EŞİT GENİŞLİKLİ AYRIKLAŞTIRMA YÖNTEMİNE DAYALI YENİ BİR ÖZELLİK ÇIKARTMA YAKLAŞIMI VE YAPAY SİNİR AĞI KULLANARAK EPİLEPTİK ATAK TESPİTİ

Yıl 2011, Cilt: 26 Sayı: 3, 0 - , 20.02.2013

Umut Orhan Mahmut Hekim Mahmut Özer

Öz

Bu çalışmada, eşit genişlikli ayrıklaştırma (EGA) yöntemine dayalı yeni bir özellik çıkartma yaklaşımı önerilmişve Elektroensefalogram (EEG) işaretlerinden epileptik atak tespitinde bu yaklaşım ile elde edilen istatikselözellikler çok katmanlı algılayıcı sinir ağı (ÇKASA) modeline giriş olarak kullanılmıştır. Bu amaç için, EEGişaretleri EGA yöntemi ile ayrıklaştırılmış, her ayrık bölgenin yoğunluğuna dayalı histogramları elde edilmiş vehem gizli katmansız hem de 5 nörona sahip tek gizli katmanlı iki ÇKASA modeline giriş vektörü olarakuygulanmıştır. Her iki ÇKASA modeli de epileptik atak tespitinde yüksek başarı sağlamıştır. Bu sonuç, önerilenözellik çıkartma yöntemi sayesinde, doğrusal sınıflayıcıların da epileptik atak tespiti problemini çözebileceğinigöstermektedir. Sonuç olarak, EGA histogramı yaklaşımı biyomedikal işaret işlemede yeni bir özellik çıkartmayöntemi olarak kullanılabilir.

Anahtar Kelimeler

Eşit genişlikli ayrıklaştırma, biyomedikal işaret işleme, EEG işaretleri, epileptik atak tespiti, çok katmanlı algılayıcı sinir ağı, histogram

Kaynakça

• Adeli, H., Zhou, Z., ve Dadmehr, N., “Analysis
• of EEE Records in an Epileptic Patient using Wavelet Transform”, Journal of Neuroscience
• Methods, No 123, 69–87, 2003.
• Güler, İ., ve Übeyli, E. D., “Adaptive Neuro-
• Fuzzy Inference System for Classification of
• EEG Signals using Wavelet Coefficients”,
• Journal of Neuroscience Methods, No 148,
• –121, 2005.
• Khan, Y. U., ve Gotman, J., “Wavelet Based
• Automatic Seizure Detection in Intra-cerebral
• Electroencephalogram”, Clinical Neurophysiology,
• No 114, 898–908, 2003.
• Kıymık, M. K., Akın, M., ve Subaşı, A.,
• “Automatic Recognition of Alertness Level by
• using Wavelet Transform and Artificial Neural
• Network”, Journal of Neuroscience Methods,
• No 139, 231–240, 2004.
• Ocak, H., “Automatic Detection of Epileptic
• Seizures in EEG using Discrete Wavelet
• Transform and Approximate Entropy”, Expert
• Systems with Applications, No 36, 2027–2036,
• -
• Subaşı, A., “Automatic Recognition of Alertness
• Level from EEG by using Neural Network and
• Wavelet Coefficients”, Expert Systems with
• Applications, No 28, 701–711, 2005.
• Subaşı, A., “Epileptic Seizure Detection using
• Dynamic Wavelet Network”, Expert Systems
• with Applications, No 29, 343–355, 2005.
• Subaşı, A., “Automatic Detection of Epileptic
• Seizure using Dynamic Fuzzy Neural Networks”,
• Expert Systems with Applications, No 31, 320–
• , 2006.
• Subaşı, A., “EEG Signal Classification using
• Wavelet Feature Extraction and a Mixture of
• Expert Model”, Expert Systems with
• Applications, No 32, 1084–1093, 2007.
• Übeyli, E. D., “Combined Neural Network Model
• Employing Wavelet Coefficients for EEG Signals
• Classification”, Digital Signal Processing, No
• , 297–308, 2009.
• Übeyli, E. D., “Decision Support Systems for
• Time-Varying Biomedical Signals: EEG Signals
• Classification”, Expert Systems with
• Applications, No 36, 2275–2284, 2009.
• Alkan, A., Köklükaya, E., ve Subaşı, A.,
• “Automatic Seizure Detection in EEG using
• Logistic Regression and Artificial Neural
• Network”, Journal of Neuroscience Methods,
• No 148, 167–176, 2005.
• Subaşı, A., ve Ercelebi, E., “Classification of
• EEG Signals using Neural Network and Logistic
• Regression”, Computer Methods and
• Programs in Biomedicine, No 78, 87–99, 2005.
• Altunay, S., Telatar, Z., ve Eroğul, O., “Epileptic
• EEG Detection using the Linear Prediction Error
• Energy”, Expert Systems with Applications,
• Cilt 37, No 8, 5661–5665, 2010.
• Acır, N., “Automated System for Detection of
• Epileptiform Patterns in EEG by using a
• Modified RBFN Classifier”, Expert Systems
• with Applications, Cilt 29, No 2, 455–462, 2005.
• Subaşı, A., “Application of Adaptive Neuro-
• Fuzzy Inference System for Epileptic Seizure
• Detection using Wavelet Feature Extraction”,
• Computers in Biology and Medicine, Cilt 37,
• No 2, 227–244, 2007.
• Aslan, K., Bozdemir, H., Şahin, S., Oğulata, S. N.,
• ve Erol, R., “A Radial Basis Function Neural
• Network Model for Classification of Epilepsy
• using EEG Signals”, The Journal of Medical
• Systems, No 32, 403–408, 2008.
• Petrosian, A., Prokhorov, D., Homan, R., Dashei,
• R., ve Wunsch, D., “Recurrent Neural Network
• Based Prediction of Epileptic Seizures in Intra
• and Extra-cranial EEG”, Neurocomputing, No
• , 201–218, 2000.
• Srinivasan, V., Eswaran, C., ve Sriraam, N.,
• “Artificial Neural Network based Epileptic
• Detection using Time-Domain and Frequency-
• Domain Features”, Journal of Medical Systems,
• Cilt 29, No 6, 647–660, 2005.
• Pradhan, N., Sadasivan, P. K., ve Arunodaya, G.
• R., “Detection of Seizure Activity in EEG by an
• Artificial Neural Network: A Preliminary Study”,
• Computers and Biomedical Research, No 29,
• –313, 1996.
• Übeyli, E. D., “Analysis of EEG Signals by
• Combining Eigenvector Methods and Multi-class
• Support Vector Machines”, Computers in
• Biology and Medicine, Cilt 38, No 1, 14–22,
• -
• Kıymık, M. K., Subaşı, A., ve Özçalık, H. R.,
• “Neural Networks with Periodogram and
• Autoregressive Spectral Analysis Methods in
• Detection of Epileptic Seizure”, Journal of
• Medical Systems, Cilt 28, No 6, 511–522, 2004.
• Kıymık, M. K., Güler, İ., Dizibüyük, A., and
• Akın, M., “Comparison of STFT and Wavelet
• Transform Methods in Determining Epileptic
• Seizure Activity in EEG Signals for Real-time
• Application”, Computers in Biology and
• Medicine, Cilt 35, No 7, 603-616, 2005.
• Andrzejak, R. G., Lehnertz, K., Mormann, F.,
• Rieke, C., David, P., ve Elger, C. E., “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,
• Cilt 64, No 6, 061907, 2001.
• Hsu, C. N., Huang, H., J., Wong, T. T.,
• “Implications of the Dirichlet Assumption for
• Discretization of Continuous Variables in Naive
• Bayesian Classifiers”, Machine Learning, Cilt
• , No 3, 235–263, 2003.
• Jiang, S., Li, X., Zheng, Q., ve Wang, L.,
• “Approximate Equal Frequency Discretization
• Method”, Global Congress on Intelligent
• Systems, 514-518, 2009.
• Tay, E. H., ve Shen, L., “A Modified Chi2
• Algorithm for Discretization”, IEEE
• Transactions on Knowledge and Data
• Engineering, Cilt 14, No 3, 666–670, 2002.
• Gang, L. ve Tong, F., “An Unsupervised
• Discretization Algorithm based on Mixture
• Probabilistic Model”, Chinese Journal of
• Computers, Cilt 25, No 2, 158–164, 2002.
• Lee, C.H., “A Hellinger-based Discretization
• Method for Numeric Attributes in Classification
• Learning”, Knowledge-Based Systems, Cilt 20,
• No 4, 419–425, 2007.
• Fayyad, U.M, ve Irani, K.B., “Multi-interval
• Discretization of Continuous Valued Attributes
• for Classification Learning”, Proc. of the 13th
• International Joint Conference on Artificial
• Intelligence, 1022–1029, 1993.
• Clarke, E.J. ve Braton, B.A., “Entropy and MDL
• Discretization of Continuous Variables for
• Bayesian Belief Networks”, International
• Journal of Intelligence Systems, No 15, 61–92,
• -
• Xi, J. Ouyang, W.M., “Clustering based
• Algorithm for Best Discretizing Continuous
• Valued Attributes”, Mini-micro systems, Cilt 21,
• No 10, 1025–1027, 2000.