dubi̇ted Duzce University Journal of Science and Technology 2148-2446 Duzce University Supervised Learning Machine Learning Algorithms Classification Algorithms Denetimli Öğrenme Makine Öğrenmesi Algoritmaları Sınıflandırma algoritmaları Epileptik Nöbet Bölgesi Tespiti için Grid Arama Algoritması Kullanılarak Farklı Hibrit Öğrenme Algoritmalarının Değerlendirilmesi Evaluating Different Hybrid Learning Algorithms using Grid Search Algorithm for Epileptic Seizure Zone Detection https://orcid.org/0000-0003-1567-2216 Özer Ezgi PİRİ REİS ÜNİVERSİTESİ https://orcid.org/0009-0004-9616-3652 Kınataş Ahmet Furkan https://orcid.org/0009-0006-3802-1482 Yiğit Emine https://orcid.org/0009-0004-3222-6542 Demir Hamza https://orcid.org/0009-0003-0983-2532 Birinci Alper 04 19 2026 14 2 324 339 07 18 2025 01 02 2026 Copyright © 2013, Duzce University Journal of Science and Technology 2013 Duzce University Journal of Science and Technology

Bu makalede, epileptik nöbetlerin erken teşhisi için Elektroensefalogram (EEG) verilerini doğru bir şekilde sınıflandırmada etkili bir yöntem sunulmaktadır. Önerilen süreç esasen istatistiksel veriyi, ayrık dalgacık dönüşümlerini (DWT), makine öğrenmesi algoritmalarını ve özellik seçme tekniklerini bağımsız olarak hibritleştirilmiştir. DWT kullanımıyla, otomatik çok çözünürlüklü sinyal işleme yaklaşımı, doğru bir sınıflandırma performansını garantilemek için EEG sinyallerini değişen pencere boyutlarına sahip ayrıntılı parçalara böldükten sonra ayrıntı ve yaklaşıklık katsayılarına ayrıştırılmıştır. Sinyallerdeki doğrusal olmayan ve dinamik örüntüleri tanımlayan bu katsayılardan istatistiksel gizli özellikler çıkarılmıştır. Önemli unsurları vurgularken özellik matrisinin boyutunu azaltmak için özellik seçme teknikleri kullanılmıştır. Giriş matrislerini sınıflandırmak için farklı sınıflandırıcı yapıları geliştirilmiştir. Tüm sınıflandırıcılar için, ızgara arama teknikleri kullanılarak optimum hiperparametreler elde edilmiştir. Modelin performansını değerlendirmek için sınıflandırmaya ilişkin performans metrikleri hesaplanmıştır. Ayrıca, EEG sinyallerini ayırt etmek için en önemli frekans bantları tespit edilmiştir. Analizde, önerilen prosedürü epileptik davranışları doğru bir şekilde tespit etme açısından diğer yaklaşımlarla karşılaştırmak için Bonn Üniversitesi veri tabanından bir kıyaslama veri seti kullanılmıştır. Sonuçlar, önerilen yaklaşımın EEG sinyallerini sınıflandırmada performans metrikleri ve bilgi kriterleri açısından daha sağlam modeller tahmin edebileceğini göstermiştir.

In this paper, an effective method for accurately classifying Electroencephalogram (EEG) data for the early identification of epileptic seizures is presented. The suggested process essentially hybridizes several statistical data, discrete wavelet transformations (DWT), machine learning algorithms, and feature selection techniques independently. The automated multi-resolution signal processing approach decomposes EEG signals into detail and approximation coefficients after splitting them into detailed parts with varying window sizes using DWT. Statistical latent features are extracted from these coefficients that describe the nonlinear and dynamical patterns in the signals. Feature selection techniques were used to reduce the dimension of the feature matrix while highlighting the important elements. Different classifier structures were developed to classify input matrices. For all classifiers, the optimal hyperparameters were found using grid search techniques. Performance metrics for classification were calculated to assess the model's performance. Also, the most important frequency bands were detected to distinguish EEG signals. In the analysis, to compare the proposed procedure with the other approaches in terms of detecting the epileptic behaviors correctly, a benchmark data set from the University of Bonn database was used. The results showed that the proposed approach can estimate more robust models concerning performance metrics and information criteria in classifying EEG signals.

 Feature extraction Feature selection Grid search Machine learning Signal processing Özellik Çıkarımı Özellik Seçimi Izgara Arama Makine Öğrenmesi Sinyal İşleme This study was carried out within the scope of a project supported by the Scientific and Technological Research Council of Türkiye (TÜBİTAK) under the 2209-A Research Project Support Programme for Undergraduate Students (Project No: 1919B012303343). 1919B012303343 Acir, N., Oztura, I., Kuntalp, M., Baklan, B., & Guzelis, C. (2005). Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks. IEEE Transactions on Biomedical Engineering, 52(1), 30-40. https://doi.org/10.1109/TBME.2004.839630 Andonie, R. (2019). Hyperparameter optimization in learning systems. Journal of Membrane Computing, 1, 279-291. https://doi.org/10.1007/s41965-019-00023-0 Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., & Elger, C. E. (2001). Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity. Physical Review E, 64, Article 061907. https://doi.org/10.1103/PhysRevE.64.061907 Beghi, E. (2020). The epidemiology of epilepsy. Neuroepidemiology, 54(2), 185-191. https://doi.org/10.1159/000503831 Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16–28. https://doi.org/10.1016/j.compeleceng.2013.11.024 Chen, M., Guo, K., Lu, K., Meng, K., Lu, J., Pang, Y., Zhang, L., Hu, Y., Yu, R., & Zhang, R. (2025). Localizing the seizure onset zone and predicting the surgery outcomes in patients with drug-resistant epilepsy: A new approach based on the causal network. Computer Methods and Programs in Biomedicine, 258, Article 108483. https://doi.org/10.1016/j.cmpb.2024.108483 El-Manzalawy, Y., Hsieh, T. Y., Shivakumar, M., Kim, D., & Honavar, V. (2018). Min-redundancy and max-relevance multi-view feature selection for predicting ovarian cancer survival using multi-omics data. BMC Medical Genomics, 11, Article 71. https://doi.org/10.1186/s12920-018-0388-0 Guyon, I., Weston, J., Barnhill, S., & Vapnik, V. (2002). Gene selection using support vector machines. Machine Learning, 46(1-3), 389-422. https://doi.org/10.1023/A:1012487302797 Hall, M. A., & Smith, L. A. (1998). Practical feature subset selection for machine learning. In C. McDonald (Ed.), Computer Science ’98 Proceedings of the 21st Australasian Computer Science Conference (ACSC’98), Perth, 4–6 February 1998 (pp. 181–191). Springer. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735 Hyvärinen, A., & Oja, E. (2000). Independent component analysis: Algorithms and applications. Neural Networks, 13(4-5), 411–430. https://doi.org/10.1016/S0893-6080(00)00026-5 Jiang, L., He, J., Pan, H., Wu, D., Jiang, T., & Liu, J. (2023). Seizure detection algorithm based on improved functional brain network structure feature extraction. Biomedical Signal Processing and Control, 79(1), Article 104053. https://doi.org/10.1016/j.bspc.2022.104053 Kocadagli, O., Ozer, E., & Batista, A. G. (2023). Preictal phase detection on EEG signals using hybridized machine learning classifiers with a novel feature selection procedure based GAs and ICOMP. Expert Systems with Applications, 212(1), Article 118825. https://doi.org/10.1016/j.eswa.2022.118825 Makeig, S., Bell, A. J., Jung, T. P., & Sejnowski, T. J. (1996). Independent component analysis of electroencephalographic data. Advances in Neural Information Processing Systems, 8(8), 145-151. Mallat, S. G. (1989). A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7), 674-693. https://doi.org/10.1109/34.192463 Ogunsanya, M., Isichei, J., & Desai, S. (2023). Grid search tuning in additive manufacturing. Manufacturing Letters, 35, 1031-1042. https://doi.org/10.1016/j.mfglet.2023.08.056 Ozer, E. (2023). Early diagnosis of epileptic seizures over EEG signals using deep learning approach [Doctoral dissertation, Mimar Sinan Fine Arts University]. Ozer, E. (2024a). Detection of brain tumor using boosting algorithms based on feature selection. Researcher, 4(2), 130-140. Ozer, E. (2024b). Brain tumor detection using deep CNNs and ensemble algorithms over MRI images. Computer Science, 9(2), 142-150. https://doi.org/10.53070/bbd.1455902 Pandey, S. K., Janghel, R. R., Mishra, P. K., & Ahirwal, M. K. (2023). Automated epilepsy seizure detection from EEG signal based on hybrid CNN and LSTM model. Signal, Image and Video Processing, 17(4), 1113–1122. https://doi.org/10.1007/s11760-022-02318-9 Patnaik, L. M., & Manyam, O. K. (2008). Epileptic EEG detection using neural networks and post-classification. Computer Methods and Programs in Biomedicine, 91(2), 100-109. https://doi.org/10.1016/j.cmpb.2008.02.005 Senliol, B., Gulgezen, G., Yu, L., & Cataltepe, Z. (2008). Fast correlation-based filter (FCBF) with a different search strategy. In 23rd International Symposium on Computer and Information Sciences. 1-4, https://doi.org/10.1109/ISCIS.2008.4717949 Shen, M., Wen, P., Song, B., & Li, Y. (2022). An EEG-based real-time epilepsy seizure detection approach using discrete wavelet transform and machine learning methods. Biomedical Signal Processing and Control, 77, Article 103820. https://doi.org/10.1016/j.bspc.2022.103820 Shen, M., Wen, P., Song, B., & Li, Y. (2023). Real-time epilepsy seizure detection based on EEG using tunable-Q wavelet transform and convolutional neural network. Biomedical Signal Processing and Control, 82, Article 104566. https://doi.org/10.1016/j.bspc.2022.104566 Shen, M., Yang, F., Wen, P., Song, B., & Li, Y. (2024). A real-time epilepsy seizure detection approach based on EEG using short-time Fourier transform and GoogLeNet convolutional neural network. Heliyon, 10(11), Article e31656. https://doi.org/10.1016/j.heliyon.2024.e31827 Tsiouris, K. M., Pezoulas, V. C., Zervakis, M., Konitsiotis, S., Koutsouris, D. D., & Fotiadis, D. I. (2018). A long short-term memory deep learning network for seizure prediction using EEG signals. Computers in Biology and Medicine, 99, 24-37. https://doi.org/10.1016/j.compbiomed.2018.05.019 Ungureanu, M., Bigan, C., Strungaru, R., & Lazarescu, V. (2004). Independent component analysis applied in biomedical signal processing. Measurement Science Review, 4(2), 1-8. Wang, X., Gong, G., Li, N., & Qiu, S. (2019). Detection analysis of epileptic EEG using a novel random forest model combined with grid search optimization. Frontiers in Human Neuroscience, 13, Article 52. https://doi.org/10.3389/fnhum.2019.00052 World Health Organization. (2024). Epilepsy. https://www.who.int/news-room/fact-sheets/detail/epilepsy Xu, Y., Nguyen, D., Mohamed, A., Carcel, C., Li, Q., Kutlubaev, M. A., Anderson, C. S., & Hackett, M. L. (2016). Frequency of a false positive diagnosis of epilepsy: A systematic review of observational studies. Seizure, 41, 167-174. https://doi.org/10.1016/j.seizure.2016.08.005