KaydedilenlerDerginizi ekleyin

Dergiler / Politeknik Dergisi / 2025 / Cilt: 28 Sayı: 6

EEG Sinyallerini Kullanarak 2D Konvolüsyonel Sinir Ağları ile Epilepsi Hastalığının Çok Sınıflı Tespiti

Multi-Class Detection of Epilepsy Disease with 2D Convolutional Neural Networks Using EEG Signals

Yiğithan Geniş(GAZİ ÜNİVERSİTESİ)0009-0009-5346-4574
Eda Akman Aydın(GAZİ ÜNİVERSİTESİ)0000-0002-9887-3808
Sayfa
1743–1753
Yayın Tarihi
2025-12-04
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Çalışmanın sonuçları GoogleNet transfer öğrenme modelinin CWT zaman-frekans gösterimi kullanılarak epilepsi teşhisinde en başarılı model olduğunu, önerilen yöntemin beş duruma ait EEG sinyallerini %95.33 doğrulukla ayırt edebildiğini göstermektedir.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Elektroensefalogram (EEG) epilepsi hastalığının teşhisi için önemli bir sinyaldir.
📊
Temel Bulgular & Veri:Sinyallerin, 2D CNN modelinde kullanılmak üzere zaman-frekans gösterimini elde edebilmek amacıyla Sürekli Dalgacık Dönüşümü (CWT) ile skalogram görüntüleri elde edilerek konvolüsyonel sinir ağı (CNN) için giriş görüntüleri olarak kullanılmıştır.
💡
Sonuç & Katkı:Çalışmanın sonuçları GoogleNet transfer öğrenme modelinin CWT zaman-frekans gösterimi kullanılarak epilepsi teşhisinde en başarılı model olduğunu, önerilen yöntemin beş duruma ait EEG sinyallerini %95.33 doğrulukla ayırt edebildiğini göstermektedir.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:EEG · Epilepsi · Sürekli Dalgacık Dönüşümü

Özet

Elektroensefalogram (EEG) epilepsi hastalığının teşhisi için önemli bir sinyaldir. Transfer öğrenme, veri boyutlarının model eğitimi için yeterli olmadığı durumlarda, önceden eğitilmiş model ağırlıklarının yeni problemlerde kullanılmasını sağlayan bir tekniktir. Bu çalışmada, transfer öğrenme modelleri sağlıklı gözü açık, sağlıklı gözü kapalı, nöbet anında olmayan hastadan epileptojenik bölgenin karşısından kaydedilmiş, nöbet anında olmayan hastadan epileptojenik bölgeden kaydedilmiş ve nöbet anındaki hastadan epileptojenik bölgeden kaydedilmiş EEG sinyal örneklerinin sınıflandırılması amacıyla kullanılmıştır. Sinyallerin, 2D CNN modelinde kullanılmak üzere zaman-frekans gösterimini elde edebilmek amacıyla Sürekli Dalgacık Dönüşümü (CWT) ile skalogram görüntüleri elde edilerek konvolüsyonel sinir ağı (CNN) için giriş görüntüleri olarak kullanılmıştır. Çalışmanın sonuçları GoogleNet transfer öğrenme modelinin CWT zaman-frekans gösterimi kullanılarak epilepsi teşhisinde en başarılı model olduğunu, önerilen yöntemin beş duruma ait EEG sinyallerini %95.33 doğrulukla ayırt edebildiğini göstermektedir.

Abstract

Electroencephalogram (EEG) is an important signal for the diagnosis of epilepsy. Transfer learning is a technique that allows the use of previously trained model weights in new problems when the data size is not sufficient for model training. In this study, transfer learning models were used to classify EEG signal samples recorded from volunteers relaxed in an awake state with eyes open and eyes closed; recorded from within the epileptogenic zone, and from the opposite of epileptogenic zone during seizure free intervals; and recorded from within the epileptogenic zone during seizure activity. In order to obtain the time-frequency representation of the signals, scalogram images were obtained with Continuous Wavelet Transform (CWT) and used as input images for the convolutional neural network (CNN). The results of the study show that the GoogleNet transfer learning model is the most successful model in the diagnosis of epilepsy with CWT images, and the proposed method can distinguish EEG signals belonging to five conditions with 95.33% accuracy.

🔖

Bu Makaleye Atıf Yap

Geniş, Y., Aydın, E. A. (2025). EEG Sinyallerini Kullanarak 2D Konvolüsyonel Sinir Ağları ile Epilepsi Hastalığının Çok Sınıflı Tespiti. Politeknik Dergisi, Cilt: 28 Sayı: 6, 1743–1753. https://doi.org/10.2339/politeknik.1589819

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (64)

  1. Bromfield E.B., Cavazos J.E., Sirven J.I., (editors) “An introduction to epilepsy: Basic mechanisms underlying seizures and epilepsy ”, American Epilepsy Society, West Hartford, (2006).
  2. WiegartzP., SeidenbergM., WoodardA., GidalB., Hermann B., “Comorbid psychiatric disorder in chronic epilepsy: recognition and etiology of depression” Neurology, 53: 3-8, (1999).
  3. Arunkumar N., KumarK.R., Venkataraman V., “Entropy features for focal EEG and non-focal EEG”, Journal of Computational Science, 27: 440-444, (2018).
  4. MendesV.C., MoritaM.E., AmorimB.J., RamosC.D., YasudaC.L., Tedeschi H., et al. “Automated online quantification method for 18F-FDG positron emission tomography/CT improves detection of the epileptogenic zone in patients with pharma coresistant epilepsy” Frontiers inNeurology, 8:453, (2017).
  5. PonnatapuraJ., VemannaS., BallalS., Singla A., “Utility of magnetic resonance ımaging brain epilepsy protocol in new-onset seizures: how is it different in developing countries?” Journal of Clinical Imaging Sciences, 8:43 (2018).
  6. DeivasigamaniS., SenthilpariC., Yong W.H., “Classification of focal and non-focal EEG signals using ANFIS classifier for epilepsy detection”, International Journal of Imaging Systems and Technology, 26: 277-283, (2016).
  7. Jobst B.C., Cascino G.D., “Resective epilepsy surgery for drug-resistant focal epilepsy: a review”, JAMA, 313 (3):285-293, (2015).
  8. Zhu G., Li Y., WenP.P., Wang S., Xi M., “Epileptogenic focus detection in intracranial EEG based on delay permutation entropy” AIP Conference Proceedings, 1559: 31-36, (2013).
  9. Sharma R., Pachori R.B., Acharya U.R., “Application of entropy measures on intrinsic mode functions for the automated identification of focal electroencephalogram signals”, Entropy, 17: 669-691, (2015).
  10. Bhattacharyya A., Pachori R.B., Acharya U.R., “Tunable-Q wavelet transform based multivariate sub-band fuzzy entropy with application to focal EEG signal analysis” Entropy, 19(3):99, (2017).
  11. Sharma R., Kumar M., Pachori R.B., Acharya U.R. “Decision support system for focal EEG signals using tunable-Q wavelet transform” Journal of Computational Science, 20:52-60, (2017).
  12. Das A.B., Bhuiyan M.I.H., “Discrimination and classification of focal and non-focal EEG signals using entropy-based features in the EMD-DWT domain”, Biomedical Signal Processing and Control, 29:11-21 (2016).
  13. Chatterjee S., Pratiher S., Bose R., “Multifractal detrended fluctuation analysis based novel feature extraction technique for automated detection of focal and non-focal electroencephalogram signals”, IET Science, Measurement & Technology, 11(8): 1014-1021, (2017).
  14. Acharya U.R., Hagiwara Y., Deshpande S.N., Suren S., Koh J.E.W., Oh S.L., et al., “Characterization of focal EEG signals: a review”, Future Generation Computer Systems, 91:290-299, (2018).
  15. Siddharth T., Gajbhiye P., Tripathy, R.K., Pachori R.B., “EEG based detection of focal seizure area using FBSE-EWT rhythm and SAE-SVM network”, IEEE Sensors Journal, 20(19):11421-11428, (2020).
  16. Rai K., Bajaj V., Kumar A., “Novel feature for identification of focal EEG signals with K-means and fuzzy C-means algorithms”, 2015 IEEE International Conference on Digital Signal Processing, Singapore, 412-416, (2015).
  17. Bajaj V., Rai K., Kumar A., Sharma D., Singh G.K., “Rhythm-based features for classification of focal and non-focal EEG signals”, IET Signal Processing, 11 (6):743-748, (2017).
  18. Arunkumar N., Ramkumar K., Venkatraman V., Abdulhay E., Fernandes S.L., Kadry S., et al. “Classification of focal and non-focal EEG using entropies”, Pattern Recognition Letters, 94: 112-117, (2017).
  19. Arunkumar N., Ramkumar K., Venkatraman V., Abdulhay E., Fernandes S.L., Kadry S., et al., “Classification of focal andnon focal EEG using entropies”, Pattern Recognition Letters,, 94:112-117, (2017).
  20. Siddharth T., Tripathy R.K., Pachori R.B., “Discrimination of focal and non-focal seizures from EEG signals using sliding mode singular spectrum analysis”, IEEE Sensors Journal, 19 (24): 12286-12296, (2019).
  21. Sharma R., Sircar P., Pachori R.B., “Automated focal EEG signal detection based on third order cumulant function”, Biomedical Signal Processing and Control, 58:101856, (2020).
  22. Acharya U.R., Hagiwara Y., Deshpande S.N., Suren S., Koh J.E.W., Oh S.L., et al., “Characterization of focal EEG signals: a review”, ”, Future Generation Computer Systems, 91: 290-299, (2018).
  23. Kiranyaz S., Zabihi M., Rad A.B., Tahir A., Ince T., Hamila R., et al., “Real-time PCG anomaly detection by adaptive 1D convolutional neural networks”, Neurocomputing, 411:291-301, (2020).
  24. Kaya U., Yılmaz A., Dikmen Y., “Sağlık alanında kullanılan derin öğrenme yöntemleri”, Avrupa Bilim ve Teknoloji Dergisi, 16:792-808, (2019).
  25. Acharya U.R., FujitaH., Oh S.L., Hagiwara Y. Tan, J.H., Adam M., “Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals” Information Sciences, 415:190-198, (2017).
  26. Huang J., Chen B., Yao B., He W., “ECG arrhythmia classification using STFT-based scalogram and convolutional neural network”, IEEE Access, 7: 92871-92880, (2019).
  27. Xu B., et al., “Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification”, IEEE Access, 7: 6084-6093, (2018).
  28. Sharma R., Sircar P., Pachori R.B., “Automated seizure classification using deep neural network based on autoencoder” Handbook of research on advancements of artificial intelligence in healthcare engineering, Advancement of Artificial Intelligence in Healthcare Engineering, IGI Global, 1-19, (2020).
  29. Xia P., Hu J., Peng Y., “EMG-Based Estimation of Limb Movement Using Deep Learning With Recurrent Convolutional Neural Networks”, Artif Organs, 2018 42(5):67-77, (2018).
  30. Talo M., “Automated classification of histopathology images using transfer learning”, Artificial Intelligence in Medicine, 101:101743, (2019).
  31. Talo M., Baloglu U.B., Yildirim Ö., Acharya U.R., “Application of deep transfer learning for automated brain abnormality classification using MR images”, Cognitive Systems Research, 54:176-188, (2019).
  32. Kumar P., Upadhyay P.K., Panda M.K., “SNSDeepNet: spike and non-spike detection in epilepsy”, Engineering Research Express, 6(3):035365, (2024).
  33. Reddy G. N., Hait S.R., Guha D., Mahadevappa M., “Classification of epileptic EEG signals with the utilization of Bonferroni mean based fuzzy pattern tree”, Expert Systems with Applications, 239: 122424, (2024).
  34. Zhao W., Wang W.F., Patnaik L. M., Zhang B.C., Weng S.J., Xiao S.X., Wei D.-Z., Zhou H.F., “Residual and bidirectional LSTM for epileptic seizure detection”, Frontiers in Computational Neuroscience, 18:1415967, (2024).
  35. Shanmugam, S., Dharmar, S. A., “CNN-LSTM hybrid network for automatic seizure detection in EEG signals”, Neural Computing and Applications, 35:20605–20617, (2023).
  36. Qiu X., Yan F., Liu H., “A difference attention ResNet-LSTM network for epileptic seizure detection using EEG signal”, Biomedical Signal Processing and Control, 82: 104652, (2023).
  37. Geniş Y., Aydin E.A., "Diagnosis of Epilepsy Disease with Deep Learning Methods Using EEG Signals," 30th Signal Processing and Communications Applications Conference, 1-4, (2022).
  38. Andrzejak R.G., Lehnertz K., Normann F., Rieke C., David P., 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, 64: 1-8, (2001).
  39. Faust O., Acharya U.R., Adeli H., Adeli A., “Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis”, Seizure, 26: 56-64, (2015).
  40. Yochum M., Renaud C., Jacquir S., “Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT” Biomedical Signal Processing and Control, 25: 46-52, (2016).
  41. Yochum M., Bakir T., Lepers R., Binczak S., “Estimation of muscular fatigue under electromyostimulation using CWT”, IEEE Transactions on Biomedical Engineering, 59(12): 3372-3378, (2012).
  42. Darvishi S., Al-Ani A., “Brain-computer interface analysis using continuous wavelet transform and adaptive neuro-fuzzy classifier”, International Conference of the IEEE Engineering in Medicine And Biology Society, Lyon, France, 3220-3223,(2007).
  43. Samar V., Bopardikar A., Rao R., Swartz K. “Wavelet analysis of neuroelectric waveforms: a conceptual tutorial”, Brain and Language, 66 (1): 7-60, (1999).
  44. LeCun Y., Bengio Y., Hinton G., “Deep learning”, Nature, 521(7553):436, (2015).
  45. Goodfellow I., Bengio Y., Courville A., “Deep learning” Cambridge: MIT Press, 1(2): 20-120, (2016).
  46. Yildirim O., Talo M., Ay B., Baloglu U.B., Aydin G., Acharya U.R., “Automated detection of diabetic subject using pre-trained 2D-CNN models with frequency spectrum images extracted from heart rate signals”, Computers in Biology and Medicine, 113: 103387, (2019).
  47. Krizhevsky A., Sutskever I., Hinton G.E., “Imagenet classification with deep convolutional neural networks”, Advances in Neural Information Processing Systems, Pereira F., BurgesC.J., Bottou L., Weinberger K.Q., Curran Associates, Inc., 25, (2012).
  48. Szegedy C., Ioffe S., Vanhoucke V., Alemi A., “Inception-v4, inception-ResNet and the impact of residual connections on learning” 31. AAAI Conference on Artificial Intelligence, California, USA, 4278-4284, (2017).
  49. Szegedy C., Reed S., Erhan D., Anguelov, D., Ioffe, S. “Scalable, high-quality object detection”, arXiv:1412.1441, (2014).
  50. Tan, M., Le, Q., “Efficientnet: Rethinking model scaling for convolutional neural networks”, 36th International Conference on Machine Learning, PMLR, California, USA, 97: 6105-6114, (2019).
  51. Simonyan K., Zisserman A., “Very deep convolutional networks for large-scale image recognition”, arXiv:1409.1556, (2014).
  52. Kingma D.P., Ba J.L., “Adam: a method for stochastic optimization”, 3rd International Conference for Learning Representations, San Diego, 1-41, (2015).
  53. Narin A., Isler Y., Ozer M., Perc M., “Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability” Physica A, 509: 56-65, (2018).
  54. Isler Y., Narin A., Ozer M., Perc M., “Multi-stage classification of congestive heart failure based on short-term heart rate variability” Chaos Solitons Fractals, 118:145-151, (2019).
  55. Tuncer E., Bolat E. D., “Destek vektör makineleri ile EEG sinyallerinden epileptik nöbet sınıflandırması”, Politeknik Dergisi, 25(1): 239249, (2022).
  56. Varlı M., Yılmaz H., “Multiple classification of EEG signals and epileptic seizure diagnosis with combined deep learning”, Journal of Computational Science, 67:101943, (2023).
  57. Xu, G., Ren, T., Chen, Y., Che, W., “A One-Dimensional CNN-LSTM Model for Epileptic Seizure Recognition Using EEG Signal Analysis”, Frontiers in Neuroscience, 14:1253, (2020).
  58. WiegartzP., SeidenbergM., WoodardA., GidalB., Hermann B., “Comorbid psychiatric disorder in chronic epilepsy: recognition and etiology of depression” Neurology, 53: 3-8, (1999).
  59. MendesV.C., MoritaM.E., AmorimB.J., RamosC.D., YasudaC.L., Tedeschi H., et al. “Automated online quantification method for 18F-FDG positron emission tomography/CT improves detection of the epileptogenic zone in patients with pharma coresistant epilepsy” Frontiers inNeurology, 8:453, (2017).
  60. PonnatapuraJ., VemannaS., BallalS., Singla A., “Utility of magnetic resonance ımaging brain epilepsy protocol in new-onset seizures: how is it different in developing countries?” Journal of Clinical Imaging Sciences, 8:43 (2018).
  61. DeivasigamaniS., SenthilpariC., Yong W.H., “Classification of focal and non-focal EEG signals using ANFIS classifier for epilepsy detection”, International Journal of Imaging Systems and Technology, 26: 277-283, (2016).
  62. Arunkumar N., Ramkumar K., Venkatraman V., Abdulhay E., Fernandes S.L., Kadry S., et al., “Classification of focal andnon focal EEG using entropies”, Pattern Recognition Letters,, 94:112-117, (2017).
  63. Acharya U.R., FujitaH., Oh S.L., Hagiwara Y. Tan, J.H., Adam M., “Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals” Information Sciences, 415:190-198, (2017).
  64. Faust O., Acharya U.R., Adeli H., Adeli A., “Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis”, Seizure, 26: 56-64, (2015).