Multiscale statistical classification

Type of project

Competition funded PhD projects

Supervisor(s)

Contact Dr Stuart Barber to discuss this project further informally.

Project description

Statistical classification of objects into groups can be either supervised (where we know which group some observations fall in to) or unsupervised (where we don't know what groups exist). Examples of supervised classification are discriminant analysis and classification trees; unsupervised classification includes cluster analysis.

These tools are widespread, especially with the advent of modern 'big data' applications such as genetic databases and market segmentation. Several of these methods are based on estimating the densities of underlying distributions; others use tree-like data structures. Both of these approaches can be thought of in a multiscale way, where we want to look at both local details and the 'big picture' simultaneously but separately. Useful tools for multiscale analysis are wavelets and the more general lifting algorithm.

This project will investigate the application of wavelets and lifting to statistical classification problems, identifying when and how these approaches can be used and assessing their strengths and weaknesses compared to more traditional methods.

Entry requirements

Applications are invited from candidates with or expecting a minimum of a UK upper second class honours degree (2:1), and/or a Master's degree in a relevant engineering or science degree such as (but not limited to) mathematics or statistics.

How to apply

Formal applications for research degree study should be made online through the university's website. Please state clearly in the research information section that the PhD you wish to be considered for is the 'Multiscale statistical classification’ as well as Dr Stuart Barber as your proposed supervisor.

If English is not your first language, you must provide evidence that you meet the University’s minimum English Language requirements.

We welcome scholarship applications from all suitably-qualified candidates, but UK black and minority ethnic (BME) researchers are currently under-represented in our Postgraduate Research community, and we would therefore particularly encourage applications from UK BME candidates.  All scholarships will be awarded on the basis of merit.