High-Resolution Power Spectral Density Approaches For Epileptic Seizure Detection

Yıl 2025, ERKEN GÖRÜNÜM, 1 - 1

Nuri İkizler , Güneş Ekim

https://doi.org/10.2339/politeknik.1605362

Öz

Epilepsy is a neurological disorder that affects millions of people worldwide, and the rapid and accurate detection of epileptic seizures is crucial in improving patients' quality of life. This study performs various analyses using different power spectral density methods and classifiers for epileptic seizure detection from EEG signals. Methods such as Music, Lomb-Scargle, Multitaper, Welch, Periodogram, and Burg are tested to identify changes in their ability to distinguish spectral resolution and frequency components. Reference signals are created for each class, and discriminative features such as spectral energy, spectral entropy, and maximum spectral deviation are extracted by comparing these reference signals. These feature vectors are used in classification with Random Forest and k-Nearest Neighbor algorithms. The results indicate that the high-resolution spectral power density methods, Music and Lomb-Scargle, along with the Random Forest classifier, achieved the highest accuracy. This study makes a significant contribution to the literature by demonstrating that the combined use of high-resolution spectral power density methods and powerful ensemble learning-based classifiers can significantly improve seizure detection accuracy.

Anahtar Kelimeler

Epileptic seizure detection, Music method, Lomb-Scargle method, Random Forest classifier

Epileptik Nöbet Tespiti İçin Yüksek Çözünürlüklü Güç Spektral Yoğunluğu Yaklaşımları

Öz

Epilepsi, dünya çapında milyonlarca insanı etkileyen bir nörolojik hastalık olup, epileptik nöbetlerin hızlı ve doğru bir şekilde tespiti, hastaların yaşam kalitesini artırmada büyük öneme sahiptir. Bu çalışmada, EEG sinyallerinden epileptik nöbet tespiti için çeşitli güç spektral yoğunluğu yöntemleri ve sınıflandırıcılar kullanılarak farklı analizler yapılmıştır. Her bir yöntemin spektral çözünürlük ve frekans bileşenlerini ayırt etme yeteneklerinin gösterdiği değişikliği tespit etmek için Music, Lomb-Scargle, Multitaper, Welch, Periodogram, Burg gibi farklı yöntemler denenmiştir. Her sınıf için referans sinyaller oluşturulmuş, bu referans sinyallerle karşılaştırılarak spektral enerji, spektral entropi ve maksimum spektral sapma gibi ayırt edici özellikler çıkarılmıştır. Bu öznitelik vektörleri, sınıflandırıcı olarak seçilen Rastgele Orman ve k-En Yakın Komşu algoritmalarında kullanılarak sınıflandırma işlemi gerçekleştirilmiştir. Elde edilen sonuçlara göre, yüksek çözünürlüklü güç spektral yoğunluğu yöntemleri olan Music ve Lomb-Scargle ile Rastgele Orman sınıflandırıcısı en yüksek doğruluğa ulaşmıştır. Bu çalışma, epileptik nöbet tespiti alanında yüksek çözünürlüklü güç spektral yoğunluğu yöntemleri ve güçlü topluluk öğrenme tabanlı sınıflandırıcıların birlikte kullanımının, nöbet tespit doğruluğunu anlamlı şekilde artırabileceğini ortaya koyarak literatüre önemli bir katkı sunmaktadır.

Anahtar Kelimeler

Epileptik nöbet tespiti, Music yöntemi, Lomb-Scargle yöntemi, Rastgele Orman sınıflandırıcısı

Kaynakça

• [1] Beghi E., "The epidemiology of epilepsy", Neuroepidemiology, 54(2): 185-191, (2020).
• [2] Moshé S.L., Perucca E., Ryvlin P. and Tomson T., “Epilepsy: new advances”, The Lancet, 385(9971): 884-898, (2015).
• [3] Acharya U.R., Sree S.V., Swapna G., Martis R.J. and Suri J.S., “Automated EEG analysis of epilepsy: a review”, Knowledge-Based Systems, 45: 147-165, (2013).
• [4] Maganti R.K. and Rutecki P., “EEG and epilepsy monitoring”, CONTINUUM: Lifelong Learning in Neurology, 19(3): 598-622, (2013).
• [5] Siddiqui M.K., Morales-Menendez R., Huang X. and Hussain N., “A review of epileptic seizure detection using machine learning classifiers”, Brain informatics, 7(1): 5, (2020).
• [6] Abdullayeva E. and Örnek H.K., “Diagnosing Epilepsy from EEG Using Machine Learning and Welch Spectral Analysis”, Traitement du Signal, 41(2): 971-977, (2024).
• [7] Shen M., Wen P., Song B. and 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] Chen D., Wan S., Xiang J. and Bao F.S., “A high-performance seizure detection algorithm based on Discrete Wavelet Transform (DWT) and EEG”, PloS one, 12(3): e0173138, (2017).
• [9] Omidvar M., Zahedi A. and Bakhshi H., “EEG signal processing for epilepsy seizure detection using 5-level Db4 discrete wavelet transform, GA-based feature selection and ANN/SVM classifiers”, Journal of ambient intelligence and humanized computing, 12(11): 10395-10403, (2021).
• [10] Altunay S., Telatar Z. and Erogul O., “Epileptic EEG detection using the linear prediction error energy”, Expert Systems with Applications, 37(8): 5661-5665, (2010).
• [11] Hassan A.R., Bashar S.K. and Bhuiyan M.I.H., “On the classification of sleep states by means of statistical and spectral features from single channel electroencephalogram”, 2015 International conference on advances in computing, communications and informatics (ICACCI), Kochi, India, 2238-2243, IEEE, (2015).
• [12] Ahmad I., Wang X., Zhu M., Wang C., Pi Y., Khan J.A., Khan S., Samuel O.G., Chen S. and Li G., “EEG‐Based Epileptic Seizure Detection via Machine/Deep Learning Approaches: A Systematic Review”, Computational Intelligence and Neuroscience, 2022(1): 6486570, (2022).
• [13] Tran L.V., Tran H.M., Le T.M., Huynh T.T., Tran H.T. and Dao S.V., “Application of machine learning in epileptic seizure detection”, Diagnostics, 12(11): 2879, (2022).
• [14] Prasanna C.S., Rahman M.Z.U. and Bayleyegn M.D., “Brain epileptic seizure detection using joint CNN and exhaustive feature selection with RNN-BLSTM classifier”, IEEE Access, 11: 97990-98004, (2023).
• [15] Shekokar K.S. and Dour S., “Automatic epileptic seizure detection using LSTM networks”, World Journal of Engineering, 19(2): 224-229, (2022).
• [16] Subasi A., Kevric J. and Abdullah Canbaz M., “Epileptic seizure detection using hybrid machine learning methods”, Neural Computing and Applications, 31: 317-325, (2019).
• [17] Sahu R., Dash S.R., Cacha L.A., Poznanski R.R. and Parida S., “Epileptic seizure detection: a comparative study between deep and traditional machine learning techniques”, Journal of integrative neuroscience, 19(1): 1-9, (2020).
• [18] Handa P., Mathur M. and Goel N., “EEG Datasets in Machine Learning Applications of Epilepsy Diagnosis and Seizure Detection”, SN Computer Science, 4(5): 437, (2023).
• [19] Harpale V.K. and Bairagi V.K., “Time and frequency domain analysis of EEG signals for seizure detection: A review”, 2016 International Conference on Microelectronics, Computing and Communications (MicroCom), Durgapur, India, 1-6, IEEE, (2016).
• [20] Alkan A. and Kiymik M.K., “Comparison of AR and Welch methods in epileptic seizure detection”, Journal of Medical Systems, 30: 413-419, (2006).
• [21] Demirel B.U., Skelin I., Zhang H., Lin J.J. and Al Faruque M.A., “Single-channel EEG based arousal level estimation using Multitaper spectrum estimation at low-power wearable devices”, 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Mexico, 542-545, IEEE, (2021).
• [22] Faust O., Acharya R.U., Allen A.R. and Lin C.M., “Analysis of EEG signals during epileptic and alcoholic states using AR modeling techniques”, Irbm, 29(1): 44-52, (2008).
• [23] Pamula V.R., Van Hoof C. and Verhelst M., “Compressed Domain Feature Extraction”, Analog-and-Algorithm-Assisted Ultra-low Power Biosignal Acquisition Systems, 55-67, (2019).
• [24] Übeyli E.D. and Güler İ., “Features extracted by eigenvector methods for detecting variability of EEG signals”, Pattern Recognition Letters, 28(5): 592-603, (2007).
• [25] Liu S., Wang J., Li S. and Cai L., “Epileptic seizure detection and prediction in EEGS using power spectra density parameterization”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 31: 3884 – 3894, (2023).
• [26] Das P., Manikandan M.S. and Ramkumar B., “Detection of epileptic seizure event in EEG signals using variational mode decomposition and mode spectral entropy”, 2018 IEEE 13th International Conference on Industrial and Information Systems (ICIIS), Rupnagar, India, 42-47, IEEE, (2018).
• [27] Boashash B., Barki H. and Ouelha S., “Performance evaluation of time-frequency image feature sets for improved classification and analysis of non-stationary signals: Application to newborn EEG seizure detection”, Knowledge-Based Systems, 132: 188-203, (2017).
• [28] Heers M., Helias M., Hedrich T., Dümpelmann M., Schulze-Bonhage A. and Ball T., “Spectral bandwidth of interictal fast epileptic activity characterizes the seizure onset zone”, NeuroImage: Clinical, 17: 865-872, (2018).
• [29] Tapani K.T., Vanhatalo S. and Stevenson N.J., “Time-varying EEG correlations improve automated neonatal seizure detection”, International journal of neural systems, 29(04): 1850030, (2019).
• [30] Vidyaratne L.S. and Iftekharuddin K.M., “Real-time epileptic seizure detection using EEG”, IEEE Transactions on Neural Systems and Rehabilitation Engineering, 25(11): 2146-2156, (2017).
• [31] Chakraborty M. and Mitra D., “Epilepsy seizure detection using kurtosis based VMD’s parameters selection and bandwidth features”, Biomedical Signal Processing and Control, 64: 102255, (2021).
• [32] Gowrishankar K., Muthukumar V., Sudhakara P.R., Deivasigamani S. and Ang C.K., “A Novel SVM and K-NN Classifier Based Machine Learning Technique for Epileptic Seizure Detection”, International Journal of Online & Biomedical Engineering, 19(7): 99-124, (2023).
• [33] Juba B. and Le H.S., “Precision-recall versus accuracy and the role of large data sets”, Proceedings of the AAAI conference on artificial intelligence, 33(01): 4039-4048, (2019).
• [34] Tuncer E. and Bolat E.D.. “Destek vektör makinaları ile EEG sinyallerinden epileptik nöbet sınıflandırması”, Politeknik Dergisi, 25(1): 239-249, (2022).