Publikations-Information
Investigating the Impact of Simulated Age-Related Macular Degeneration on Eye Movements in Virtual Reality (Using Machine Learning)
BT/MT
Status | open |
Student | N/A |
Advisor | Jesse Grootjen |
Professor | Prof. Dr. Sven Mayer |
Task
Description
Age-related macular degeneration (AMD) is an emerging visual impairment affecting millions globally [1]. In this thesis, we want you to investigate the challenges faced by individuals with AMD, particularly focusing on the differences in eye movements during simulated AMD experiences in virtual reality (VR) compared to normal or corrected vision. Building on prior research, we continue to develop a VR simulation in Unity, allowing precise control over parameters such as occlusion, visual acuity, contrast, color shifts, dark shadows, and glaring lights. Departing from previous studies, our analysis concentrates on understanding how these parameters influence task performance. Machine learning is applied to eye tracking and head movement data to discern variations between normal or corrected vision and impaired vision due to AMD.
In this thesis you aim to establish a correlation between eye movements and simulated AMD parameters. Utilising semi-constructed interviews and self-reporting, we identify when participants notice the simulated AMD, with a focus on subsequent data analysis to unveil differences in eye movements. In conclusion, visual impairments like AMD significantly impact daily tasks. One outcome could be to suggest that deviations in eye movements can be detected before users notice visual changes, offering potential as an early indicator for visual impairments.
You will
- Perform a literature review
- Modify an existing VR environment
- Implement an preprocessing pipeline for eye-tracking data
- Collect and analyze eye-tracking data using Machine Learning
- Summarize your findings in a thesis and present them to an audience
- (Optional) co-writing a research paper
You need
- Strong communication skills in English
- Good knowledge of Unity
- Good knowledge of Python libraries for scientific computing (e.g. Scipy, SK Learn, Tensorflow, PyTorch).
References
- [1] World report on vision. Geneva: World Health Organization; 2019. Licence: CC BY-NC-SA 3.0 IGO.