Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data

Hümeyra Beylan; Mehmet Recep Bozkurt

doi:10.35377/saucis...1869600

Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data

Abstract

Epilepsy is a chronic neurological disorder characterized by recurrent and unpredictable seizures, which can result in significant impairment in quality of life and may cause sudden death, particularly in patients with drug-resistant epilepsy. Consequently, the early and reliable detection of epileptic seizures is critically important for ensuring patient safety and enabling timely clinical intervention. In this study, machine learning-based methods for epileptic seizure detection using data acquired from wearable devices are comparatively evaluated. The Open Seizure Database (OSDB) was utilized to extract time-domain and frequency-domain features from raw accelerometer signals. Recursive Feature Elimination (RFE), Principal Component Analysis (PCA), and Mutual Information (MI) techniques were employed for feature selection. For the classification task, Multilayer Perceptron (MLP) and Random Forest (RF) models were implemented. Model performance was assessed using accuracy, precision, recall, and F1-score metrics, with particular emphasis placed on recall for the seizure class due to its clinical relevance. The experimental results demonstrate that the Random Forest model achieves the highest generalization performance, attaining a recall of 85\% for the seizure class on the validation dataset. Moreover, SHAP-based explainability analysis demonstrates that high-frequency energy components and statistical measures reflecting signal variability are the most influential features in the decision-making process. Overall, the results suggest that explainable machine learning approaches based on wearable sensor data offer effective and clinically interpretable solutions for epileptic seizure detection.

Keywords

Ethical Statement

This study uses publicly available open-access data from the Open Seizure Database (OSDB). No direct human or animal intervention was involved; therefore, ethical committee approval was not required. All procedures were conducted in accordance with relevant scientific and ethical standards.

References

World Health Organization (WHO), “Epilepsy”, World Health Organization, Feb. 07, 2024. Available: https://www.who.int/news-room/fact-sheets/detail/epilepsy [Accessed: Dec. 26, 2025].
Stafstrom, Carl E. and Lionel Carmant, “Seizures and epilepsy: An overview for neuroscientists”, Cold Spring Harb Perspect Biol., vol. 7, no. 5, pp. 1–19, 2015, doi: 10.1101/cshperspect.a022426.
Goldenberg, Marvin M., “Overview of drugs used for epilepsy and seizures: etiology, diagnosis and treatment”, P T., 2010 Jul;35(7):392–415. PMID: 20689626; PMCID: PMC2912003.
Hasija, Tanuj et al., “Improving wearable-based seizure prediction by feature fusion using an explainable growing network”, Artificial Intelligence in Medicine, vol. 169, Nov. 2025, doi: 10.1016/j.artmed.2025.103228.
Çağlıyan, Beyda, and Utku Köse, “Epilepsi EEG Verilerinin Makine Öğrenmesi Teknikleriyle Sınıflandırılması”, European Journal of Science and Technology, Jan. 2021, pp. 163–172, doi: 10.31590/ejosat.857507.
T. Musumeci, A. Bonaccorso, and G. Puglisi, “Epilepsy disease and nose-to-brain delivery of polymeric nanoparticles: An overview”, Mar. 01, 2019, MDPI AG, doi: 10.3390/pharmaceutics11030118.
E. Bergil, M. R. Bozkurt, and C. Oral, “An Evaluation of the Channel Effect on Detecting the Preictal Stage in Patients With Epilepsy”, Clinical EEG and Neuroscience, vol. 52, no. 5, pp. 376–385, 2021, doi: 10.1177/1550059420966436.
A. Shoeb and J. Guttag, “Application of machine learning to epileptic seizure detection”, Proceedings of the 27th International Conference on Machine Learning, pp. 975–982, 2010, doi: 10.5555/3104322.3104446.

Germino, J., Brinkmann, B., Chawla, N. V. et al., “Mixture of checkpoint experts for explainable seizure detection using wearable devices”, Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-27610-9.
Onorati, Francesco et al., “Prospective study of a multimodal convulsive seizure detection wearable system on pediatric and adult patients in the epilepsy monitoring unit”, Frontiers in Neurology, vol. 12, 724904, 18 Aug. 2021, doi: 10.3389/fneur.2021.724904.
Wu, Shasha, and Douglas R. Nordli, “Motor seizure semiology”, Handbook of Clinical Neurology, 2023;196:295–304. doi: 10.1016/B978-0-323-98817-9.00014-4. PMID: 37620075.
S. Kusmakar, C. K. Karmakar, B. Yan, T. J. O’Brien, R. Muthuganapathy, and M. Palaniswami, “Automated detection of convulsive seizures using a wearable accelerometer device”, IEEE Transactions on Biomedical Engineering, vol. 66, no. 2, pp. 421–432, Feb. 2019, doi: 10.1109/TBME.2018.2845865.
Bruno, Elisa et al., “Wearable technology in epilepsy: The views of patients, caregivers, and healthcare professionals”, Epilepsy and Behavior, vol. 85, pp. 141–149, Aug. 2018, doi: 10.1016/j.yebeh.2018.05.044.
G. Jones, “Open Seizure Database (OSDB) Licence”, OpenSeizureDetector, 2025. [Online]. Available: https://github.com/OpenSeizureDetector/OpenSeizureDatabase/blob/main/documentation/LICENCE.md [Accessed: Dec. 23, 2025].
I. Guyon and A. Elisseeff, “An introduction to variable and feature selection”, Journal of Machine Learning Research, vol. 3, pp. 1157–1182, Mar. 2003, doi: 10.5555/944919.944968.
U. R. Acharya, F. Molinari, S. V. Sree, S. Chattopadhyay, K. H. Ng, and J. S. Suri, “Automated diagnosis of epileptic EEG using entropies”, Biomed. Signal Process. Control, vol. 7, no. 4, pp. 401–408, 2012, doi: 10.1016/j.bspc.2011.07.007.
A. Subasi, “EEG signal classification using wavelet feature extraction and a mixture of expert model”, Expert Syst. Appl., vol. 32, no. 4, pp. 1084–1093, May 2007, doi: 10.1016/j.eswa.2006.02.005.
Huan Liu and Lei Yu, “Toward integrating feature selection algorithms for classification and clustering”, IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 4, pp. 491–502, Apr. 2005, doi: 10.1109/TKDE.2005.66.
A. Şenol, T. Talan, and C. Aktürk, “A new hybrid feature reduction method by using MCMSTClustering algorithm with various feature projection methods: a case study on sleep disorder diagnosis”, Signal Image Video Process., vol. 18, no. 5, pp. 4589–4603, Jul. 2024, doi: 10.1007/s11760-024-03097-1.
H. Abdi and L. J. Williams, “Principal component analysis”, WIREs Comp. Stat., vol. 2, no. 4, pp. 433–459, 2010, doi: 10.1002/wics.101.
I. Guyon, J. Weston, S. Barnhill, and V. Vapnik, “Gene selection for cancer classification using support vector machines”, Machine Learning, vol. 46, no. 1–3, pp. 389–422, 2002, https://doi.org/10.1023/A:1012487302797.
M. A. Sulaiman and J. Labadin, “Feature selection based on mutual information”, 2015 9th International Conference on IT in Asia (CITA), Sarawak, Malaysia, 2015, pp. 1–6, doi: 10.1109/CITA.2015.7349827.
L. Breiman, “Random forests”, Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001, https://doi.org/10.1023/A:1010933404324.
A. Chatur, M. Haghi, N. Ganapathy, N. Taherinejad, R. Seepold, and N. M. Madrid, “Advanced Classifiers and Feature Reduction for Accurate Insomnia Detection Using Multimodal Dataset”, IEEE Access, vol. 12, pp. 150664–150678, 2024, doi: 10.1109/ACCESS.2024.3456904.

Details

Primary Language

English

Subjects

Computing Applications in Health, Artificial Intelligence (Other)

Journal Section

Research Article

Authors

Hümeyra Beylan ^*
0009-0000-9885-1046
Türkiye

Mehmet Recep Bozkurt
0000-0003-0673-4454
Türkiye

Early Pub Date

June 23, 2026

Publication Date

June 30, 2026

Submission Date

January 22, 2026

Acceptance Date

February 26, 2026

Published in Issue

Year 2026 Volume: 9 Number: 3

DOI

https://doi.org/10.35377/saucis...1869600

IZ

https://izlik.org/JA64HX63CP

Cite

RIS / Bibtex

APA

Beylan, H., & Bozkurt, M. R. (2026). Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data. Sakarya University Journal of Computer and Information Sciences, 9(3), 840-845. https://doi.org/10.35377/saucis...1869600

AMA

1.Beylan H, Bozkurt MR. Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data. SAUCIS. 2026;9(3):840-845. doi:10.35377/saucis.1869600

Chicago

Beylan, Hümeyra, and Mehmet Recep Bozkurt. 2026. “Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data”. Sakarya University Journal of Computer and Information Sciences 9 (3): 840-45. https://doi.org/10.35377/saucis. 1869600.

EndNote

Beylan H, Bozkurt MR (June 1, 2026) Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data. Sakarya University Journal of Computer and Information Sciences 9 3 840–845.

IEEE

[1]H. Beylan and M. R. Bozkurt, “Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data”, SAUCIS, vol. 9, no. 3, pp. 840–845, June 2026, doi: 10.35377/saucis...1869600.

ISNAD

Beylan, Hümeyra - Bozkurt, Mehmet Recep. “Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data”. Sakarya University Journal of Computer and Information Sciences 9/3 (June 1, 2026): 840-845. https://doi.org/10.35377/saucis. 1869600.

JAMA

1.Beylan H, Bozkurt MR. Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data. SAUCIS. 2026;9:840–845.

MLA

Beylan, Hümeyra, and Mehmet Recep Bozkurt. “Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 3, June 2026, pp. 840-5, doi:10.35377/saucis. 1869600.

Vancouver

1.Hümeyra Beylan, Mehmet Recep Bozkurt. Analysis of Machine Learning Models for Epileptic Seizure Detection Using Wearable Sensor Data. SAUCIS. 2026 Jun. 1;9(3):840-5. doi:10.35377/saucis. 1869600