PhD in AI and Social Network Analysis for Early Prediction of Disease

Social network data now gives us unprecedented means to research human and animal behaviour, and recently has found much value in the early prediction of mental health disorders and degenerative disease. Human behaviour in the general environment is extremely complex, so there is much potential in investigating more structured animal environments where we have found evidence that social activity subtly changes even under mild (subclinical) infection (https://doi.org/10.3168/jds.2020-20047).

This PhD project is aimed at developing vision-based artificial intelligence(AI) techniques to build dynamic social networks to understand changes in social dynamics associated with early and chronic subclinical disease in cows. This studentship will combine and extend our AI methods (https://arxiv.org/abs/2006.09205 and https://doi.org/10.1016/j.compind.2018.02.016) and the underlying behavioural science to develop a system that tracks individuals and classifies their social interactions.

The studentship would suit either computational student interested in social network analysis, or someone with biosciences expertise who wishes to build up artificial intelligence skills – a tailored training package will be developed to suit. The student will be based 50%/50% at two leading, geographically close institutes – Bristol Robotics Laboratory at the University of West of England with Dr Mark Hansen and Professor Melvyn Smith, and Bristol Veterinary School at the University of Bristol, with data scientist Professor Andrew Dowsey, behavioural scientist Dr Suzanne Held, computer vision expert Dr Tilo Burghardt and Animal Welfare and Behaviour Group Lead Professor Mike Mendl.

Salary: Standard BBSRC stipend rate

Closing date: 06/12/2021

Further information can be found here.