EEG-Based Depression Detection using Time-frequency Representation and Transfer Learning Techniques on MODMA Dataset
DOI:
https://doi.org/10.32350.umt-air.61.02Keywords:
Electroencephalography, Major depressive disorder, MODMA, Deep learning, Transfer learning, Machine learning, Signal processingAbstract
According to the World Health Organization (WHO), millions of people are affected by mental health issues, and depression is increasing rapidly. Present methods for depression detection include surveys, clinical interviews, and questionnaires that are very time-consuming and often not accurate. Many people do not express their feelings in interviews with doctors, or sometimes provide incorrect information. So, these techniques are not fully reliable. Using Electroencephalography (EEG) signals, the current study diagnosed depression in a better way since these signals record the brain activity directly. If the EEG shows some disturbance or unusual patterns in the brain activity, this means that the person is disturbed and facing depression. The MODMA dataset is a multimodal dataset that is widely used and medically tested for EEG signals. Many Machine Learning Algorithms (MLA’s), feature extraction techniques, and Deep Learning (DL) approaches have been applied to EEG for depression detection. However, the EEG signal is a 1-D signal that changes with respect to time, so it is sometimes used to detect depression. To solve this issue, researchers converted the EEG from a 1-D to a 2-D signal using time-frequency representation with transfer learning techniques. CNN-based pretrained models used for depression detection performed well on image data. Many studies showed that the combination of transfer learning with time-frequency representation is very effective and improves accuracy. This study primarily discussed transfer learning and time-frequency representation techniques for EEG-based depression detection. Finally, this technique would be used for other neurological disorders in the future.
Downloads
References
[1] H. Oh, J. Schiffman, J. Marsh, S. Zhou, A. Koyanagi, and J. DeVylder, “COVID-19 infection and psychotic experiences: Findings from the Healthy Minds Study 2020,” Biol. Psychiatry Glob. Open Sci., vol. 1, no. 4, pp. 310–316, Dec. 2021, doi: https://doi.org/10.1016/j.bpsgos.2021.05.005.
[2] E. A. Holmes, R. C. O’Connor, V. H. Perry, I. Tracey, S. Wessely, L. Arseneault, et al., “Multidisciplinary research priorities for the COVID-19 pandemic: A call for action for mental health science,” Lancet Psychiatry, vol. 7, no. 6, pp. 547–560, June 2020, doi: https://doi.org/10.1016/S2215-0366(20)30168-1.
[3] M. Taquet, S. Luciano, J. R. Geddes, and P. J. Harrison, “Bidirectional associations between COVID-19 and psychiatric disorder: Retrospective cohort studies of 62,354 COVID-19 cases in the USA,” Lancet Psychiatry, vol. 8, no. 2, pp. 130–140, Feb. 2021, doi: https://doi.org/10.1016/S2215-0366(20)30462-4.
[4] M. Taquet, J. R. Geddes, M. Husain, S. Luciano, and P. J. Harrison, “6-month neurological and psychiatric outcomes in 236,379 survivors of COVID-19: A retrospective cohort study using electronic health records,” Lancet Psychiatry, vol. 8, no. 5, pp. 416–427, May 2021, doi: https://doi.org/ 10.1016/S2215-0366(21)00084-5.
[5] C. H. Hodgman and E. R. McAnarney, “Adolescent depression and suicide: Rising problems,” Hosp. Pract. (Off. Ed.), vol. 27, no. 4, pp. 73–76, 81, 84–85, Apr. 1992, doi: https://doi.org /10.1080/21548331.1992.11705400.
[6] Y. Y. Wang, N. Z. Jiang, E. F. C. Cheung, H. W. Sun, and R. C. K. Chan, “Role of depression severity and impulsivity in the relationship between hopelessness and suicidal ideation in patients with major depressive disorder,” J. Affect. Disord., vol. 183, pp. 83–89, Sep. 2015, doi: https:// doi.org/10.1016/j.jad.2015.05.001.
[7] J. W. Murrough, D. V. Iosifescu, L. C. Chang, R. K. Al Jurdi, C. E. Green, A. M. Perez, et al., “Antidepressant efficacy of ketamine in treatment-resistant major depression: A two-site randomized controlled trial,” Am. J. Psychiatry, vol. 170, no. 10, pp. 1134–1142, Oct. 2013, doi: https://doi.org/ 10.1176/appi.ajp.2013.13030392.
[8] S. Bhat, U. R. Acharya, Y. Hagiwara, N. Dadmehr, and H. Adeli, “Parkinson’s disease: Cause factors, measurable indicators, and early diagnosis,” Comput. Biol. Med., vol. 102, pp. 234–241, Nov. 2018, doi: https://doi.org /10.1016/j.compbiomed.2018.09.008.
[9] S. Yasin, S. A. Hussain, S. Aslan, I. Raza, M. Muzammel, and A. Othmani, “EEG-based major depressive disorder and bipolar disorder detection using neural networks: A review,” Comput. Methods Programs Biomed., vol. 202, Art. no. 106007, Apr. 2021, doi: https://doi.org/10.1016/j.cmpb.2021.106007.
[10] S. D. Puthankattil and P. K. Joseph, “Analysis of EEG signals using wavelet entropy and approximate entropy: A case study on depression patients,” Int. J. Bioeng. Life Sci., vol. 8, no. 7, pp. 430–434, July 2014, doi: https://doi.org/10.5281/zenodo.1094265.
[11] J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural Netw., vol. 61, pp. 85–117, Jan. 2015, doi: https://doi.org/10.1016 /j.neunet.2014.09.003.
[12] H. Cai, Z. Yuan, Y. Gao, S. Sun, N. Li, F. Tian, et al., “A multi-modal open dataset for mental-disorder analysis,” Sci. Data, vol. 9, no. 1, Art. no. 178, Apr. 2022, doi: https:// doi.org/10.1038/s41597-022-01211-x.
[13] X. Li, R. La, Y. Wang, B. Hu, and X. Zhang, “A deep learning approach for mild depression recognition based on functional connectivity using electroencephalography,” Front. Neurosci., vol. 14, Art. no. 192, Apr. 2020, doi: https://doi.org/10. 3389/fnins.2020.00192.
[14] S. Sun, J. Li, H. Chen, T. Gong, X. Li, and B. Hu, “A study of resting-state EEG biomarkers for depression recognition,” arXiv, arXiv:2002.11039, Feb. 2020, doi: https://doi.org/10. 48550/arXiv.2002.11039.
[15] Q. Shi, A. Liu, R. Chen, J. Shen, Q. Zhao, and B. Hu, “Depression detection using resting-state three-channel EEG signal,” arXiv, arXiv:2002.09175, Feb. 2020, doi: https://doi.org/10.48550/arXiv.2002.09175.
[16] X.-W. Wang, D. Nie, and B.-L. Lu, “Emotional state classification from EEG data using machine learning approach,” Neurocomputing, vol. 129, pp. 94–106, 2014, doi: https://doi.org/ 10.1016/j.neucom.2013.06.046.
[17] X. Li, X. Zhang, J. Zhu, W. Mao, S. Sun, Z. Wang, C. Xia, and B. Hu, “Depression recognition using machine learning methods with different feature generation strategies,” Artif. Intell. Med., vol. 99, Art. no. 101696, Aug. 2019, doi: https://doi. org/10.1016/j.artmed.2019.07.004.
[18] K. Suzuki, T. Laohakangvalvit, and M. Sugaya, “Machine-learning-based depression detection model from electroencephalograph (EEG) data obtained by consumer-grade EEG device,” Brain Sci., vol. 14, no. 11, Art. no. 1107, Nov. 2024, doi: https:// doi.org/10.3390/brainsci14111107.
[19] X.-W. Song, D.-D. Yan, L.-L. Zhao, and L.-C. Yang, “LSDD-EEGNet: An efficient end-to-end framework for EEG-based depression detection,” Biomed. Signal Process. Control, vol. 75, Art. no. 103612, May 2022, doi: https://doi.org/10.1016/j.bspc.2022.103612.
[20] A. Seal, R. Bajpai, J. Agnihotri, A. Yazidi, E. Herrera-Viedma, and O. Krejcar, “DeprNet: A deep convolution neural network framework for detecting depression using EEG,” IEEE Trans. Instrum. Meas., vol. 70, Art. no. 2505413, pp. 1–13, Jan. 2021, doi: https://doi.org/10.1109/TIM. 2021.3053999.
[21] S. Bagherzadeh, M. R. Norouzi, A. Ghasri, P. T. Kouroshi, S. B. Hampa, F. Farokhshad, and A. Shalbaf, “Automated depression detection via cloud-based EEG analysis with transfer learning and synchrosqueezed wavelet transform,” Sci. Rep., vol. 15, no. 1, Art. no. 18008, May 2025, doi: https://doi.org/10.1038/s41598-025-02452-7.
[22] A. Sarkar, A. Singh, and R. Chakraborty, “A deep learning-based comparative study to track mental depression from EEG data,” Neurosci. Inform., vol. 2, no. 4, Art. no. 100039, Dec. 2022, doi: https:// doi.org/10.1016/j.neuri.2022.100039.
[23] W. Mumtaz and A. Qayyum, “A deep learning framework for automatic diagnosis of unipolar depression,” Int. J. Med. Inform., vol. 132, Art. no. 103983, Dec. 2019, doi: https://doi. org/10.1016/j.ijmedinf.2019.103983.
[24] Ş. Kaya and B. Tasci, “Electroencephalogram-based major depressive disorder classification using convolutional neural network and transfer learning,” Turk. J. Sci. Technol., vol. 18, no. 1, pp. 207–214, Mar. 2023, doi: https://doi.org/10.55525/tjst.1242881.
[25] X. Jia, J. Chen, K. Liu, Q. Wang, and J. He, “Multimodal depression detection based on an attention graph convolution and transformer,” Math. Biosci. Eng., vol. 22, no. 3, pp. 652–676, Feb. 2025, doi: https://doi.org/ 10.3934/mbe.2025024.
[26] W. Liu, K. Jia, and Z. Wang, “Graph-based EEG approach for depression prediction: Integrating time-frequency complexity and spatial topology,” Front. Neurosci., vol. 18, Art. no. 1367212, Apr. 2024, doi: https:// doi.org/10.3389/fnins.2024.1367212.
[27] J. Qiu, J. Liang, X. Fan, M. Zhang, and Z. He, “ELPG-DTFS: Prior-guided adaptive time-frequency graph neural network for EEG depression diagnosis,” arXiv, arXiv:2509.24860, Sep. 2025, doi: https://doi.org/10.48550/arXiv. 2509.24860.
[28] L.-X. Zhao, C.-Y. Xu, W.-Q. Li, B. Wang, R.-X. Wei, and Q.-H. Meng, “TF-MCL: Time–frequency fusion and multi-domain cross-loss for self-supervised depression detection,” Biomed. Phys. Eng. Express, vol. 12, no. 3, Art. no. 035026, May 2026, doi: https://doi.org/10.1088/2057-1976/ae6783.
[29] A. Rafiei, R. Zahedifar, C. Sitaula, and F. Marzbanrad, “Automated detection of major depressive disorder with EEG signals: A time series classification using deep learning,” IEEE Access, vol. 10, pp. 73804–73817, 2022, doi: https://doi.org/10.1109/ACCESS.2022.3190502.
[30] C. Sun, M. Guan, K. Duan, S. Gao, and Z. Chen, “A depression detection approach leveraging transfer learning with single-channel EEG,” J. Neural Eng., vol. 22, no. 3, Art. no. 036001, May 2025, doi: https://doi.org/ 10.1088/1741-2552/adcfc8.
[31] A. M. Almars, “Attention-based Bi-LSTM model for Arabic depression classification,” Comput. Mater. Contin., vol. 71, no. 2, pp. 3091–3106, 2022, doi: https://doi.org/10. 32604/cmc.2022.022609.
[32] B. Ay, O. Yildirim, M. Talo, U. B. Baloglu, G. Aydin, S. D. Puthankattil, and U. R. Acharya, “Automated depression detection using deep representation and sequence learning with EEG signals,” J. Med. Syst., vol. 43, no. 7, Art. no. 205, July 2019, doi: https://doi.org/10.1007/s10916-019-1345-y.
[33] J. Zhu, Z. Wang, T. Gong, S. Zeng, X. Li, B. Hu, J. Li, S. Sun, and L. Zhang, “An improved classification model for depression detection using EEG and eye-tracking data,” IEEE Trans. Nanobiosci., vol. 19, no. 3, pp. 527–537, July 2020, doi: https:// doi.org/10.1109/TNB.2020.2990690.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rida Fatima, Amad Ud Din, Amair Arsalan
This work is licensed under a Creative Commons Attribution 4.0 International License.
UMT-AIR follow an open-access publishing policy and full text of all published articles is available free, immediately upon publication of an issue. The journal’s contents are published and distributed under the terms of the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Thus, the work submitted to the journal implies that it is original, unpublished work of the authors (neither published previously nor accepted/under consideration for publication elsewhere). On acceptance of a manuscript for publication, a corresponding author on the behalf of all co-authors of the manuscript will sign and submit a completed the Copyright and Author Consent Form.
