TY  - JOUR
T1  - Epileptik Nöbetlerin Tespiti için Öznitelik Çıkartma ve Sınıflandırma Yöntemleri
TT  - Feature Extraction and Classification Methods for Epileptic Seizure Detection
AU  - İkizler, Nuri
AU  - Ekim, Güneş
PY  - 2025
DA  - August
Y2  - 2025
DO  - 10.35414/akufemubid.1574539
JF  - Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi
PB  - Afyon Kocatepe University
WT  - DergiPark
SN  - 2149-3367
SP  - 956
EP  - 968
VL  - 25
IS  - 4
LA  - tr
AB  - Bu çalışmada, Bonn Üniversitesi Epileptoloji Bölümü'nden alınan EEG veri seti kullanılarak, epileptik nöbet tespitine yönelik bir model sunulmuştur. Frekans analizinde daha hassas sonuçlar elde etmek için ikiye ayrılan sinyaller ile sınıflandırma algoritmalarının performansının artırılmasına katkı sağlanan çalışmada, her sınıf için oluşturulan referans sinyaller, sınıf içi tutarlılık ve anormal sinyallerin tespiti açısından önemli bir rol oynamıştır. Sinyallerin spektral özelliklerinin karşılaştırılmasının, sınıflar arasındaki farkların belirginleşmesine ve sınıflandırma performansının artmasına yardımcı olduğu modelde, özellik vektöründe spektral farklar, enerji, entropi ve frekans sapmaları gibi özellikler kullanılarak, özellikle Kullback-Leibler ayrışması ve Euclidean mesafesi gibi metrikler sayesinde sınıflar arası spektral farklılıkların tespit edilmesi sağlanmıştır. Sınıflandırma aşamasında kullanılan beş farklı sınıflandırma algoritması içinde k-EYK (k=1) ve LMA en yüksek performansı göstererek, on üç sınıflandırma görevi içerisinde yedi görevde epileptik nöbetlerin %100 doğrulukla tespit edilmesi sağlamıştır. Tüm sınıflandırma görevlerinde k-EYK ile LMA sınıflandırıcıları için bulunan ortalama %98,03 ve %98,23 doğruluk değerleri, modelin epileptik nöbet tespiti için çok başarılı ve güvenilir bir yöntem olduğunu göstermektedir.
KW  - Epileptik nöbet tespiti
KW  - EEG
KW  - Spektral analiz
KW  - Welch yöntemi
KW  - k-En yakın komşu
N2  - In this study, a model for detecting epileptic seizures is presented using the EEG dataset from the Epileptology Department of the University of Bonn. To obtain more precise results in frequency analysis, the signals are split into two parts, which contributed to improving the performance of the classification algorithms. The reference signals is obtained for each class played a significant role in assessing intra-class consistency and detecting abnormal signals. The comparison of spectral features among signals is helped to highlight differences between classes and enhance classification performance. In the feature vector, spectral differences, energy, entropy, and frequency deviations are employed, with metrics such as Kullback-Leibler divergence and Euclidean distance are used to detect spectral differences between classes. Among the five different classification algorithms used, k-NN (k=1) and LMT showed the highest performance, successfully detecting epileptic seizures with 100% accuracy in seven out of thirteen classification tasks. The average accuracy values of 98.03% for k-NN and 98.23% for LMT across all classification tasks demonstrate that the model is a highly effective and reliable method for detecting epileptic seizures.
CR  - Al-Hadeethi, H., Abdulla, S., Diykh, M., Deo, R.C. and Green, J.H., 2020. Adaptive boosts LS-SVM classification approach for time-series signal classification in epileptic seizure diagnosis applications. Expert Systems with Applications, 161, 113676.
https://doi.org/10.1016/j.eswa.2020.113676
CR  - Alkan, A. and Kiymik, M.K., 2006. Comparison of AR and Welch methods in epileptic seizure detection. Journal of Medical Systems, 30, 413-419.
https://doi.org/10.1007/s10916-005-9001-0
CR  - Alotaiby, T.N., Alshebeili, S.A., Abd El-Samie, F.E., Alabdulrazak, A. and Alkhnaian, E., 2016. Channel selection and seizure detection using a statistical approach. In 2016 5th international conference on electronic devices, systems and applications (ICEDSA). Ras Al Khaimah, United Arab Emirates, 1-4.
https://doi.org/10.1109/ICEDSA.2016.7818505
CR  - Basri, A. and Arif, M., 2021. Classification of seizure types using random forest classifier. Advances in Science and Technology Research Journal, 15(3), 167–178.
https://doi.org/10.12913/22998624/140542
CR  - Birjandtalab, J., Pouyan, M.B., Cogan, D., Nourani, M. and Harvey, J., 2017. Automated seizure detection using limited-channel EEG and non-linear dimension reduction. Computers in biology and medicine, 82, 49-58.
https://doi.org/10.1016/j.compbiomed.2017.01.011
CR  - Boubchir, L., Daachi, B. and Pangracious, V., 2017. A review of feature extraction for EEG epileptic seizure detection and classification. In 2017 40th International Conference on Telecommunications and Signal Processing (TSP). Barcelona, Spain, 456-460.
https://doi.org/10.1109/TSP.2017.8076027
CR  - Choubey, H. and Pandey, A., 2019. A new feature extraction and classification mechanisms For EEG signal processing. Multidimensional Systems and Signal Processing, 30, 1793-1809.
https://doi.org/10.1007/s11045-018-0628-7
CR  - Eltrass, A.S., Tayel, M.B. and EL-qady, A.F., 2021. Automatic epileptic seizure detection approach based on multi-stage Quantized Kernel Least Mean Square filters. Biomedical Signal Processing and Control, 70, 103031.
CR  - Gabr, R.H., Shahin, A.I., Sharawi, A.A. and Aouf, M., 2020. A deep learning identification system for different epileptic seizure disease stages. Journal of Engineering and Applied Science, 67(4), 925-944.
	
Gao, X., Yan, X., Gao, P., Gao, X. And Zhang, S., 2020. Automatic detection of epileptic seizure based on approximate entropy, recurrence quantification analysis and convolutional neural networks. Artificial intelligence in medicine, 102, 101711.
https://doi.org/10.1016/j.artmed.2019.101711
CR  - Harpale, V., and Bairagi, V., 2021. An adaptive method for feature selection and extraction for classification of epileptic EEG signal in significant states. Journal of King Saud University-Computer and Information Sciences, 33(6), 668-676.
https://doi.org/10.1016/j.jksuci.2018.04.014
CR  - Hasan, M.K., Ahamed, M.A., Ahmad, M. and Rashid, M.A., 2017. Prediction of epileptic seizure by Analysing time series EEG signal using k‐NN classifier. Applied bionics and biomechanics, 2017(1), 6848014.
https://doi.org/10.1155/2017/6848014
CR  - Jana, G.C., Praneeth, M.S. and Agrawal, A., 2023. A multi-view SVM approach for seizure detection from single channel EEG signals. IETE Journal of Research, 69(6), 3120-3131.
https://doi.org/10.1080/03772063.2021.1913074
CR  - Ji, S., Zhang, Z., Ying, S., Wang, L., Zhao, X. and Gao, Y., 2020. Kullback–Leibler divergence metric learning. IEEE transactions on cybernetics, 52(4), 2047-2058.
https://doi.org/10.1109/TCYB.2020.3008248
CR  - Jiang, Y., Chen, W. and You, Y., 2020. Scattering transform-based features for the automatic seizure detection. Biocybernetics and Biomedical Engineering, 40(1), 77-89.
https://doi.org/10.1016/j.bbe.2019.11.002
CR  - Juba, B. and Le, H.S., 2019. Precision-recall versus accuracy and the role of large data sets. In Proceedings of the AAAI conference on artificial intelligence. Honolulu, Hawaii, USA, 4039-4048.
https://doi.org/10.1609/aaai.v33i01.33014039
CR  - Kabir, E.S. and Zhang, Y., 2016. Epileptic seizure detection from EEG signals using logistic model trees. Brain informatics, 3, 93-100.
https://doi.org/10.1007/s40708-015-0030-2
CR  - Krislock, N. and Wolkowicz, H., 2012. Euclidean Distance Matrices and Applications. In Handbook on Semidefinite, Conic and Polynomial Optimization. International Series in Operations Research & Management Science, vol 166. Springer, New York, NY, 879-914.
https://doi.org/10.1007/978-1-4614-0769-0_30
CR  - Kumar, A. and Kolekar, M.H., 2014. Machine learning approach for epileptic seizure detection using wavelet analysis of EEG signals. In 2014 International Conference on Medical Imaging, m-Health and Emerging Communication Systems (MedCom), Greater Noida, India, 412-416.
https://doi.org/10.1109/MedCom.2014.7006043
CR  - Li, M., Sun, X., Chen, W., Jiang, Y. and Zhang, T., 2019. Classification epileptic seizures in EEG using time-frequency image and block texture features. IEEE Access, 8, 9770-9781.
https://doi.org/10.1109/ACCESS.2019.2960848
CR  - Liu, S., Wang, J., Li, S. and Cai, L., 2023. Epileptic seizure detection and prediction in EEGS using power spectra density parameterization. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31, 3884-3894.
https://doi.org/10.1109/TNSRE.2023.3317093
CR  - Mandhouj, B., Cherni, M.A. and Sayadi, M., 2021. An automated classification of EEG signals based on spectrogram and CNN for epilepsy diagnosis. Analog integrated circuits and signal processing, 108(1), 101-110.
https://doi.org/10.1007/s10470-021-01805-2
CR  - Menéndez, M.L., Pardo, J.A., Pardo, L. and Pardo, M.C., 1997. The jensen-shannon divergence. Journal of the Franklin Institute, 334(2), 307-318.
https://doi.org/10.1016/S0016-0032(96)00063-4
CR  - Milligan, T.A., 2021. Epilepsy: a clinical overview. The American Journal of Medicine, 134(7), 840-847.
https://doi.org/10.1016/j.amjmed.2021.01.038
CR  - Miltiadous, A., Tzimourta, K.D., Giannakeas, N., Tsipouras, M.G., Glavas, E., Kalafatakis, K. and Tzallas, A.T., 2022. Machine learning algorithms for epilepsy detection based on published EEG databases: A systematic review. IEEE Access, 11, 564-594.
https://doi.org/10.1109/ACCESS.2022.3232563
CR  - Mirzaei, A., Ayatollahi, A., Gifani, P. and Salehi, L., 2010. Spectral entropy for epileptic seizures detection. In 2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks. Liverpool, UK, 301-307.
https://doi.org/10.1109/CICSyN.2010.84
CR  - Niknazar, H., Mousavi, S.R., Niknazar, M., Mardanlou, V. and Coelho, B.N., 2020. Performance analysis of EEG seizure detection features. Epilepsy Research, 167, 106483.
https://doi.org/10.1016/j.eplepsyres.2020.106483
CR  - Nogay, H.S. and Adeli, H., 2021. Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning. European neurology, 83(6), 602-614.
https://doi.org/10.1159/000512985
CR  - Nwe, T.L., Hieu, N.T. and Limbu, D.K., 2013. Bhattacharyya distance based emotional dissimilarity measure for emotion classification. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, BC, Canada, 7512-7516.
https://doi.org/10.1109/ICASSP.2013.6639123
CR  - Pal, H. and Kumar, A., 2023. Stability analysis of multiscale bubble entropy and power metric-based seizure detection technique with MLA. IETE Journal of Research, 69(6), 3455-3466.
https://doi.org/10.1080/03772063.2021.1912650
CR  - Polat, K. and Nour, M., 2020. Epileptic seizure detection based on new hybrid models with electroencephalogram signals. IRBM, 41(6), 331-353.
https://doi.org/10.1016/j.irbm.2020.06.008
CR  - Paul, Y., 2018. Various epileptic seizure detection techniques using biomedical signals: a review. Brain informatics, 5, 1-19.
https://doi.org/10.1186/s40708-018-0084-z
CR  - Quintero-Rincón, A., d'Giano, C. and Batatia, H., 2020. A quadratic linear-parabolic model-based EEG classification to detect epileptic seizures. Journal of Biomedical Research, 34(3), 205.
https://doi.org/10.7555/JBR.33.20190012
CR  - Saini, J. and Dutta, M., 2018. Epilepsy classification using optimized artificial neural network. Neurological Research, 40(11), 982-994.
https://doi.org/10.1080/01616412.2018.1508544
CR  - Sharmila, A. and Mahalakshmi, P., 2017. Wavelet-based feature extraction for classification of epileptic seizure EEG signal. Journal of medical engineering & technology, 41(8), 670-680.
https://doi.org/10.1080/03091902.2017.1394388
CR  - Shiao, H.T., Cherkassky, V., Lee, J., Veber, B., Patterson, E. E., Brinkmann, B.H. and Worrell, G.A., 2016. SVM-based system for prediction of epileptic seizures from iEEG signal. IEEE Transactions on Biomedical Engineering, 64(5), 1011-1022.
https://doi.org/10.1109/TBME.2016.2586475
CR  - Siddiqui, M.K., Huang, X., Morales-Menendez, R., Hussain, N. and Khatoon, K., 2020. Machine learning based novel cost-sensitive seizure detection classifier for imbalanced EEG data sets. International Journal on Interactive Design and Manufacturing (IJIDeM), 1491-1509.
https://doi.org/10.1007/s12008-020-00715-3
CR  - Sriraam, N., Raghu, S., Tamanna, K., Narayan, L., Khanum, M., Hegde, A. S. and Kumar, A. B., 2018. Automated epileptic seizures detection using multi-features and multilayer perceptron neural network. Brain Informatics, 5(2), 10.
https://doi.org/10.1186/s40708-018-0088-8
CR  - Vidyaratne, L.S. and Iftekharuddin, K.M., 2017. Real-time epileptic seizure detection using EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11), 2146-2156.
https://doi.org/10.1109/TNSRE.2017.2697920
CR  - Wang, Z., Na, J. and Zheng, B., 2020. An improved k-NN classifier for epilepsy diagnosis. IEEE Access, 8, 100022-100030.
https://doi.org/10.1109/ACCESS.2020.2996946
CR  - Zhang, J., Wei, Z., Zou, J. and Fu, H., 2020. Automatic epileptic EEG classification based on differential entropy and attention model. Engineering Applications of Artificial Intelligence, 96, 103975.
https://doi.org/10.1016/j.engappai.2020.103975
CR  - Zhao, X., Zhang, R., Mei, Z., Chen, C. and Chen, W., 2019. Identification of epileptic seizures by characterizing instantaneous energy behavior of EEG. IEEE Access, 70059-70076.
https://doi.org/10.1109/ACCESS.2019.2919158
CR  - National Institute of Neurological Disorders and Stroke. http://www.ninds.nih.gov/(23.08.2024)
World Health Organization, https://www.who.int/, (23.08.2024)
UR  - https://doi.org/10.35414/akufemubid.1574539
L1  - https://dergipark.org.tr/en/download/article-file/4319099
ER  -