Artificial Intelligence research theme

The Artificial Intelligence theme carries out theoretical and applied research in a number of areas, including optimisation, machine learning, and human-interactive adaptive systems. We have a strong emphasis on biology-inspired techniques such as evolutionary computation, memetic and self-learning systems, and reinforcement learning.

Recent examples of how our research has been applied include ensuring the privacy of confidential data, medical device design, multi-agent modelling of domestic energy use, and  modelling/enhancing ‘customer journeys’ through legal/financial processes. We have extensive partnerships with a range of businesses from different sectors, as well as with statutory bodies holding confidential data including UK Office for National Statistics, and a range of national and international Trusted Research Environments. 

Professor Jim Smith

• Dr Mehmet Aydin
• Dr Steve Battle
• Professor Larry Bull
• Dr Nathan Duran
• Dr Marco Perez Hernandez
• Dr Jun Hong
• Dr Haixia Liu
• Dr Elias Pimenidis
• Professor Jim Smith
• Dr Michail-Antisthenis Tsompanas

SACRO (UKRI DARE Driver, 2023)

The SACRO project addresses a major bottleneck in the process of delivering valuable research insights from confidential data such as medical records held in Trusted Research Environments (TREs). This project will produce a consolidated framework with a rigorous statistical basis that provides guidance for TREs to agree consistent, standard processes to assist in quality assurance. It will design and implement a semi-automated system for checks on common research outputs, with increasing levels of support for other types of output, such as Machine Learning models. Working with a range of different types of TRE in different sectors (for example, health and socioeconomic data), organisations (including academia, government and the private sector) and the public will ensure wide applicability. This project is a collaboration with the Data Research, Access and Governance Network and the Mathematics and Statistics Research Group.

For further information, please contact Professor Jim Smith.

BioMeld (EU Horizon, 2022-2025)

The goal of project BioMeld is to design and manufacture a biohybrid catheter that would be small and flexible enough to gain access to hard-to-reach areas and deliver drugs on site. In order to achieve this, we will develop a modelling and simulation framework, test it and optimise it by developing a reconfigurable modular biohybrid machine (BHM catheter, and group the necessary manufacturing equipment into a biointelligent manufacturing cell (BIMC). This project is a collaboration with the Unconventional Computing Laboratory.

For further information, contact Dr Michail-Antisthenis Tsompanas.

Active Machine Learning for forecasting in the legal profession (Innovate UK, 2022-24)

The provision of legal services is in a period of dramatic and rapid transition, and Lyons Davidson has identified AI-based technology to streamline its delivery as a key strategic aim, enabling it to thrive by out-competing other players in both quality and costs of provision. This Knowledge Transfer Partnership project will address how to build and deploy systems that can learn predictive models from historical records and adapt rapidly in response to human expertise in a way that conventional Machine Learning (ML) approaches do not accommodate. The project will focus throughout on demonstrating that strict ethical considerations such as privacy-preservation apply to all parts of the resulting systems.

For further information, please contact Professor Jim Smith.