A Hybrid Deep Learning Framework and Dwarf Mangoose Optimized Layers for an Effective Depression Classification
DOI:
https://doi.org/10.22399/ijcesen.1738Keywords:
Depression, Adapted Dilated Convolutional Network, Dwarf Mongoose Model, Hybrid Ensemble ModelAbstract
Depression is considered to be one of the dangerous diseases that affects physical state of human and even causes the fatal end to the patients. The depression leads to the anxiety disorders, bipolar disorders and at the same time may hit the person’s mind set to the suicide thoughts. Hence it is considerably demanding task to recognise the individuals with mental conditions. Traditionally, depression detection was done through patient’s interview and PHQ scores, but these traditional methods produce the accuracy which has very little effect on the diagnosis and treatment process. With the advent of machine (ML) and deep learning (DL) models, depression detection has reached its new dimensional path but still diagnosis performance and computational overhead remains to be real bottleneck for achieving its own strength of classification and early diagnosis. To solve this aforementioned problem, this research paper proposed hybrid ensemble of deep learning models and optimized training networks. Proposed framework consists of three components: first, adaptive dilated convolutional networks in which the model is trained with text and audio features, third is Bi-GRU Networks a finally the learning layers are optimized by DwarfMangoose Model to attain the better classification of depressions. The recommended model is examined and evaluated by utilizingDAIC-WOZ database and performance metrics such as accuracy, precision, recall, specificity and F1-score are measured and examined with the varied state-of-art learning procedures. The results demonstrate the recommended model has provided the optimal solution in detecting the depressions and produced the accuracy of 0.98, precision of 0.972, recall of 0.98, specificity of 0.98 and F1-score of 0.987 respectively. Experimental findings have proved that the proposed model has produced the promising results that improvises the clinical treatment and overcomes the fatal fears of the patients caused by the depression.
References
Ramirez-Cifuentes, D., Largeron, C., Tissier, J., Baeza-Yates, R., & Freire, A. (2021). Enhanced word embedding variations for the detection of substance abuse and mental health issues on social media writings. IEEE Access, 9, 130449–130471. https://doi.org/10.1109/ACCESS.2021.3112102
Lam, G., Dongyan, H., Lin, W., & City, S. (2021). Context; Multi-Modal (pp. 3946–3950)..
Rao, G., Zhang, Y., Zhang, L., Cong, Q., & Feng, Z. (2020). MGL-CNN: A hierarchical post representations model for identifying depressed individuals in online forums. IEEE Access, 8, 32395–32403. https://doi.org/10.1109/ACCESS.2020.2973737
Parapar, J., Martín Rodilla, P., Losada, D., & Crestani, F. (2023). Overview of eRisk 2023: Early risk prediction on the internet. In Experimental IR Meets Multilinguality, Multimodality, and Interaction: 14th International Conference of the CLEF Association, CLEF 2023. Springer International Publishing.
Zhang, Yipeng&Lyu, Hanjia& Liu, Yubao& Zhang, Xiyang& Wang, Yu &Luo, Jiebo. (2020). Monitoring Depression Trend on Twitter during the COVID-19 Pandemic: Observational Study (Preprint). JMIR Formative Research. 1. 10.2196/26769.
Ji, S., Zhang, T., Ansari, L., Fu, J., Tiwari, P., & Cambria, E. (2021). MentalBERT: Publicly available pretrained language models for mental healthcare. arXiv preprint arXiv:2110.15621.
Tian, H., et al. (2023). Deep learning for depression recognition from speech. Mobile Networks and Applications. https://doi.org/10.1007/s11036-022-02086-3
Bhuvaneswari, M., & Prabha, V. L. (2023). A deep learning approach for depression detection of social media data with hybrid feature selection and attention mechanism. Expert Systems, 40(9), Article e13371. https://doi.org/10.1111/exsy.13371
Kalpana, P., Narayana, P., Smitha, M., Dasari, K., Smerat, A., & Akram, M. (2025). Health-Fots: A latency-aware fog-based IoT environment and efficient monitoring of body’s vital parameters in smart healthcare environment. Journal of Intelligent Systems and Internet of Things, 15(1), 144-156. https://doi.org/10.54216/JISIoT.150112
Ramirez-Cifuentes, D., Largeron, C., Tissier, J., Baeza-Yates, R., & Freire, A. (2021). Enhanced word embedding variations for the detection of substance abuse and mental health issues on social media writings. IEEE Access, 9, 130449–130471. https://doi.org/10.1109/ACCESS.2021.3112102
Alghamdi, N. S., Hosni Mahmoud, H. A., Abraham, A., Alanazi, S. A., & García-Hernández, L. (2020). Predicting depression symptoms in an Arabic psychological forum. IEEE Access, 8, 57317–57334. https://doi.org/10.1109/ACCESS.2020.2981834
Alhanai, T., Ghassemi, M., & Glass, J. (2018). Detecting depression with audio/text sequence modeling of interviews. Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), 1716–1720. https://doi.org/10.21437/Interspeech.2018-2522
Lin, L., Chen, X., Shen, Y., & Zhang, L. (2020). Towards automatic depression detection: A BiLSTM/1D CNN-based model. Applied Sciences, 10(23), 1–20. https://doi.org/10.3390/app10238701
Babu, N. V., & Kanaga, E. G. M. (2022). Sentiment analysis in social media data for depression detection using artificial intelligence: A review. SN Computer Science, 3(1), 1–20. https://doi.org/10.1007/s42979-021-00958-1
Beniwal, R., & Saraswat, P. (2024). A hybrid BERT-CNN approach for depression detection on social media using multimodal data. The Computer Journal, 67(7), 2453–2472. https://doi.org/10.1093/comjnl/bxae018
Vara Sree Yenugutalaa, N. (2024). Depression detection using machine learning and deep learning techniques. International Journal of Research Publication and Reviews, 5(1), 25–33.
Tejaswini, V., Sathya Babu, K., & Sahoo, B. (2024). Depression detection from social media text analysis using natural language processing techniques and hybrid deep learning model. ACM Transactions on Asian and Low-Resource Language Information Processing, 23(1), Article 4. https://doi.org/10.1145/3569580
Vandana, Marriwala, N., & Chaudhary, D. (2023). A hybrid model for depression detection using deep learning. Measurement: Sensors, 25, 100587. https://doi.org/10.1016/j.measen.2022.100587
Khafaga, D. S., Auvdaiappan, M., Deepa, K., Abouhawwash, M., & Karim, F. K. (2023). Deep learning for depression detection using Twitter data. Intelligent Automation & Soft Computing, 36(2), 1301-1313. https://doi.org/10.32604/iasc.2023.033360
Amanat, A., Rizwan, M., Javed, A. R., Abdelhaq, M., Alsaqour, R., Pandya, S., & Uddin, M. (2022). Deep learning for depression detection from textual data. Electronics, 11(5), 676. https://doi.org/10.3390/electronics11050676
Kalpana, P., Kodati, S., Smitha, L., Sreekanth, D., Smerat, N., & Akram, A. (2025). Explainable AI-driven gait analysis using wearable IoT and human activity recognition. Journal of Intelligent Systems and Internet of Things, 15(2), 55–75. https://doi.org/10.54216/JISIoT.150205
Nadeem, A., Naveed, M., Islam Satti, M., Afzal, H., Ahmad, T., & Kim, K. I. (2022). Depression detection based on hybrid deep learning SSCL framework using self-attention mechanism: An application to social networking data. Sensors (Basel, Switzerland), 22(24), 9775. https://doi.org/10.3390/s22249775
Kalpana, P., Almusawi, M., Chanti, Y., Sunil Kumar, V., & Varaprasad Rao, M. (2024). A deep reinforcement learning-based task offloading framework for edge-cloud computing. 2024 International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India. https://doi.org/10.1109/ICICACS60521.2024.10498232
Kaggle. (2023). Kaggle: Your Machine Learning and Data Science Community. Retrieved July 3, 2023, from https://www.kaggle.com.
Chung, Junyoung & Gulcehre, Caglar & Cho, KyungHyun & Bengio, Y.. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
