Multimodal Depression Detection using Audio and Visual Features

Chani, Sachleen Singh (2024) Multimodal Depression Detection using Audio and Visual Features. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (766kB) | Preview

Abstract

Depression is one of the most common mental health disorders, yet the diagnosis for this is either not readily available or often misdiagnosed. Recent studies using machine learning techniques for depression detection have shown promising results but more research needs to be done in using multiple modalities of data for depression detection. To address this, this research outlines a BiLSTM with Attention layer model with two separate pathways, one for audio modality and the other for video modality. Further, a comparison is done with single modality models to evaluate the proposed model. The testing was done on the DAIC-WOZ dataset and the proposed model was able to achieve an accuracy of 0.934 and recall of 0.944.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning R Medicine > RA Public aspects of medicine > RA790 Mental Health
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	18 Jun 2025 11:00
Last Modified:	18 Jun 2025 11:00
URI:	https://norma.ncirl.ie/id/eprint/7904

Actions (login required)

View Item