Enhancing Mental Health Disorders Classification using Convolutional Variational Autoencoder

  • Sri Hasta Mulyani Universitas Respati Yogyakarta


This research investigates the application of Convolutional Variational Autoencoder (CVAE) for multi-class classification of mental health disorders. The study utilizes a diverse dataset comprising five classes: Normal, Anxiety, Depression, Loneliness, and Stress. The CVAE model effectively captures spatial dependencies and learns latent representations from the mental health disorder data. The classification results demonstrate high precision, recall, and F1 scores for all classes, indicating the model's robustness in distinguishing between different disorders accurately. The research contributes by leveraging the unique capabilities of CVAE, combining convolutional neural networks and variational autoencoders to enhance the accuracy and interpretability of the classification process. The findings highlight the potential of CVAE as a powerful tool for accurate and efficient mental health disorder classification. This research paves the way for further advancements in deep learning techniques, supporting improved diagnosis and personalized healthcare in mental health.


Download data is not yet available.
How to Cite
MULYANI, Sri Hasta. Enhancing Mental Health Disorders Classification using Convolutional Variational Autoencoder. International Journal of Informatics and Computation, [S.l.], v. 6, n. 1, p. 1-10, june 2024. ISSN 2714-5263. Available at: <https://ijicom.respati.ac.id/index.php/ijicom/article/view/65>. Date accessed: 13 july 2024. doi: https://doi.org/10.35842/ijicom.v6i1.65.