A Hybrid CNN-HMM Framework for EEG-Based Classification of Anxiety, Chronic Stress, and Depression

Document Type : Original Article

Authors

1 Department of Electrical and Computer Engineering, Hamedan University of Technology, Hamedan, Iran

2 Department of Electrical and computer Engineering, Hamedan University of Technology, Hamedan, Iran.

10.22091/jdaid.2026.16603.1082

Abstract

One of the biggest challenges in clinical medicine is early and accurate diagnosis of brain disorders, especially functional and psychological disorders like stress, anxiety and depression. While conventional machine learning relies on hand engineered time-consuming features, deep learning models, despite showing superior accuracy, can be limited in clinic application by interpretability issues because of their “black-box” design. In this paper we present a novel hybrid approach for brain disorder detection and classification through the analysis of EEG signals. Our model combines the strength of automatic feature extraction of Convolutional Neural Network (CNN) and time sequence modelling & interpretation of Hidden Markov Model (HMM). A real clinical data from 200 individuals (healthy group, anxiety group, chronic stress group, depression group) is collected and used to train and evaluate our system. This local collected data is for the first time used to validate models. Our results show that the hybrid approach achieved 92.30 percent in 4-class classification, and showed superiority to other standard approaches. The interpretable nature by HMM transition matrices also make it more relevant to aid clinical decision-making.

Keywords

Main Subjects

References

Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., & Adeli, H. (2018). Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Computers in Biology and Medicine, 100, 270–278. https://doi.org/10.1016/j.compbiomed.2017.09.017
Afrakoti, I. E. P., Shouraki, S. B., Bayat, F. M., & Gholami, M. (2017). Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm. Fuzzy Sets and Systems, 307, 115–128. https://doi.org/10.1016/j.fss.2016.02.016
Al-Fahoum, A. S., & Al-Fraihat, A. A. (2014). Methods of EEG signal features extraction using linear analysis in frequency and Time-Frequency domains. ISRN Neuroscience, 2014, 1–7. https://doi.org/10.1155/2014/730218
Alhagry, S., Aly, A., & A, R. (2017). Emotion recognition based on EEG using LSTM recurrent neural network. International Journal of Advanced Computer Science and Applications, 8(10). https://doi.org/10.14569/ijacsa.2017.081046
American Psychiatric Association. (2013). Diagnostic and statistical manual of mental disorders (5th ed.). American Psychiatric Association Publishing. https://doi.org/10.1176/appi.books.9780890425596
Ay, B., Yildirim, O., Talo, M., Baloglu, U. B., Aydin, G., Puthankattil, S. D., & Acharya, U. R. (2019). Automated depression detection using deep representation and sequence learning with EEG signals. Journal of Medical Systems, 43(7), 205. https://doi.org/10.1007/s10916-019-1345-y
Bashivan, P., Rish, I., Yeasin, M., & Codella, N. (2016). Learning representations from EEG with deep recurrent-convolutional neural networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1511.06448
Cai, H., Qu, Z., Li, Z., Zhang, Y., Hu, X., & Hu, B. (2020). Feature-level fusion approaches based on multimodal EEG data for depression recognition. Information Fusion, 59, 127–138. https://doi.org/10.1016/j.inffus.2020.01.008
Chavan, P. A., & Desai, S. (2023). Effective epileptic seizure detection by classifying focal and non-focal EEG signals using human learning optimization-based hidden Markov model. Biomedical Signal Processing and Control, 83, 104682. https://doi.org/10.1016/j.bspc.2023.104682
Chavan, P. A., & Desai, S. (2024). An efficient epileptic seizure detection by classifying focal and non-focal EEG signals using optimized deep dual adaptive CNN-HMM classifier. Multimedia Tools and Applications, 83(19), 57347–57388. https://doi.org/10.1007/s11042-024-18560-x
Craik, A., He, Y., & Contreras-Vidal, J. L. (2019). Deep learning for electroencephalogram (EEG) classification tasks: A review. Journal of Neural Engineering, 16(3), 031001. https://doi.org/10.1088/1741-2552/ab0ab5
Fazli, M., & Alipour, S. (2026). Proportional representation in artificial intelligence: Clustering, alignment, and beyond. Journal of Data Analytics and Intelligent Decision-Making, 2(2), 31-47. https:// doi.org/10.22091/jdaid.2026.15981.1051
Fouladi, S., Safaei, A. A., Mammone, N., Ghaderi, F., & Ebadi, M. J. (2022). Efficient deep neural networks for classification of alzheimer’s disease and mild cognitive impairment from scalp EEG recordings. Cognitive Computation, 14(4), 1247–1268. https://doi.org/10.1007/s12559-022-10033-3
GBD 2019 Mental Disorders Collaborators (2022). Global, regional, and national burden of 12 mental disorders in 204 countries and territories, 1990-2019: A systematic analysis for the global burden of disease study 2019. The lancet. Psychiatry, 9(2), 137–150. https://doi.org/10.1016/S2215-0366(21)00395-3
Hadipour-Rokni, R., Asli-Ardeh, E. A., Jahanbakhshi, A., Paeen-Afrakoti, I. E., & Sabzi, S. (2023). Intelligent detection of citrus fruit pests using machine vision system and convolutional neural network through transfer learning technique. Computers in Biology and Medicine, 155, 106611. https://doi.org/10.1016/j.compbiomed.2023.106611
Hassan, M., & Kaabouch, N. (2024). Impact of feature selection techniques on the performance of machine learning models for depression detection using EEG data. Applied Sciences, 14(22), 10532. https://doi.org/10.3390/app142210532
Hyvärinen, A., & Oja, E. (2000). Independent component analysis: Algorithms and applications. Neural Networks, 13(4–5), 411–430. https://doi.org/10.1016/s0893-6080(00)00026-5
Kaya, Ş., & Tasci̇, B. (2023). Electroencephalogram-Based major depressive disorder classification using convolutional neural network and transfer learning. Turkish Journal of Science and Technology, 18(1), 207–214. https://doi.org/10.55525/tjst.1242881
Luo, X., Xu, Y., Yan, Z., Liu, W., Zhou, B., Li, G., & Zhu, Y. (2026). Multidimensional EEG features integration with feature selection strategy for precision diagnosis of depressive disorders. Frontiers in Psychiatry, 16, 1624997. https://doi.org/10.3389/fpsyt.2025.1624997
Molani Aghdam, M., & Ardeshir Larijani, I. (2026). Artificial neural network evaluating nonlinear evolutionary effect of cognitive and risk complexity in Ambidextrous strategy renewal. Journal of Data Analytics and Intelligent Decision-making, 2(2), 10-30. https://doi.org/10.22091/jdaid.2026.15918.1050
Mumtaz, W., Xia, L., Ali, S. S. A., Yasin, M. a. M., Hussain, M., & Malik, A. S. (2017). Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD). Biomedical Signal Processing and Control, 31, 108–115. https://doi.org/10.1016/j.bspc.2016.07.006
Newson, J. J., & Thiagarajan, T. C. (2019). EEG frequency bands in psychiatric disorders: A review of resting state studies. Frontiers in Human Neuroscience, 12, 521. https://doi.org/10.3389/fnhum.2018.00521
Phang, C., Noman, F., Hussain, H., Ting, C., & Ombao, H. (2020). A multi-domain connectome convolutional neural network for identifying schizophrenia from EEG connectivity patterns. IEEE Journal of Biomedical and Health Informatics, 24(5), 1333–1343. https://doi.org/10.1109/jbhi.2019.2941222
Rabiner, L. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. In Proceedings of the IEEE, 77(2), 257–286. https://doi.org/10.1109/5.18626
Rastegarnia, H., Bigdeli, M., & Morshedi, Z. (2026). The impact of artificial intelligence on medical science vision and labor market processes in medical occupational groups. Journal of Data Analytics and Intelligent Decision-making, 2(2), 48-66. https://doi.org/10.22091/jdaid.2026.15999.1057
Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T. H., & Faubert, J. (2019). Deep learning-based electroencephalography analysis: a systematic review. Journal of Neural Engineering, 16(5), 051001. https://doi.org/10.1088/1741-2552/ab260c
Saidutta, Y. M., Zou, J., & Fekri, F. (2018). Increasing the learning capacity of BCI systems via CNN-HMM models. Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, 2018, 1–4. https://doi.org/10.1109/EMBC.2018.8512714
Widmann, A., Schröger, E., & Maess, B. (2015). Digital filter design for electrophysiological data – a practical approach. Journal of Neuroscience Methods, 250, 34–46. https://doi.org/10.1016/j.jneumeth.2014.08.002
Yang, B., Zhu, X., Liu, Y., & Liu, H. (2021). A single-channel EEG based automatic sleep stage classification method leveraging deep one-dimensional convolutional neural network and hidden Markov model. Biomedical Signal Processing and Control, 68, 102581. https://doi.org/10.1016/j.bspc.2021.102581
Zhong, Q., Zhu, Y., Cai, D., Xiao, L., & Zhang, H. (2020). Electroencephalogram access for emotion recognition based on a deep hybrid network. Frontiers in Human Neuroscience, 14, 589001. https://doi.org/10.3389/fnhum.2020.589001
Journal of Data Analytics and Intelligent Decision-making

Articles in Press, Accepted Manuscript
Available Online from 30 September 2026

Files

Share

How to cite

Statistics