SavedAdd your journal

Journals / Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi / 2026 / Cilt: 42 Sayı: 2

Automated Schizophrenia Detection via Resnet50-based Ensemble Learning Using Multi-entropy EEG Feature Maps

Çoklu Entropi EEG Özellik Haritaları Kullanılarak Resnet50 Tabanlı Topluluk Öğrenimi ile Otomatik Şizofreni Tespiti

Özlem Karabiber Cura(İZMİR KATİP ÇELEBİ ÜNİVERSİTESİ)0000-0001-8650-1137
Pages
—
Publication Date
2026-06-16
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Conclusion: The integration of entropy-based EEG features into the deep learning ensemble improves schizophrenia detection.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Background/Aim: A complicated neuropsychiatric condition, schizophrenia is commonly investigated using one-dimensional EEG signals.
📊
Key Findings & Data:In this work, a novel deep learning framework for automated schizophrenia detection is proposed, integrating an ensemble model based on ResNet50 with multi-entropy-based feature maps derived from 10-second EEG segments.
💡
Conclusion & Impact:Conclusion: The integration of entropy-based EEG features into the deep learning ensemble improves schizophrenia detection.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Şizofreni · EEG · Entropi tabanlı Özellik Haritaları

Abstract

Background/Aim: A complicated neuropsychiatric condition, schizophrenia is commonly investigated using one-dimensional EEG signals. In this work, a novel deep learning framework for automated schizophrenia detection is proposed, integrating an ensemble model based on ResNet50 with multi-entropy-based feature maps derived from 10-second EEG segments. Methods: Six entropy measures—approximate, bubble, fuzzy, permutation, sample, and spectral entropy—are computed to create two-dimensional EEG feature maps (EEG-FMs). A distinct ResNet50 model processes each EEG-FM, and soft voting is utilized for final predictions. The framework's effectiveness is evaluated using a leave-one-group-out cross-validation (LOGO-CV) method on two EEG datasets. Results: The ensemble framework exhibits high sensitivity and specificity, achieving average accuracies of 81.4% on Dataset 1 and 95.7% on Dataset 2. It evaluates the framework's performance across varied EEG distributions using a combined dataset and the Wilcoxon signed-rank test. The soft voting generally yields more balanced results than individual entropy-based models, although performance declines with increased dataset variability. An independent third EEG dataset (Dataset 3) is used to further assess the framework under differing conditions. Conclusion: The integration of entropy-based EEG features into the deep learning ensemble improves schizophrenia detection.

Özet

Karmaşık bir nöropsikiyatrik durum olan şizofreni, genellikle tek boyutlu EEG sinyalleri kullanılarak incelenir. Bu çalışmada, 10 saniyelik EEG segmentlerinden üretilen çoklu entropi tabanlı özellik haritalarıyla ResNet50 tabanlı bir topluluk modelini entegre eden otomatik şizofreni tespiti için yeni bir derin öğrenme çerçevesi önerilmiştir. İki boyutlu EEG özellik haritaları (EEG-FM) oluşturmak için altı entropi ölçüsü (yaklaşık, kabarcık, bulanık, permütasyon, örnek ve spektral entropi) hesaplanmıştır. Her EEG-FM ayrı bir ResNet50 modeli tarafından işlenmiş ve nihai tahminler için yumuşak oylama kullanılmıştır. Çerçevenin etkinliği, iki EEG veri kümesi üzerinde bir grup dışarı bırakma çapraz doğrulama (LOGO-CV) yöntemi kullanılarak değerlendirilmiştir. Topluluk çerçevesi, Veri Kümesi 1'de %81,4 ve Veri Kümesi 2'de %95,7 ortalama doğruluk oranlarına ulaşarak yüksek duyarlılık ve özgüllük sergilemiştir. Çerçevenin performansı, birleşik veri kümesi ve Wilcoxon işaretli sıralama testi kullanılarak çeşitli EEG dağılımları üzerinde değerlendirilmiştir. Performans veri kümesi değişkenliğinin artmasıyla düşse de, yumuşak oylama genel olarak bireysel entropi tabanlı modellerden daha dengeli sonuçlar vermiştir. Çerçeveyi farklı koşullar altında daha ayrıntılı olarak değerlendirmek için bağımsız bir üçüncü EEG veri kümesi (Veri Kümesi 3) kullanılmıştır. Entropi tabanlı EEG özelliklerinin derin öğrenme topluluğuna entegrasyonu, şizofreni tespitini iyileştirmiştir.

🔖

Cite This Article

Cura, Ö. K. (2026). Automated Schizophrenia Detection via Resnet50-based Ensemble Learning Using Multi-entropy EEG Feature Maps. Erciyes Üniversitesi Fen Bilimleri Enstitüsü Fen Bilimleri Dergisi, Cilt: 42 Sayı: 2. https://doi.org/10.65520/erciyesfen.1888892

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (33)

  1. Jangde, A. S., & Verma, G. K. 2026. EEG-Based Schizophrenia Classification Using Attention-Integrated Deep Convolutional Networks. Psychiatry Research: Neuroimaging, 112138.
  2. Krishnan, P. T., Raj, A. N. J., Balasubramanian, P., Chen, Y. 2020. Schizophrenia detection using Multivariate Empirical Mode Decomposition and entropy measures from multichannel EEG signal. Biocybernetics and Biomedical Engineering, 40(3), 1124-1139.
  3. Puri, D. V., Kachare, P. H., Al–Shourbaji, I., Jabbari, A., Kirner, R., Alameen, A. 2025. Design of efficient bi-orthogonal wavelets for EEG-based detection of Schizophrenia. Engineering Science and Technology, an International Journal, 68, 102090.
  4. Puri, D. V., Kachare, P. H., Sangle, S. B., Al-Shourbaji, I., Jabbari, A., Kirner, R. 2026. A hybrid dwarf mongoose and artificial ecosystem-based EEG channel optimization for Schizophrenia detection. Biomedical Signal Processing and Control, 112, 108513.
  5. Agarwal, M., Singhal, A. 2023. Fusion of pattern-based and statistical features for Schizophrenia detection from EEG signals. Medical Engineering & Physics, 112, 103949.
  6. Guo, Z., Wang, J., Jing, T., & Fu, L. 2024. Investigating the interpretability of schizophrenia EEG mechanism through a 3DCNN-based hidden layer features aggregation framework. Computer Methods and Programs in Biomedicine, 247, 108105.
  7. Das, K., Pachori, R. B. 2021. Schizophrenia detection technique using multivariate iterative filtering and multichannel EEG signals. Biomedical Signal Processing and Control, 67, 102525.
  8. Parija, S., Sahani, M., Rout, S. K. 2025. Robust broad learning system with parametrized variational mode decomposition for schizophrenia diagnosis. Engineering Applications of Artificial Intelligence, 158, 111294.
  9. Khare, S. K., Bajaj, V. 2022. A hybrid decision support system for automatic detection of Schizophrenia using EEG signals. Computers in biology and medicine, 141, 105028.
  10. Piryatinska, A., Darkhovsky, B., Kaplan, A. 2017. Binary classification of multichannel-EEG records based on the ϵ-complexity of continuous vector functions. Computer methods and programs in biomedicine, 152, 131-139.
  11. Kumar, T. S., Rajesh, K. N., Maheswari, S., Kanhangad, V., Acharya, U. R. 2023. Automated Schizophrenia detection using local descriptors with EEG signals. Engineering Applications of Artificial Intelligence, 117, 105602.
  12. Gosala, B., Kapgate, P. D., Jain, P., Chaurasia, R. N., Gupta, M. 2023. Wavelet transforms for feature engineering in EEG data processing: An application on Schizophrenia. Biomedical Signal Processing and Control, 85, 104811.
  13. Hassan, F., Hussain, S. F., Qaisar, S. M. 2023. Fusion of multivariate EEG signals for schizophrenia detection using CNN and machine learning techniques. Information Fusion, 92, 466-478.
  14. Lillo, E., Mora, M., Lucero, B. 2022. Automated diagnosis of schizophrenia using EEG microstates and Deep Convolutional Neural Network. Expert Systems with Applications, 209, 118236.
  15. Mudavath, U. K. N., Ahamed, S. R., Wong-Lin, K. 2025. Toward Interpretable Schizophrenia Detection from EEG Using Autoencoder and EfficientNet. medRxiv, 2025-05.
  16. Shen, M., Wen, P., Song, B., Li, Y. 2023. Automatic identification of schizophrenia based on EEG signals using dynamic functional connectivity analysis and 3D convolutional neural network. Computers in Biology and Medicine, 160, 107022.
  17. Bagherzadeh, S., Shahabi, M. S., & Shalbaf, A. 2022. Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal. Computers in Biology and Medicine, 146, 105570.
  18. Jahmunah, V., Oh, S. L., Rajinikanth, V., Ciaccio, E. J., Cheong, K. H., Arunkumar, N., & Acharya, U. R. 2019. Automated detection of schizophrenia using nonlinear signal processing methods. Artificial intelligence in medicine, 100, 101698.
  19. Sun, J., Cao, R., Zhou, M., Hussain, W., Wang, B., Xue, J., & Xiang, J. 2021. A hybrid deep neural network for the classification of schizophrenia using EEG Data. Scientific Reports, 11(1), 4706.
  20. Kim, K., Duc, N. T., Choi, M., & Lee, B. 2021. EEG microstate features for schizophrenia classification. PloS one, 16(5), e0251842.
  21. Nikhil Chandran, A., Sreekumar, K., & Subha, D. P. (2020). EEG-based automated detection of schizophrenia using long short-term memory (LSTM) network. In Advances in Machine Learning and Computational Intelligence: Proceedings of ICMLCI 2019 (pp. 229-236). Singapore: Springer Singapore.
  22. M.V. Lomonosov Moscow State University. EEG of healthy adolescents and adolescents with symptoms of schizophrenia http://brain.bio.msu.ru/eeg_schizophrenia.htm (Erişim Tarihi: 15.06.2025)
  23. Olejarczyk, E., & Jernajczyk, W. 2017. Graph-based analysis of brain connectivity in schizophrenia. PloS one, 12(11), e0188629.
  24. Fontaine, S. A. S., Amigó, J. M. 2025. Applications of entropy in data analysis and machine learning: A review. arXiv preprint arXiv:2503.02921.
  25. Shen, F., Dai, G., Lin, G., Zhang, J., Kong, W., & Zeng, H. 2020. EEG-based emotion recognition using 4D convolutional recurrent neural network. Cognitive Neurodynamics, 14(6), 815-828.
  26. Kim, S., Kim, T. S., & Lee, W. H. 2022. Accelerating 3D convolutional neural network with channel bottleneck module for EEG-based emotion recognition. Sensors, 22(18), 6813.
  27. Li, Y., Huang, J., Zhou, H., & Zhong, N. 2017. Human emotion recognition with electroencephalographic multidimensional features by hybrid deep neural networks. Applied Sciences, 7(10), 1060.
  28. Cura, O. K., Akan, A., & Atli, S. K. 2024. Detection of Attention Deficit Hyperactivity Disorder based on EEG feature maps and deep learning. Biocybernetics and Biomedical Engineering, 44(3), 450-460.
  29. Salehi, A. W., Khan, S., Gupta, G., Alabduallah, B. I., Almjally, A., Alsolai, H.,. & Mellit, A. 2023. A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope. Sustainability, 15(7), 5930.
  30. Reddy, J., Mundra, S., Mundra, A. 2024. Ensembling Deep Learning Models for Fake News Classification. Procedia Computer Science, 235, 2766-2774.
  31. Mosaku, S. K., Olateju, E. O., Ayodele, K. P., Akinsulore, A., Ajiboye, P. O., Oloniniyi, O. I.,. & Oyekunle, W. A. 2025. An open-access EEG dataset from indigenous African populations for schizophrenia research. Data in Brief, 111934.
  32. Salehi, A. W., Khan, S., Gupta, G., Alabduallah, B. I., Almjally, A., Alsolai, H.,. & Mellit, A. 2023. A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope. Sustainability, 15(7), 5930.
  33. Mosaku, S. K., Olateju, E. O., Ayodele, K. P., Akinsulore, A., Ajiboye, P. O., Oloniniyi, O. I.,. & Oyekunle, W. A. 2025. An open-access EEG dataset from indigenous African populations for schizophrenia research. Data in Brief, 111934.