Classification of Depression Indication Based on Facial Expression Using MobileNetV2 and Support Vector
DOI:
https://doi.org/10.30871/jaic.v10i4.13495Keywords:
Depression, Facial Expression Recognition, MobileNetV2, Support Vector Machine, Deep LearningAbstract
Depression is a mental health disorder that can affect an individual's emotional condition, behavior, and quality of life. Facial expressions can represent a person's emotional state and therefore have the potential to be utilized as a visual source of information in the development of artificial intelligence-based classification systems. This study aims to develop a depression indication classification model based on facial expressions using MobileNetV2 as a feature extractor and Support Vector Machine (SVM) as a classifier. The FER2013 dataset was used and grouped into two classes, namely depression indication and non-depression indication based on predefined facial expression categories used in this study. After the labeling process, a total of 19,275 facial images were obtained, with 3,855 images used as testing data. The proposed method consists of image preprocessing, feature extraction using MobileNetV2, classification using SVM, threshold optimization, and model evaluation. Experimental results show that the proposed model achieved an accuracy of 79.69% with an AUC value of 88.62%. Threshold optimization produced an optimal threshold value of 0.44 and improved the accuracy to 80.34%. The precision, recall, and F1-score values indicate relatively balanced performance across both classes. The results demonstrate that the combination of MobileNetV2 and SVM can provide good classification performance on the FER2013 dataset grouped into depression indication and non-depression indication classes.
Downloads
References
[1] M. Squires et al., “Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment,” Dec. 01, 2023, Springer Science and Business Media Deutschland GmbH. doi: 10.1186/s40708-023-00188-6.
[2] N. K. Iyortsuun, S. H. Kim, M. Jhon, H. J. Yang, and S. Pant, “A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis,” Feb. 01, 2023, MDPI. doi: 10.3390/healthcare11030285.
[3] M.-M. Han et al., “Automatic recognition of depression based on audio and video: A review,” World J. Psychiatry, vol. 14, no. 2, pp. 225–233, Feb. 2024, doi: 10.5498/wjp.v14.i2.225.
[4] R. Guo, H. Guo, L. Wang, M. Chen, D. Yang, and B. Li, “Development and application of emotion recognition technology — a systematic literature review,” Dec. 01, 2024, BioMed Central Ltd. doi: 10.1186/s40359-024-01581-4.
[5] E. M. G. Younis, S. Mohsen, E. H. Houssein, and O. A. S. Ibrahim, “Machine learning for human emotion recognition: a comprehensive review,” Jun. 01, 2024, Springer Science and Business Media Deutschland GmbH. doi: 10.1007/s00521-024-09426-2.
[6] E. G. Dada, D. O. Oyewola, S. B. Joseph, O. Emebo, and O. O. Oluwagbemi, “Facial Emotion Recognition and Classification Using the Convolutional Neural Network-10 (CNN-10),” Applied Computational Intelligence and Soft Computing, vol. 2023, 2023, doi: 10.1155/2023/2457898.
[7] M. A. H. Akhand, S. Roy, N. Siddique, M. A. S. Kamal, and T. Shimamura, “Facial emotion recognition using transfer learning in the deep CNN,” Electronics (Switzerland), vol. 10, no. 9, May 2021, doi: 10.3390/electronics10091036.
[8] T. Kopalidis, V. Solachidis, N. Vretos, and P. Daras, “Advances in Facial Expression Recognition: A Survey of Methods, Benchmarks, Models, and Datasets,” Information (Switzerland), vol. 15, no. 3, Mar. 2024, doi: 10.3390/info15030135.
[9] Q. Zhu, H. Zhuang, M. Zhao, S. Xu, and R. Meng, “A study on expression recognition based on improved mobilenetV2 network,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-58736-x.
[10] H. M. Shahzad, S. M. Bhatti, A. Jaffar, S. Akram, M. Alhajlah, and A. Mahmood, “Hybrid Facial Emotion Recognition Using CNN-Based Features,” Applied Sciences (Switzerland), vol. 13, no. 9, May 2023, doi: 10.3390/app13095572.
[11] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, “An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review,” Information (Switzerland), vol. 15, no. 4, Apr. 2024, doi: 10.3390/info15040235.
[12] M. J. Adamu et al., “Efficient and Accurate Brain Tumor Classification Using Hybrid MobileNetV2–Support Vector Machine for Magnetic Resonance Imaging Diagnostics in Neoplasms,” Brain Sci., vol. 14, no. 12, Dec. 2024, doi: 10.3390/brainsci14121178.
[13] M. Azeez Joodi, M. Hadi Saleh, and D. Jasim Kadhim, “A New Proposed Hybrid Learning Approach with Features for Extraction of Image Classification,” Journal of Robotics, vol. 2023, 2023, doi: 10.1155/2023/9961421.
[14] W. Guo, H. Yang, Z. Liu, Y. Xu, and B. Hu, “Deep Neural Networks for Depression Recognition Based on 2D and 3D Facial Expressions Under Emotional Stimulus Tasks,” Front. Neurosci., vol. 15, Apr. 2021, doi: 10.3389/fnins.2021.609760.
[15] Y. Mahayossanunt, N. Nupairoj, S. Hemrungrojn, and P. Vateekul, “Explainable Depression Detection Based on Facial Expression Using LSTM on Attentional Intermediate Feature Fusion with Label Smoothing,” Sensors, vol. 23, no. 23, Dec. 2023, doi: 10.3390/s23239402.
[16] Z. Shangguan, Z. Liu, G. Li, Q. Chen, Z. Ding, and B. Hu, “Dual-Stream Multiple Instance Learning for Depression Detection With Facial Expression Videos,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 554–563, 2023, doi: 10.1109/TNSRE.2022.3204757.
[17] R. Wang et al., “FacialPulse: An Efficient RNN-based Depression Detection via Temporal Facial Landmarks,” in MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia, Association for Computing Machinery, Inc, Oct. 2024, pp. 311–320. doi: 10.1145/3664647.3681546.
[18] H. Arabian, T. Abdulbaki Alshirbaji, J. G. Chase, and K. Moeller, “Emotion Recognition beyond Pixels: Leveraging Facial Point Landmark Meshes,” Applied Sciences (Switzerland), vol. 14, no. 8, Apr. 2024, doi: 10.3390/app14083358.
[19] S. Alsubai, A. Alqahtani, A. Alanazi, M. Sha, and A. Gumaei, “Facial emotion recognition using deep quantum and advanced transfer learning mechanism,” Front. Comput. Neurosci., vol. 18, 2024, doi: 10.3389/fncom.2024.1435956.
[20] K. Mao, Y. Wu, and J. Chen, “A systematic review on automated clinical depression diagnosis,” Dec. 01, 2023, Nature Publishing Group. doi: 10.1038/s44184-023-00040-z.
[21] H. Kim et al., “Facial Expressions Track Depressive Symptoms in Old Age,” Sensors, vol. 23, no. 16, Aug. 2023, doi: 10.3390/s23167080.
[22] M. Monferrer, A. S. García, J. J. Ricarte, M. J. Montes, A. Fernández-Caballero, and P. Fernández-Sotos, “Facial emotion recognition in patients with depression compared to healthy controls when using human avatars,” Sci. Rep., vol. 13, no. 1, Dec. 2023, doi: 10.1038/s41598-023-31277-5.
[23] R. A. Elsheikh, M. A. Mohamed, A. M. Abou-Taleb, and M. M. Ata, “Improved facial emotion recognition model based on a novel deep convolutional structure,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-79167-8.
[24] A. W. Salehi et al., “A Study of CNN and Transfer Learning in Medical Imaging: Advantages, Challenges, Future Scope,” Apr. 01, 2023, MDPI. doi: 10.3390/su15075930.
[25] Y. Terhorst, L. B. Sander, D. D. Ebert, and H. Baumeister, “Optimizing the predictive power of depression screenings using machine learning,” Digit. Health, vol. 9, Jan. 2023, doi: 10.1177/20552076231194939.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Eswin Bakkar, Christy Atika Sari, Eko Hari Rachmawanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
