Öz
The detection of epileptic seizures by electroencephalography (EEG) signals has become a standard method for the diagnosis of epilepsy. Accurate and automatic detection of epileptic seizures is needed since manual identification of epileptic seizures by specialist neurologists is a time consuming and labor intensive process, which also leads to various errors. For this purpose, frequency-based features were extracted from the EEG signal and a various classifiers based on ensemble learning was used to detect epileptic seizures automatically. The performance of the proposed method was tested using cross-validation and cross-patient experiments. According to the experimental results, sensitivity, specificity and accuracy rates were 94%, 93% and 93% for cross-validation and 76%, 90% and 90% for cross-patients, respectively.
Anahtar Kelimeler
Kaynakça
- Alvarado-Rojas, C., Valderrama, M., Fouad-Ahmed, A., Feldwisch-Drentrup, H., Ihle, M., Teixeira, C., . . . Dourado, A. (2014). Slow modulations of high-frequency activity (40–140 Hz) discriminate preictal changes in human focal epilepsy. Scientific reports, 4(1), 1-9.
- Chandaka, S., Chatterjee, A., & Munshi, S. (2009). Cross-correlation aided support vector machine classifier for classification of EEG signals. Expert Systems with Applications, 36(2), 1329-1336.
- Chen, D., Wan, S., Xiang, J., & Bao, F. S. (2017). A high-performance seizure detection algorithm based on Discrete Wavelet Transform (DWT) and EEG. PloS one, 12(3), e0173138.
- Feudjio, C., Noyum, V. D., Mofendjou, Y. P., & Fokoué, E. (2021). A Novel Use of Discrete Wavelet Transform Features in the Prediction of Epileptic Seizures from EEG Data. arXiv preprint arXiv:2102.01647.
- Ghritlahare, R., Sahu, M., & Kumar, R. (2019). Classification of Two-Class Motor Imagery EEG Signals Using Empirical Mode Decomposition and Hilbert–Huang Transformation. In Computing and Network Sustainability (pp. 375-386): Springer.
- Hussein, R., Palangi, H., Ward, R. K., & Wang, Z. J. (2019). Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals. Clinical Neurophysiology, 130(1), 25-37.
Öz
Elektroensefalografi (EEG) sinyallerinin analizi ile epileptik nöbetlerin belirlenmesi, epilepsi hastalığı tanısı için standart bir yöntem haline gelmiştir. Epileptik nöbetlerin uzman nörologlar tarafından el ile belirlenmesi yoğun çalışma gerektiren, oldukça zaman alıcı bir işlem olduğu gibi kişilerden kaynaklanan çeşitli hataların oluşmasına sebep olmaktadır. Bu sebeple epileptik nöbetlerin doğru ve otomatik bir şekilde belirlenmesine ihtiyaç duyulmaktadır. Bu amaç doğrultusunda bu tez kapsamında, EEG sinyalinden frekans tabanlı öznitelikler çıkarılmış ve kolektif öğrenmeye dayalı sınıflandırıcılar kullanılması önerilmiştir. Önerilen yöntemin performansı çapraz doğrulama ve çapraz hasta deneyleri kullanılarak test edilmiştir. Elde edilen deneysel sonuçlara göre çapraz doğrulama deneyi için duyarlılık, özgüllük ve doğruluk oranları yaklaşık olarak sırayla %94, %93 ve %93 ve çapraz hasta için ise %76, %90 ve %90 olarak bulunmuştur.
Anahtar Kelimeler
Kaynakça
- Alvarado-Rojas, C., Valderrama, M., Fouad-Ahmed, A., Feldwisch-Drentrup, H., Ihle, M., Teixeira, C., . . . Dourado, A. (2014). Slow modulations of high-frequency activity (40–140 Hz) discriminate preictal changes in human focal epilepsy. Scientific reports, 4(1), 1-9.
- Chandaka, S., Chatterjee, A., & Munshi, S. (2009). Cross-correlation aided support vector machine classifier for classification of EEG signals. Expert Systems with Applications, 36(2), 1329-1336.
- Chen, D., Wan, S., Xiang, J., & Bao, F. S. (2017). A high-performance seizure detection algorithm based on Discrete Wavelet Transform (DWT) and EEG. PloS one, 12(3), e0173138.
- Feudjio, C., Noyum, V. D., Mofendjou, Y. P., & Fokoué, E. (2021). A Novel Use of Discrete Wavelet Transform Features in the Prediction of Epileptic Seizures from EEG Data. arXiv preprint arXiv:2102.01647.
- Ghritlahare, R., Sahu, M., & Kumar, R. (2019). Classification of Two-Class Motor Imagery EEG Signals Using Empirical Mode Decomposition and Hilbert–Huang Transformation. In Computing and Network Sustainability (pp. 375-386): Springer.
- Hussein, R., Palangi, H., Ward, R. K., & Wang, Z. J. (2019). Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals. Clinical Neurophysiology, 130(1), 25-37.
Ayrıntılar
| Birincil Dil | İngilizce |
|---|---|
| Konular | Mühendislik |
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 31 Mart 2021 |
| Yayımlandığı Sayı | Yıl 2021 |