Skip to main content
  • Home
  • Thesis Topics 
  • Explainable Artificial Intelligence Predictive Models of Solar Ultraviolet UV Radiation and Cloud Cover Effects for Skin and Eye Health Risk Evaluation

Research Thesis Topic

Explainable Artificial Intelligence Predictive Models of Solar Ultraviolet UV Radiation and Cloud Cover Effects for Skin and Eye Health Risk Evaluation


Topic ID
113

Thesis Topic/Title
Explainable Artificial Intelligence Predictive Models of Solar Ultraviolet UV Radiation and Cloud Cover Effects for Skin and Eye Health Risk Evaluation

Description

Australians are at high risk of malignant keratinocyte cancers and eye disease due to solar ultraviolet (UV) radiation. Implementing sun-protection to mitigate health risk of erythemally-effective UV is a strategic initiative of World Health Organisation. UV forecasting apps used as a skin health decision support system to predict UV Index can mitigate the risk of skin cancer and eye disease.

Predictive models inform real-time sun-protection behaviour in humans and advocate for better public health risk reduction. In this project students learn about artificial intelligence (AI) models and learn to build explainable and interpretable AI systems (denoted as xAI models) that have the skill for real-time simulation of UV index. They will integrate innovative mathematical tools such as deep Taylor decomposition, layer wise relevance propagation (LRP), Local Interpretable Model-agnostic Explanations (LIME), sensitivity analysis and feature heat maps to analyse sky images. The xAI approach will offer the explanation of machine decisions and predictions to justify their reliability. The models will also provide greater interpretability, which often means we would better understand the mechanism underlying the algorithms when building an xAI model for UV forecasting. Some of the other well-known methods such as wavelet and Bayesian method will also be used using satellite data to yield high performance. Overall, this project will contribute to the mitigation of health-risk (e.g. skin cancer and eye disease minimisation efforts).

The project aims to enhance the science of solar UV index while developing forecasting capabilities for real-time advice to mitigate risk of solar UV-exposure-related disease. It will suit students with some background in health, solar science, computing, climatology, meteorology, mathematics, statistics, environmental or atmospheric physics. Student will learn Python, r or MATLAB programming, extensive data analysis and explainable AI modelling tool.

The research project is strongly centred on AI and Health Technologies.

This project is suitable for PhD, Research or Coursework Masters Thesis. It provides opportunity to publish in high quality Q1 journals. The research student will be part of the Advanced Data Analytics Research Group under Prof Ravinesh Deo.

For more details see https://eportfolio.usq.edu.au/view/view.php?id=116719.


Principal Supervisor


Research Affiliations
  • Centre for Health Sciences Research
  • Institute for Agriculture and the Environment
  • School of Agricultural, Computational and Environmental Sciences

Field of Research
  • Applied Mathematics
  • Artificial Intelligence and Image Processing
  • Atmospheric Sciences
  • Environmental Science and Management
  • Public Health and Health Services
  • Statistics


Application Open Date
19/10/2020

Application Close Date
31/12/2022

USQ Scholarship Applications

Other Scholarship Funding Details
http://www.usq.edu.au/scholarships/results?level=Research

Pre-approved for Ethics
No

Admission Requirements

Please review the admission requirements for the academic program associated with this Thesis Topic

Student will learn Python, r or MATLAB programming as an intensive data analysis and artificial intelligent modelling tool. The project is scalable for further research and model design with strong publication opportunity in Q1 journals.

To discuss this topic contact the Project Supervisor Associate Professor Ravinesh Deo or visit Advanced Data Analytics Research Group.

https://eportfolio.usq.edu.au/view/view.php?id=116719




Back to List