Pembe gürültü enjeksiyonunun EEG tabanlı epileptik nöbet tespiti üzerindeki etkisinin değerlendirilmesi

Yıl 2026, Cilt: 41 Sayı: 1 , 703 - 718 , 31.03.2026

Güneş Ekim

https://doi.org/10.17341/gazimmfd.1790413

https://izlik.org/JA85CX43MR

Öz

Epilepsi, dünya genelinde 50 milyondan fazla kişiyi etkileyen ciddi bir nörolojik hastalıktır ve nöbetlerin öngörülemeyen şekilde ortaya çıkması hasta güvenliği ve yaşam kalitesi açısından kritik riskler oluşturmaktadır. Bu nedenle, otomatik nöbet tespit sistemlerinin yalnızca yüksek doğruluk sağlaması değil, aynı zamanda gerçek hayatta karşılaşılan gürültü ve artefaktlara karşı dayanıklılık göstermesi gerekir. Ancak mevcut çalışmaların çoğu, yalnızca temiz EEG verileri üzerinde değerlendirme yapmakta ve gerçek klinik koşullardaki bozucuları dikkate almamaktadır. Bu çalışmada, düşük frekans bileşenlerinde yoğun enerji dağılımı nedeniyle biyolojik sinyalleri daha gerçekçi biçimde temsil eden pembe gürültü koşullarında epileptik nöbet tespit sistemlerinin dayanıklılığı sistematik olarak değerlendirilmiştir. Özellik çıkarımı için iki yöntem karşılaştırılmıştır: Sınıf bazlı referans spektrumları ile güç spektral yoğunluğu fark özellikleri ve çeşitli dalgacık tipleri arasından Coiflet 4’ün seçildiği ayrık dalgacık dönüşümü. Sınıflandırma Rastgele Orman, Çok Katmanlı Algılayıcı ve k-En Yakın Komşu ile yapılmıştır. Sonuçlar, özellikle güç spektral yoğunluğu özellikleri ile rastgele orman sınıflandırıcısının farklı gürültü seviyelerinde en yüksek başarımı sağladığını göstermiştir. Ayrıca, düşük ve orta seviyelerdeki pembe gürültünün doğruluk performansını yalnızca korumakla kalmayıp belirli durumlarda iyileştirdiği gözlemlenmiştir. Çalışma, pembe gürültü enjeksiyonunu dayanıklılığı test eden gerçekçi bir çerçeve olarak sunması ve güç spektral yoğunluğu ve rastgele orman kombinasyonunun hesaplama açısından verimli, klinikte uygulanabilir bir çözüm olduğunu göstermektedir.

Anahtar Kelimeler

Epileptik nöbet tespiti , EEG sinyal analizi , pembe gürültü enjeksiyonu , güç spektral yoğunluğu , dalgacık dönüşümü

Evaluating the impact of pink noise injection on EEG-based epileptic seizure detection

https://izlik.org/JA85CX43MR

Öz

Epilepsy is a serious neurological disorder affecting more than 50 million people worldwide, and the unpredictable occurrence of seizures poses critical risks to patient safety and quality of life. Therefore, automatic seizure detection systems must not only achieve high accuracy but also demonstrate robustness against noise and artifacts encountered in real-world scenarios. However, most existing studies are conducted solely on clean EEG data and fail to adequately account for the disturbances present in clinical conditions. In this study, the robustness of epileptic seizure detection systems was systematically evaluated under pink noise conditions, which, due to their high energy distribution at low frequencies, provides a more realistic representation of biological signals. Two feature extraction methods were compared: power spectral density with class-based reference spectral difference features, and discrete wavelet transform with Coiflet 4 selected among various wavelet types. Classification was performed using Random Forest, Multilayer Perceptron, and k-Nearest Neighbor. The results demonstrated that power spectral density features combined with the Random Forest classifier consistently achieved the highest performance across different noise levels. Furthermore, low and moderate levels of pink noise were observed not only to preserve but, in some cases, to improve classification accuracy. This study highlights the introduction of pink noise injection as a realistic framework for testing robustness and shows that the combination of power spectral density and Random Forest provides a computationally efficient and clinically applicable solution for EEG-based seizure detection.

Anahtar Kelimeler

Epileptic seizure detection , EEG signal analysis , pink noise injection , power spectral density , wavelet transform

Kaynakça

• 1. World Health Organization. https://www.who.int/news-room/fact-sheets/detail/epilepsy. Yayın tarihi Şubat 7, 2024. Erişim tarihi Temmuz 23, 2025.
• 2. Milligan T.A., Epilepsy: a clinical overview, The American Journal of Medicine, 134 (7), 840-847, 2021.
• 3. Farooq M.S., Zulfiqar A., Riaz S., Epileptic seizure detection using machine learning: Taxonomy, opportunities, and challenges, Diagnostics, 13 (6), 1058, 2023.
• 4. Ein Shoka A.A., Dessouky M.M., El-Sayed A., Hemdan E.E.D., EEG seizure detection: concepts, techniques, challenges, and future trends, Multimedia Tools and Applications, 82 (27), 42021-42051, 2023.
• 5. Almahdi A.J., Yaseen A.J., Dakhil A.F., EEG signals analysis for epileptic seizure detection using DWT method with SVM and KNN classifiers, Iraqi Journal of Science, Special Issue (2), 54-62, 2021.
• 6. Saday A., Ozkan İ.A., Classification of epileptic EEG signals using DWT-based feature extraction and machine learning methods, International Journal of Applied Mathematics Electronics and Computers, 9 (4), 122-129, 2021.
• 7. 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, 77, 103820, 2022.
• 8. Djemili R., Djemili I., Nonlinear and chaos features over EMD/VMD decomposition methods for ictal EEG signals detection, Computer Methods in Biomechanics and Biomedical Engineering, 27 (15), 2091-2110, 2024.
• 9. Zhang X., Yan C., An extraction and classification based on EMD and LSSVM of epileptic EEG, Biomedical Engineering: Applications, Basis and Communications, 34 (05), 2250034, 2022.
• 10. Bairagi V.K., Harpale V.K., Improved epileptic seizure detection using singular spectrum empirical mode decomposition and machine learning approach, Journal of Statistics and Management Systems, 25 (1), 103-123, 2022.
• 11. Zarei A., Asl B.M., Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy-based features of EEG signals, Computers in Biology and Medicine, 131, 104250, 2021.
• 12. Kbah S.N.S., Al-Qazzaz N.K., Jaafer S.H., Sabir M.K., Epileptic EEG activity detection for children using entropy-based biomarkers, Neuroscience Informatics, 2 (4), 100101, 2022.
• 13. Sikarwar S.S., Rana A.K., Sengar S.S., Entropy-driven deep learning framework for epilepsy detection using electro encephalogram signals, Neuroscience, 577, 12-24, 2025.
• 14. Pandey S.K., Janghel R.R., Mishra P.K., Ahirwal M.K., Automated epilepsy seizure detection from EEG signal based on hybrid CNN and LSTM model, Signal, Image and Video Processing, 17 (4), 1113-1122, 2023.
• 15. Shanmugam S., Dharmar S., A CNN-LSTM hybrid network for automatic seizure detection in EEG signals, Neural Computing and Applications, 35 (28), 20605-20617, 2023.
• 16. Wang X., Wang Y., Liu D., Wang Y., Wang Z., Automated recognition of epilepsy from EEG signals using a combining space–time algorithm of CNN-LSTM, Scientific Reports, 13 (1), 14876, 2023.
• 17. Shoeibi A., Khodatars M., Ghassemi N., Jafari M., Moridian P., Alizadehsani R., Acharya U.R., Epileptic seizures detection using deep learning techniques: a review, International Journal of Environmental Research and Public Health, 18 (11), 5780, 2021.
• 18. Chen W., Wang Y., Ren Y., Jiang H., Du G., Zhang J., Li J., An automated detection of epileptic seizures EEG using CNN classifier based on feature fusion with high accuracy, BMC Medical Informatics and Decision Making, 23 (1), 96, 2023.
• 19. Ahmad I., Wang X., Javeed D., Kumar P., Samuel O.W., Chen S., A hybrid deep learning approach for epileptic seizure detection in EEG signals, IEEE Journal of Biomedical and Health Informatics, 2023.
• 20. Islam M.S., Thapa K., Yang S.H., Epileptic-net: An improved epileptic seizure detection system using dense convolutional block with attention network from EEG, Sensors, 22 (3), 728, 2022.
• 21. Kumar G., Chander S., Almadhor A., An intelligent epilepsy seizure detection system using adaptive mode decomposition of EEG signals, Physical and Engineering Sciences in Medicine, 45 (1), 261-272, 2022. 22. Handa P., Mathur M., Goel N., EEG datasets in machine learning applications of epilepsy diagnosis and seizure detection, SN Computer Science, 4 (5), 437, 2023.
• 23. Göker H., Automatic detection of developmental coordination disorder from power spectral densities of electroencephalography (EEG) signals using deep learning model, Journal of the Faculty of Engineering and Architecture of Gazi University, 40 (1), 401-412, 2024.
• 24. 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, 64, 102005, 2025.
• 25. Ikizler N., Ekim G., Epileptik nöbet tespiti için yüksek çözünürlüklü güç spektral yoğunluğu yaklaşımları, Politeknik Dergisi, 1-1, 2025.
• 26. Rabby M.K.M., Islam A.K., Belkasim S., Bikdash M.U., Wavelet transform-based feature extraction approach for epileptic seizure classification, ACMSE '21:Proceedings of the 2021 ACM Southeast Conference, Virtual Event USA, 164-169, 15-17 April, 2021.
• 27. Demirci B.A., Demirci O., Engin M., Comparative analysis of ANN performance of four feature extraction methods used in the detection of epileptic seizures, Computers in Biology and Medicine, 166, 107491, 2023.
• 28. Mostafa M., Samin M.A., Hassan N.B., Nibras S.Z., Rahman S., Abrar M.A., Parvez M.Z., DWT based transformed domain feature extraction approach for epileptic seizure detection, TENCON 2021 – 2021 IEEE Region 10 Conference (TENCON), Auckland, New Zealand, 411-416, 7-10 December, 2021.
• 29. Barry R.J., De Blasio F.M., Duda A.T., Munford B.S., Prestimulus EEG oscillations and pink noise affect Go/No-Go ERPs, Sensors, 25 (6), 1733, 2025.
• 30. Huang C.M., Lai W.L., Yang C.C., Hsieh Y.J., Wu C.M., Lee C.H., EEG channel localization and selection via training with noise injection for BCI applications, 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA, 1-4, 15-19 July, 2024.
• 31. Basri A., Arif M., Classification of seizure types using random forest classifier, Advances in Science and Technology Research Journal, 15 (3), 2021.
• 32. Zubair M., Belykh M.V., Naik M.U.K., Gouher M.F.M., Vishwakarma S., Ahamed S.R., Kongara R., Detection of epileptic seizures from EEG signals by combining dimensionality reduction algorithms with machine learning models, IEEE Sensors Journal, 21 (15), 16861-16869, 2021.
• 33. Thangarajoo R.G., Reaz M.B.I., Srivastava G., Haque F., Ali S.H.M., Bakar A.A.A., Bhuiyan M.A.S., Machine learning-based epileptic seizure detection methods using wavelet and EMD-based decomposition techniques: A review, Sensors, 21 (24), 8485, 2021.
• 34. Mouleeshuwarapprabu R., Kasthuri N., Feature extraction and classification of EEG signal using multilayer perceptron, Journal of Electrical Engineering & Technology, 18 (4), 3171-3178, 2023.
• 35. Herbozo Contreras L.F., Cui J., Yu L., Huang Z., Nikpour A., Kavehei O., KAN–EEG: Towards replacing backbone–MLP for an effective seizure detection system, Royal Society Open Science, 12 (3), 240999, 2025.
• 36. Nogay H.S., Adeli H., Detection of epileptic seizure using pretrained deep convolutional neural network and transfer learning, European Neurology, 83 (6), 602-614, 2021.
• 37. Dash D.P., Kolekar M.H., Jha K., Surface EEG based epileptic seizure detection using wavelet based features and dynamic mode decomposition power along with KNN classifier, Multimedia Tools and Applications, 81 (29), 42057-42077, 2022.
• 38. Değirmenci M., Yüce Y., İşler, Y., Classification of finger movements using statistically significant time-domain EEG features, Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (3), 1597-1610, 2024.
• 39. Vujović Ž., Classification model evaluation metrics, International Journal of Advanced Computer Science and Applications, 12 (6), 599-606, 2021.
• 40. Naidu G., Zuva T., Sibanda E.M., A review of evaluation metrics in machine learning algorithms, Computer Science On-line Conference, Cham: Springer International Publishing, 15-25, 9 July, 2023.
• 41. Hassan A.R., Subasi A., Zhang Y., Epilepsy seizure detection using complete ensemble empirical mode decomposition with adaptive noise, Knowledge-Based Systems, 191, 105333, 2020.
• 42. Thomas A.H., Aminifar A., Atienza D., Noise-resilient and interpretable epileptic seizure detection, 2020 IEEE International Symposium on Circuits and Systems (ISCAS), Seville, Spain, 1-5, 12-14 October, 2020.
• 43. Hussein R., Palangi H., Ward R.K., Wang Z.J., Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals, Clinical Neurophysiology, 130 (1), 25-37, 2019.