Richard Wilson, Ilkay Ulusoy (PI), Edwin Hancock

A joint project between METU, Turkey and York, our research aims to improve the modelling of human brain connectivity using probabilistic and nonlinear approaches to find causal connections between brain regions, and to improve the understanding of the relationship between these connections and diseases of the brain. 

Funding: £11,100 (Newton Mobility Grant, Royal Society)

Adam Katona, Ryan Spick, Victoria Hodge, Simon Demediuk, Florian Block, Anders Drachen, James Alfred Walker

Esports have become major international sports with hundreds of millions of spectators and they generate massive amounts of telemetry data.  In this project, we used deep learning network with shared weights which provides accurate death predictions within a five-second window. This model enables real-time micro-predictions of kills in Dota 2, one of the most played esports titles in the world, giving commentators and viewers time to move their attention to these key events.

Richard Wilson (PI) and Dimitris Kolovos

In partnership with Jigsaw Insurance Ltd and InnovateUK, we aim to develop a telematics offering which uses the driver's mobile phone to collect and analyse driving data in real time with the ability to detect accidents and dispatch emergency services.

Funding:  £241,202 (InnovateUK and Jigsaw Insurance)

Peter Nightingale (PI)

Decision problems such as planning, scheduling, logistics, and resource allocation are ubiquitious, and providing optimized timely solutions to these difficult problems often has substantial economic value. Our goal is to enable automatic solving of larger and more difficult decision problems than currently possible. To achieve this, we will exploit solver feedback loops -- a promising technique for improving the formulation of a decision problem, thus improving solver effectiveness, sometimes by orders of magnitude. 

Funding: £307,728 (EPSRC)

Dimitar Kazakov (PI)