KaydedilenlerDerginizi ekleyin

Dergiler / Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 32 Sayı: 6

Uyarlanabilir sinyal işleme ve makine öğrenmesi teknikleri ile EEG sinyalleri üzerinden majör depresif bozukluk analizi

Analysis of major depressive disorder with EEG signals using adaptive signal processing and machine learning techniques

Fatma Latifoğlu(ERCIYES UNIVERSITY)
Sabrına Turturova(ERCIYES UNIVERSITY)
Fırat Orhanbulucu(INONU UNIVERSITY)
Sayfa
1265–1273
Yayın Tarihi
2026-10-08
🏛️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)

Bulgular: Elde edilen sonuçlar, adaptif sinyal işleme yöntemlerinin, ham EEG analiziyle karşılaştırıldığında performansı anlamlı ölçüde artırdığını göstermektedir.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Giriş ve Amaç: Majör Depresif Bozukluk (MDB), bireylerin yaşam kalitesini olumsuz etkileyen önemli bir ruh sağlığı sorunudur.
📊
Temel Bulgular & Veri:Yöntem: Varyasyonel Mod Ayrıştırma (VMA), Ampirik Mod Ayrıştırma (AMA) ve Ampirik Dalgacık Dönüşümü (ADD) yöntemleri, frontal bölgeden elde edilen sınırlı sayıda EEG kanalına ait veriler kullanılarak 26 majör depresif bozukluk (MDB) hastası ve 29 sağlıklı kontrol deneğine uygulanmıştır.
💡
Sonuç & Katkı:Bulgular: Elde edilen sonuçlar, adaptif sinyal işleme yöntemlerinin, ham EEG analiziyle karşılaştırıldığında performansı anlamlı ölçüde artırdığını göstermektedir.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Elektroensefalografi · Majör depresif bozukluk · Varyasyonel mod ayrıştırma

Özet

Giriş ve Amaç: Majör Depresif Bozukluk (MDB), bireylerin yaşam kalitesini olumsuz etkileyen önemli bir ruh sağlığı sorunudur. Bu çalışmada, elektroensefalogram (EEG) sinyalleri aracılığıyla MDB’nin akıllı teşhisi için adaptif sinyal işleme ve makine öğrenmesi tabanlı bir yaklaşım geliştirilmiştir. Yöntem: Varyasyonel Mod Ayrıştırma (VMA), Ampirik Mod Ayrıştırma (AMA) ve Ampirik Dalgacık Dönüşümü (ADD) yöntemleri, frontal bölgeden elde edilen sınırlı sayıda EEG kanalına ait veriler kullanılarak 26 majör depresif bozukluk (MDB) hastası ve 29 sağlıklı kontrol deneğine uygulanmıştır. Bu sayede sinyaller alt frekans bantlarına ayrıştırılmıştır. Ham ve ayrıştırılmış EEG sinyallerinden frekans ve istatistiksel özellikler çıkarılmıştır. Özellik seçimi için LASSO algoritması kullanılmış ve dört farklı makine öğrenme modeli ile sınıflandırma işlemi gerçekleştirilmiştir. Bulgular: Elde edilen sonuçlar, adaptif sinyal işleme yöntemlerinin, ham EEG analiziyle karşılaştırıldığında performansı anlamlı ölçüde artırdığını göstermektedir. Özellikle VMA ve yapay sinir ağı (YSA) kombinasyonu en başarılı model olarak öne çıkmıştır. Bu model, diğer modellere kıyasla %96.66 doğruluk, %98.60 AUC ve %96.72 F1 skoru ile üstün sınıflandırma performansı sergilemiştir. Ayrıca, bu modelin karar mekanizması SHAP analizi kullanılarak ayrıntılı biçimde incelenmiş ve MDB tanısında klinik karar verme süreçlerine rehberlik edebilecek potansiyel biyobelirteçler belirlenmiştir. Sonuç: Bu kapsamda, önerilen çalışmada elde edilen bulgular, erken tanı süreçlerinin iyileştirilmesine ve otomatik tanı sistemlerinin geliştirilmesine önemli ölçüde katkı sağlamaktadır. Ayrıca, bu bulgular klinik karar destek mekanizmalarını güçlendirecek bilgisayar tabanlı tanı araçlarının geliştirilmesi için sağlam bir temel oluşturmaktadır.

Abstract

Background and Objective: Major Depressive Disorder (MDD) is a significant mental health issue that negatively affects individuals' quality of life. In this study, an adaptive signal processing and machine learning-based approach was developed for the intelligent diagnosis of MDD through electroencephalogram (EEG) signals. Methods: The Variational Mode Decomposition (VMD), Empirical Mode Decomposition (EMD) and Empirical Wavelet Transform (EWT) methods were applied to EEG data from 26 MDD patients and 29 healthy control subjects using a limited number of EEG channels obtained from the frontal region, thereby decomposing the signals into sub-frequency bands. Frequency and statistical features were extracted from the raw and decomposed EEG signals. The LASSO algorithm was used for feature selection, and classification was performed using four different machine learning models. Results: The results obtained show that adaptive signal processing methods significantly improve performance compared to raw EEG analysis. In particular, the VMD & artificial neural network (ANN) combination emerged as the most successful model. This model demonstrated superior classification performance compared to other models, with 96.66% accuracy, 98.60% AUC, and 96.72% F1 score values. Furthermore, the decision mechanism of this model was examined in detail using SHAP analysis, and potential biomarkers that could guide clinical decision-making processes in MDD diagnosis were identified. Conclusion: In this context, the findings obtained in the proposed study significantly contribute to improving early diagnosis processes and developing automated diagnosis systems, providing a solid foundation for the development of computer-based diagnostic tools that will strengthen clinical decision support mechanisms.

🔖

Bu Makaleye Atıf Yap

Latifoğlu, F., Turturova, S., Orhanbulucu, F. (2026). Uyarlanabilir sinyal işleme ve makine öğrenmesi teknikleri ile EEG sinyalleri üzerinden majör depresif bozukluk analizi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 32 Sayı: 6, 1265–1273. https://doi.org/10.65206/pajes.25438

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (41)

  1. Thulasi K, Balakrishnan S, Suan YJ, Qing YX, Malarvili MB, Murugesan RK, Devandran P. “Detecting mild depression from EEG signal in a non-clinical environment using machine learning technique”. IEEE 2nd National Biomedical Engineering Conference (NBEC), Kuala Lumpur, Malaysia, 27–28 September 2023.
  2. Rehman M, Saeed SMU, Khan S, Noorani SH, Rauf U. “EEG-Based Depression Detection: A Temporal Domain Feature-Centric Machine Learning Approach”. International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan, 18–20 December 2023.
  3. Gulenc NG, Ozturk M. “Diagnosis of Major Depressive Disorder from EEG Signals Using Empirical Wavelet Transform and Machine Learning Methods”. Medical Technologies Congress (TIPTEKNO), Antalya, Türkiye, 25–27 October 2024.
  4. Hoy D, March L, Brooks P, Blyth F, Woolf A, Bain C, Buchbinder R. “The global burden of low back pain: estimates from the Global Burden of Disease 2010 study”. Annals of the Rheumatic Diseases, 73(6), 968-974, 2014.
  5. Cai H, Yuan Z, Gao Y, Sun S, Li N, Tian F, Hu B. “A multi-modal open dataset for mental-disorder analysis”. Scientific Data, 9(1), 178, 2022.
  6. Duan L, Duan H, Qiao Y, Sha S, Qi S, Zhang X, Wang C. “Machine learning approaches for MDD detection and emotion decoding using EEG signals”. Frontiers in Human Neuroscience, 14, 284, 2020.
  7. Bachmann M, Päeske L, Kalev K, Aarma K, Lehtmets A, Ööpik P, Hinrikus H. “Methods for classifying depression in single channel EEG using linear and nonlinear signal analysis”. Computer Methods and Programs in Biomedicine, 155, 11-17, 2018.
  8. Balakrishnan S, Murugesan RK, Lim EL, Faisal A, Ashraf H. “Survey of deep learning and machine learning approaches for major depressive disorder detection using EEG data”. Journal of Electrical and Computer Engineering, 2025(1), 6277690, 2025.
  9. Durairaj M, Rani JR. “Mining and extracting emotional information from human-based EEG: an overview”. Productivity, 59(4), 343-351, 2019.
  10. Fang X, Klawohn J, De Sabatino A, Kundnani H, Ryan J, Yu W, Hajcak G. “Accurate classification of depression through optimized machine learning models on high-dimensional noisy data”. Biomedical Signal Processing and Control, 71, 103237, 2022.
  11. Yasin S, Hussain SA, Aslan S, Raza I, Muzammel M, Othmani A. “EEG based major depressive disorder and bipolar disorder detection using neural networks: a review”. Computer Methods and Programs in Biomedicine, 202, 106007, 2021.
  12. Noda Y, Sakaue K, Wada M, Takano M, Nakajima S. “Development of artificial intelligence for determining major depressive disorder based on resting-state EEG and single-pulse transcranial magnetic stimulation-evoked EEG indices”. Journal of Personalized Medicine, 14(1), 101, 2024.
  13. Mumtaz W, Xia L, Ali SSA, Yasin MAM, Hussain M, Malik AS. “Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD)”. Biomedical Signal Processing and Control, 31, 108-115, 2017.
  14. Greco C, Matarazzo O, Cordasco G, Vinciarelli A, Callejas Z, Esposito A. “Discriminative power of EEG-based biomarkers in major depressive disorder: a systematic review”. IEEE Access, 9, 112850-112870, 2021.
  15. Shen J, Zhang X, Wang G, Ding Z, Hu B. “An improved empirical mode decomposition of electroencephalogram signals for depression detection”. IEEE Transactions on Affective Computing, 13(1), 262-271, 2019.
  16. Kaur C, Bisht A, Singh P, Joshi G. “EEG signal denoising using hybrid approach of Variational Mode Decomposition and wavelets for depression”. Biomedical Signal Processing and Control, 65, 102337, 2021.
  17. Mumtaz W, Xia L, Mohd Yasin MA, Azhar Ali SS, Malik AS. “A wavelet-based technique to predict treatment outcome for major depressive disorder”. PloS One, 12(2), e0171409, 2017.
  18. Liu T, Luo Z, Huang J, Yan S. “A comparative study of four kinds of adaptive decomposition algorithms and their applications”. Sensors, 18(7), 2120, 2018.
  19. Shi Q, Liu A, Chen R, Shen J, Zhao Q, Hu B. “Depression detection using resting state three-channel EEG signal”. arXiv preprint, arXiv:2002.09175, 2020. https://arxiv.org/abs/2002.09175.
  20. Deslandes AC, De Moraes H, Pompeu FA, Ribeiro P, Cagy M, Capitão C, Laks J. “Electroencephalographic frontal asymmetry and depressive symptoms in the elderly”. Biological Psychology, 79(3), 317-322, 2008.
  21. American Psychiatric Association. Diagnostic and Statistical Manual of Mental Disorders: DSM-5. 5th ed. Washington, DC, USA, American Psychiatric Association, 2013.
  22. Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Liu HH. “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis”. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971), 903-995, 1998.
  23. Wang Y, Xu L, Qian H, Lin H, Zhang X. “Improved empirical wavelet transform combined with particle swarm optimization-support vector machine for EEG-based depression recognition”. EURASIP Journal on Advances in Signal Processing, 2024(1), 101, 2024.
  24. Gilles J. “Empirical wavelet transform”. IEEE Transactions on Signal Processing, 61(16), 3999-4010, 2013.
  25. Carvalho VR, Moraes MF, Braga AP, Mendes EM. “Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification”. Biomedical Signal Processing and Control, 62, 102073, 2020.
  26. Dragomiretskiy K, Zosso D. “Variational mode decomposition”. IEEE Transactions on Signal Processing, 62(3), 531-544, 2013.
  27. Latifoğlu F, Penekli S, Orhanbulucu F, Chowdhury ME. “A novel approach for Parkinson’s disease detection using Vold-Kalman order filtering and machine learning algorithms”. Neural Computing and Applications, 36(16), 9297-9311, 2024.
  28. Kang J, Kim Y, Yang J, Chung S, Hwang S, Oh U, Lee HW. “EEG feature engineering for machine learning-based CPAP titration optimization in obstructive sleep apnea”. International Journal of Advanced Smart Convergence, 12(3), 89-103, 2023.
  29. Peng H, Xia C, Wang Z, Zhu J, Zhang X, Sun S, Jianxiu L, Xiaoning H, Li X. “Multivariate pattern analysis of EEG-based functional connectivity: A study on the identification of depression”. Ieee Access, 7, 92630-92641, 2019.
  30. Mahato S, Paul S. “Detection of major depressive disorder using linear and non-linear features from EEG signals”. Microsystem Technologies, 25(3), 1065-1076, 2019.
  31. Muthukrishnan R, Rohini R. “LASSO: A feature selection technique in predictive modeling for machine learning”. 2016 IEEE International Conference on Advances in Computer Applications (ICACA), Coimbatore, India, 24–26 October 2016.
  32. Karakaş MF, Latifoğlu F. “Distinguishing Parkinson’s disease with GLCM features from the hankelization of EEG signals”. Diagnostics, 13(10), 1769, 2023.
  33. Hosseini MP, Hosseini A, Ahi K. “A review on machine learning for EEG signal processing in bioengineering”. IEEE Reviews in Biomedical Engineering, 14, 204-218, 2020.
  34. Akbari H, Sadiq MT, Siuly S, Li Y, Wen P. “Identification of normal and depression EEG signals in variational mode decomposition domain”. Health Information Science and Systems, 10, 24, 2022.
  35. Akbari H, Sadiq MT, Rehman AU. “Classification of normal and depressed EEG signals based on centered correntropy of rhythms in empirical wavelet transform domain”. Health Information Science and Systems, 9(1), 1-15, 2021.
  36. Ravi T, Taran SA. “A novel decomposition-based architecture for multilingual speech emotion recognition”. Neural Computing and Applications, 36(16), 9347–9359, 2024.
  37. Soman KP, Poornachandran P, Athira S, Harikumar K. “Recursive variational mode decomposition algorithm for real time power signal decomposition”. Procedia Technology, 21, 540–546, 2015.
  38. Yurtsever U, Evirgen H, Avunduk MC. “Detection of Colon Cancer Using K-means And Deep Learning Algorithms on Histopathological Images”. Pamukkale University Journal of Engineering Sciences, 31(5), 821-832, 2025.
  39. Xiong P, Lee SMY, Chan G. “Deep learning for detecting and locating myocardial infarction by electrocardiogram: A literature review”. Frontiers in cardiovascular medicine, 9, 860032, 2022.
  40. Bashir N, Narejo S, Naz B, Ismail F, Anjum MR, Butt A, Anwar S, Prasad R. “A machine learning framework for major depressive disorder (MDD) detection using non-invasive EEG signals”. Wireless personal communications, 140(1), 39-61, 2025.
  41. Uyulan C, Ergüzel TT, Unubol H, Cebi M, Sayar GH, Nezhad Asad M, Tarhan, N “Major depressive disorder classification based on different convolutional neural network models: Deep learning approach”. Clinical EEG and Neuroscience, 52(1), 38–51, 2020.