Ensemble Learning with Hybrid Linear Predictive Coding and Discrete Wavelet Transform Features for Enhanced Epileptic Seizure Detection

Öz

Automated detection of epileptic seizures from electroencephalogram signals plays a critical role in clinical decision support and continuous patient monitoring. In this study, a novel hybrid feature extraction method is proposed, combining Linear Predictive Coding coefficients and statistical descriptors from Discrete Wavelet Transform sub-bands to enhance the representational capacity of EEG signals. Unlike conventional approaches that rely solely on spectral, time-domain, or entropy-based features, this method captures both temporal dynamics and localized frequency characteristics of the signal. The system was developed and evaluated using the publicly available Bonn EEG dataset, which includes both healthy and epileptic recordings in controlled conditions. Each 4096-sample EEG segment was split into two equal parts to increase data volume, resulting in 1000 segments for analysis. Feature vectors were classified using an ensemble model based on majority voting across four classifiers: Random Forest, Support Vector Machine, Multilayer Perceptron and k-Nearest Neighbors. Performance was assessed across 16 binary and multi-class classification tasks using accuracy and Matthews Correlation Coefficient as evaluation metrics. The proposed hybrid approach consistently outperformed individual feature types in all tasks, achieving up to 100% accuracy and perfect Matthews Correlation Coefficient in seizure vs. non-seizure classifications. These findings highlight the effectiveness of integrating Linear Predictive Coding and Discrete Wavelet Transform features in a lightweight and interpretable ensemble architecture, offering a promising solution for accurate and scalable seizure detection in clinical and portable settings.Automated detection of epileptic seizures from electroencephalogram signals plays a critical role in clinical decision support and continuous patient monitoring. In this study, a novel hybrid feature extraction method is proposed, combining Linear Predictive Coding coefficients and statistical descriptors from Discrete Wavelet Transform sub-bands to enhance the representational capacity of EEG signals. Unlike conventional approaches that rely solely on spectral, time-domain, or entropy-based features, this method captures both temporal dynamics and localized frequency characteristics of the signal. The system was developed and evaluated using the publicly available Bonn EEG dataset, which includes both healthy and epileptic recordings in controlled conditions. Each 4096-sample EEG segment was split into two equal parts to increase data volume, resulting in 1000 segments for analysis. Feature vectors were classified using an ensemble model based on majority voting across four classifiers: Random Forest, Support Vector Machine, Multilayer Perceptron and k-Nearest Neighbors. Performance was assessed across 16 binary and multi-class classification tasks using accuracy and Matthews Correlation Coefficient as evaluation metrics. The proposed hybrid approach consistently outperformed individual feature types in all tasks, achieving up to 100% accuracy and perfect Matthews Correlation Coefficient in seizure vs. non-seizure classifications. These findings highlight the effectiveness of integrating Linear Predictive Coding and Discrete Wavelet Transform features in a lightweight and interpretable ensemble architecture, offering a promising solution for accurate and scalable seizure detection in clinical and portable settings.

Anahtar Kelimeler

• Epileptic seizure detection
• EEG signal analysis
• Hybrid feature extraction
• Ensemble learning
• Discrete wavelet transform
• Linear predictive coding

Gelişmiş Epileptik Nöbet Tespiti için Hibrit Doğrusal Öngörümleme Kodlama ve Ayrık Dalgacık Dönüşümü Öznitelikleriyle Topluluk Öğrenmesi

Öz

Epileptik nöbetlerin EEG sinyallerinden otomatik olarak tespit edilmesi, klinik karar desteği ve sürekli hasta takibi açısından kritik bir rol oynamaktadır. Bu çalışmada, EEG sinyallerinin temsil gücünü artırmak amacıyla, Doğrusal Öngörümleme Kodlama katsayıları ile Ayrık Dalgacık Dönüşümü alt bantlarından elde edilen istatistiksel tanımlayıcıları birleştiren yeni bir hibrit öznitelik çıkarım yöntemi önerilmiştir. Geleneksel yaklaşımların yalnızca spektral, zaman domeni veya entropi tabanlı özniteliklere dayanmasının aksine, bu yöntem hem zamansal dinamikleri hem de sinyalin yerel frekans özelliklerini yakalamaktadır. Sistem hem sağlıklı hem de epileptik kayıtları içeren ve kontrollü koşullarda elde edilmiş herkese açık Bonn EEG veri seti kullanılarak geliştirilmiş ve değerlendirilmiştir. Her biri 4096 örnekten oluşan EEG sinyalleri, veri hacmini artırmak amacıyla iki eşit parçaya bölünmüş ve analiz için toplam 1000 segmente ulaşılmıştır. Öznitelik vektörleri, Rastgele Orman, Destek Vektör Makinesi, Çok Katmanlı Algılayıcı ve k-En Yakın Komşu olmak üzere dört sınıflandırıcıdan oluşan ve çoğunluk oylamasına dayanan bir topluluk modeli ile sınıflandırılmıştır. Performans değerlendirmesi, doğruluk ve Matthews Korelasyon Katsayısı ölçütleri kullanılarak 16 adet ikili ve çok sınıflı sınıflandırma görevinde gerçekleştirilmiştir. Önerilen hibrit yaklaşım, tüm görevlerde bireysel öznitelik türlerine göre tutarlı şekilde üstün performans göstermiş; nöbet ve nöbet dışı sınıflandırmalarında %100’e kadar doğruluk ve kusursuz Matthews Korelasyon Katsayısı elde etmiştir. Bu bulgular, Doğrusal Öngörümleme Kodlama ve Ayrık Dalgacık Dönüşümü özniteliklerinin yükte hafif ve yorumlanabilir bir topluluk mimarisi içinde entegrasyonunun etkinliğini ortaya koymakta; klinik ve taşınabilir uygulamalarda doğru ve ölçeklenebilir nöbet tespiti için umut verici bir çözüm sunmaktadır.

Anahtar Kelimeler

• Epileptik nöbet tespiti
• EEG sinyal analizi
• Hibrit öznitelik çıkarımı
• Topluluk öğrenmesi
• Ayrık dalgacık dönüşümü
• Doğrusal öngörümleme kodlama

Kaynakça

1. [1] World Health Organization (WHO). Accessed 20.01.2025, https://www.who.int/news-room/fact-sheets/detail/epilepsy.
2. [2] Milligan TA. Epilepsy: a clinical overview. The American Journal of Medicine. 2021; 134(7): 840–847. doi: 10.1016/j.amjmed.2021.01.038
3. [3] Farooq MS, Zulfiqar A, Riaz S. Epileptic seizure detection using machine learning: Taxonomy, opportunities, and challenges. Diagnostics. 2023; 13(6): 1058. doi: 10.3390/diagnostics13061058
4. [4] Thijs RD, Surges R, O'Brien TJ, Sander JW. Epilepsy in adults. The Lancet. 2019; 393(10172): 689–701. doi:10.1016/S0140-6736(18)32596-0
5. [5] Supriya S, Siuly S, Wang H, Zhang Y. Epilepsy detection from EEG using complex network techniques: A review. IEEE Reviews in Biomedical Engineering. 2021; 16: 292–306. doi:10.1109/RBME.2021.3055956.
6. [6] Miltiadous A, Tzimourta KD, Giannakeas N, Tsipouras MG, Glavas E, Kalafatakis K, Tzallas AT. Machine learning algorithms for epilepsy detection based on published EEG databases: A systematic review. IEEE Access. 2022; 11: 564–594. doi:10.1109/ACCESS.2022.3232563
7. [7] Zeng J, Tan XD, Chang'an AZ. Automatic detection of epileptic seizure events using the time-frequency features and machine learning. Biomedical Signal Processing and Control. 2021; 69: 102916. doi:10.1016/j.bspc.2021.102916
8. [8] Zhang X, Yan C. An extraction and classification based on EMD and LSSVM of epileptic EEG. Biomedical Engineering: Applications, Basis and Communications. 2022; 34(05): 2250034. doi:10.4015/S101623722250034X

9. [9] Thangarajoo RG, Reaz MBI, Srivastava G, Haque F, Ali SHM, Bakar AAA, Bhuiyan MAS. Machine learning-based epileptic seizure detection methods using wavelet and EMD-based decomposition techniques: A review. Sensors. 2021; 21(24): 8485. doi:10.3390/s21248485
10. [10] Acharya UR, Shoeibi A, Khodatars M, Ghassemi N, Jafari M, Moridian P, Alizadehsani R, et al. Epileptic seizures detection using deep learning techniques: a review. International Journal of Environmental Research and Public Health. 2021; 18(11): 5780. doi:10.3390/ijerph18115780
11. [11] Handa P, Mathur M, Goel N. EEG datasets in machine learning applications of epilepsy diagnosis and seizure detection. SN Computer Science. 2023; 4(5): 437. doi:10.1007/s42979-023-01958-z
12. [12] Subasi A, Subasi TN, Ozaltin O. Artificial intelligence in diagnosis of neural disorders using biosignals and imaging. In: Advances in Artificial Intelligence. 2024; 523–560. doi:10.1016/B978-0-443-19073-5.00014-8
13. [13] Wang X, Gong G, Li N, Qiu S. Detection analysis of epileptic EEG using a novel random forest model combined with grid search optimization. Frontiers in Human Neuroscience. 2019; 13: 52. doi:10.3389/fnhum.2019.00052
14. [14] Shen M, Wen P, Song B, Li Y. An EEG based real-time epilepsy seizure detection approach using discrete wavelet transform and machine learning methods. Biomedical Signal Processing and Control. 2022; 77: 103820. doi:10.1016/j.bspc.2022.103820
15. [15] Tajmirriahi M, Rabbani H. A review of EEG-based localization of epileptic seizure foci: common points with multimodal fusion of brain data. Journal of Medical Signals & Sensors. 2024; 14(7): 19. doi:10.4103/jmss.jmss_11_24
16. [16] Atlam HF, Aderibigbe GE, Nadeem MS. Effective epileptic seizure detection with hybrid feature selection and SMOTE-based data balancing using SVM classifier. Applied Sciences. 2025; 15(9): 4690. doi:10.3390/app15094690
17. [17] Pan Y, Zhou X, Dong F, Wu J, Xu Y, Zheng S. Epileptic seizure detection with hybrid time-frequency EEG input: A deep learning approach. Computational and Mathematical Methods in Medicine. 2022; 2022: 8724536. doi:10.1155/2022/8724536
18. [18] Andrzejak RG, Lehnertz K, Mormann F, Rieke C, David P, Elger CE. Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E. 2001; 64(6): 061907. doi:10.1103/PhysRevE.64.061907
19. [19] Anjum MF, Dasgupta S, Mudumbai R, Singh A, Cavanagh JF, Narayanan NS. Linear predictive coding distinguishes spectral EEG features of Parkinson's disease. Parkinsonism & Related Disorders. 2020; 79: 79–85. doi:10.1016/j.parkreldis.2020.08.001
20. [20] Spratling MW. A review of predictive coding algorithms. Brain and Cognition. 2017; 112: 92–97. doi:10.1016/j.bandc.2015.11.003
21. [21] Khandekar D, Patil SP. Prediction of epileptic seizure from EEG signal by DWT and ANN technique – a review. Journal of Electronic Engineering & Communication Engineering. 2024; 12(3): 37–42
22. [22] Rabby MKM, Islam AK, Belkasim S, Bikdash MU. Wavelet transform-based feature extraction approach for epileptic seizure classification. In: Proceedings of the 2021 ACM Southeast Conference. 2021: 164–169. doi:10.1145/3409334.3452078
23. [23] Kunekar P, Kumawat C, Lande V, Lokhande S, Mandhana R, Kshirsagar M. Comparison of different machine learning algorithms to classify epilepsy seizure from EEG signals. Engineering Proceedings. 2024; 59(1): 166. doi:10.3390/engproc2023059166
24. [24] Jana R, Mukherjee I. Patient-specific and patient-independent seizure prediction using ensemble learning technique. In: International Conference on Data Science and Network Engineering. 2024: 41–52. doi:10.1007/978-981-97-8336-6_4
25. [25] Naidu G, Zuva T, Sibanda EM. A review of evaluation metrics in machine learning algorithms. In: Computer Science Online Conference. 2023: 15–25. doi:10.1007/978-3-031-35314-7_2
26. [26] Ikizler N, Ekim G. Investigating the effects of Gaussian noise on epileptic seizure detection: The role of spectral flatness, bandwidth, and entropy. Engineering Science and Technology, an International Journal. 2025; 64: 102005. doi:10.1016/j.jestch.2025.102005