” ¨ Frontiers in Neurology, vol. 16, Sep. 2025, Art. no. 1693132. doi: 10.3389/fneur.2025.1693132
[3] U. R. Acharya, S. L. Oh, Y. Hagiwara, J. H. Tan, and H. Adeli, “Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals,” Comput. Biol. Med., vol. 100, pp. 270– 278, Sep. 2018, doi: 10.1016/j.compbiomed.2017.09.017.
[4] S. Saminu, G. Xu, S. Zhang, I. Ab El Kader, H. A. Aliyu, A. H. Jabire, Y. K. Ahmed, and M. J. Adamu, “Applications of Artificial
Intelligence in Automatic Detection of Epileptic Seizures Using EEG Signals: A Review,” Artif. Intell. Appl., vol. 1, no. 1, pp. 11–25, 2023, doi: 10.47852/bonviewAIA2202297.
[5] A. Miltiadous, K. D. Tzimourta, N. Giannakeas, M. G. Tsipouras, E. Glavas, K. Kalafatakis, and A. T. Tzallas, “Machine Learning Algorithms for Epilepsy Detection Based on Published EEG Databases: A Systematic Review,” IEEE Access, vol. 11, pp. 564– 594, 2023, doi: 10.1109/ACCESS.2022.3232563. [Online]. Available: https://ieeexplore.ieee.org/document/9999444/.
[6] A. Naser, M. Tantawi, H. Shedeed, and M. F. Tolba, “Detecting Epileptic Seizures Using Abe Entropy, Line Length and SVM Classifier,” in Proc. Int. Conf. Advanced Machine Learning Technologies and Applications (AMLTA 2019), Adv. Intell. Syst. Comput., vol. 921, Cham: Springer, 2020, pp. 169–178, doi: 10.1007/978-3-030-141189 17.
[7] U. Hazarika, B. B. Borah, S. Roy, and M. J. Saikia, “Automated Detection of Aberrant Episodes in Epileptic Conditions: Leveraging EEG and Machine Learning Algorithms,” Bioengineering, vol. 12, no. 4, p. 355, Mar. 2025, doi: 10.3390/bioengineering12040355. [Online]. Available: https://www.mdpi.com/2306-5354/12/4/355.
[8] H. G. Alfughi, A. H. Maamar, and A. N. Mohammed, “Utilizing EEG Signals for Epilepsy Seizure Detection,” in Proc. 2024 IEEE 4th Int.
Maghreb Meeting of the Conf. Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), Tripoli, Libya, 2024, pp. 619–624, doi: 10.1109/MI-STA61267.2024.10599692.
[9] L. Bai, G. Litscher, and X. Li, “Epileptic Seizure Detection Using Machine Learning: A Systematic Review and Meta-Analysis,” Brain Sci., vol. 15, no. 6, p. 634, Jun. 2025, doi: 10.3390/brainsci15060634. [Online]. Available: https://www.mdpi.com/2076-3425/15/6/634.
[10] M. A. Alsuwaiket, “Feature Extraction of EEG Signals for Seizure Detection Using Machine Learning Algorithms,” Eng. Technol.
Appl. Sci. Res., vol. 12, no. 5, pp. 9247–9251, Oct. 2022, doi:
10.48084/etasr.5208.
[11] S. Liu, J. Wang, S. Li, and L. Cai, “Epileptic Seizure Detection and Prediction in EEGs Using Power Spectra Density Parameterization,” IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 3884–3894, 2023, doi: 10.1109/TNSRE.2023.3317093.
[12] “CHB-MIT Scalp EEG Database v1.0.0.” PhysioNet. [Online]. Available: https://physionet.org/content/chbmit/1.0.0/. [Accessed: 17-Dec2025].
[13] S. Mazurek, R. Blanco, J. Falco-Roget, J. K. Argasi´ nski, and A.´ Crimi, “Impact of the Pre-processing and Balancing of EEG Data on the Performance of Graph Neural Network for Epileptic Seizure Classification,” in Artificial Intelligence and Soft Computing, Lect. Notes Comput. Sci., vol. 14125, Cham: Springer Nature Switzerland, 2023, pp. 258–268, doi: 10.1007/978-3-031-42508-0 24.
[14] C. Mahjoub, R. Le Bouquin Jeannes, T. Lajnef, and A. Kachouri,` “Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods,” Biomed. Tech. (Berl.), vol. 65, no. 1, pp. 33–50, Jan. 2020, doi: 10.1515/bmt-20190001. [Online]. Available: https://pubmed.ncbi.nlm.nih.gov/31469648/.
[15] T. Z. Chin, A. Saidatul, and Z. Ibrahim, “Exploring EEG based Authentication for Imaginary and Non-imaginary tasks using Power Spectral Density Method,” IOP Conf. Ser. Mater. Sci. Eng., vol. 557, no. 1, p. 012031, Jun. 2019, doi: 10.1088/1757-899X/557/1/012031.
[16] J. Brownlee, “A Gentle Introduction to k-fold CrossValidation,” MachineLearningMastery.com. [Online]. Available:
https://machinelearningmastery.com/k-fold-cross-validation/.
[Accessed: 27-Sep-2023].
[17] S. M. Malakouti, M. B. Menhaj, and A. A. Suratgar, “The usage of 10fold cross-validation and grid search to enhance ML methods performance in solar farm power generation prediction,” Cleaner Eng. Technol., vol. 15, p. 100664, Aug. 2023, doi: 10.1016/j.clet.2023.100664.
[18] M. M. Taye, “Understanding of Machine Learning with Deep Learning: Architectures, Workflow, Applications and Future Directions,” Computers, vol. 12, no. 5, p. 91, 2023, doi: 10.3390/computers12050091. [Online]. Available: https://www.mdpi.com/2073-431X/12/5/91.
[19] A. Bablani, D. R. Edla, and S. Dodia, “Classification of EEG Data using k-Nearest Neighbor approach for Concealed Information Test,” Procedia Comput. Sci., vol. 143, pp. 242–249, Jan. 2018, doi: 10.1016/j.procs.2018.10.392.
[20] K. Taunk, S. De, S. Verma, and A. Swetapadma, “A Brief Review of Nearest Neighbor Algorithm for Learning and Classification,” in Proc. 2019 Int. Conf. Intelligent Computing and Control Systems (ICCS), Madurai, India, 2019, pp. 1255–1260, doi: 10.1109/ICCS45141.2019.9065747.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Electrical and Electronic Engineering and Information Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
