Skip to main content
  • Home
  • Thesis Topics 
  • Artificial Intelligence Modelling of Harmful Solar Ultraviolet Index for Health-risk Mitigation

Research Thesis Topic

Artificial Intelligence Modelling of Harmful Solar Ultraviolet Index for Health-risk Mitigation


Topic ID
113

Thesis Topic/Title
Artificial Intelligence Modelling of Harmful Solar Ultraviolet Index for Health-risk Mitigation

Description

Australians (particularly Queenslanders), New Zealanders and Europeans facing significant damage from solar ultraviolet radiation effects on the human body. Implementing sun-protection to mitigate health risk of erythemally-effective solar radiation is a strategic initiative of the WHO Global Solar UV index (UVI). Exposure to UV contributes to malignant keratinocyte cancers. Smart forecasting models embedded in an outdoor decision-support system to simulate solar index (UVI) can predict UVI and help mitigate the risk of skin cancers. Such predictive models can inform the real-time sun-protection behaviour and act as a useful tool for public health advocacy.

In project, the student will learn new modelling skills, develop and apply artificial intelligence models to design high-performance systems to simulate solar ultraviolet index. Students will learn to integrate innovative mathematical tools, such as wavelets, Bayesian Average Models and Artificial Neural Network to generate artificial intelligence based predictive models. The models will utilise satellite-based data including ground measured products and reanalysis, yielding high performance in scientific models applied for mitigation of health-risk (e.g. skin cancer).

The purpose of this project is
• Develop neural network tools (e.g., artificial neural networks, extreme learning machine or support vector machines) and statistical models (ARIMA) for forecasting solar radiation at risky locations in Australia.
• Apply statistical techniques to investigate uncertainties in UV predictive models, particularly from the viewpoint of designing a real-time decision support system for health-risk mitigation.
• Evaluate model preciseness with statistical score metrics (and implement modern-day multi-resolution analysis techniques e.g. wavelet transformation and empirical mode decomposition).

The project will empower students to enhance the science in respect to forecasting capabilities of models related to measured conditions that provide real-time advice for public to mitigate the potential for solar UV-exposure-related disease. It suits students with a background in public health, engineering, solar radiation science, computing, climatology, meteorology, mathematics, statistics, environmental and atmospheric physics.

Student will learn MATLAB as an intensive data analysis and artificial intelligent modelling tool. The project is scalable for further research, such as to a Masters or a PhD program to advance research careers, acquire programming skills and model design with strong publication opportunity within Environmental Modelling and Simulation Research Group.


Principal Supervisor

Associate Supervisors

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
13/03/2017

Application Close Date
31/12/2019

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 MATLAB as an intensive data analysis and artificial intelligent modelling tool. The project is scalable for further research, such as to a Masters or a PhD program to advance research careers, acquire programming skills and model design with strong publication opportunity within Environmental Modelling and Simulation Research Group.




Back to List