ID 2334: Depression detection using multi-domain features from motion sensors and voice

Master’s Thesis

Depression is a common mental health disorder that often goes undetected or is diagnosed at a late stage, leading to long periods of suffering for individuals affected. Early identification allows for prompt intervention and treatment that can alleviate symptoms and improve overall mental well-being. Recent advancements in wearable technology have opened new possibilities for early and objective methods of depression detection.

Details

The goal of this thesis is to design a multi-domain system to detect depression by combining motion data from ear-worn IMUs and voice features. A study to collect a representative data set should be planned and conducted. All developed algorithms should be data-driven and the impact of individual features as potential markers of depression should be analyzed.

Start Date: Sommer/Fall 2023

Tasks

• Literature research
• Data recording
• Process data and extras relevant features for motion data and voice
• Design a system for the detection of depression based on motion and voice features
• Bring in your own ideas

Requirements

• Fluent German skills (required for data collection)
• You should have empathy and show a lot of initiative
• Strong programming skills in Python
• Advanced knowledge and some experience in Machine Learning
• Advanced knowledge in signal processing
• Bachelor’s degree in a related field of study

Supervisors

Ann-Kristin Seifer, M. Sc.

Researcher & PhD Candidate