About the Project
This project is part-funded by Renishaw Plc. It is expected that the successful applicant would undertake a placement at Renishaw to take advantage of technical expertise on the project context and data.
Overview of the Research:
Advances in hyperspectral imaging have resulted in high-quality images at fine spatial resolutions over hundreds of spectral wavelengths. Being able to efficiently extract information from these `data cubes' has the potential to provide scientific and industrial insight in several application areas, from medical diagnosis to geophysical mineral exploration.
Machine learning for hyperspectral imaging has shown promise for common analysis tasks, but using simplistic models without spatial information limits performance for analysis tasks such as classification, prediction and unmixing. In addition, current methods are computationally demanding, hindering uptake in practical scenarios. This project will develop new, efficient, spatially-aware machine learning methods for hyperspectral imaging based on modern mathematical optimisation techniques, and provide guidelines to practitioners on employing these tools in different data collection scenarios.
Example research questions we aim to address in this project are:
How can we harness spatial information to improve hyperspectral analysis tasks?
How can we take advantage of spectral correlations?
What are the computational bottlenecks in current ML methodology and how do we circumvent them?
Can we quantify uncertainty in the analysis outputs to support statistical decision-making?
It is anticipated that the mathematical methods developed in this project will involve aspects of machine learning, statistics and signal processing / data dimension reduction techniques.
Equality, Diversity and Inclusion:
We value a diverse research environment and aim to be an inclusive university, where difference is celebrated and respected. We welcome and encourage applications from under-represented groups.
If you have circumstances that you feel we should be aware of that have affected your educational attainment, then please feel free to tell us about it in your application form. The best way to do this is a short paragraph at the end of your personal statement.