The Computational Intelligence research group has a primary focus in the three related areas of evolutionary algorithms, data mining, probabilistic modelling, and parallel computing.
The work of the group involves a variety of approaches to problems falling under the general category of analysis, learning and optimisation.
The researchers in the group specialise in adaptive, intelligent computational approaches to data analytics and problem-solving.
Many real-world problems are complex, involving the consideration of vast amounts of data, the balancing of multiple objectives within challenging constraints and the shifting demands of a fast-moving world.
We research powerful and versatile computational approaches to discover key relationships in data, to intelligently search for solutions in complex scenarios, and to provide high performance computation that best adapts resources to demands.
The aims of the group are:
- to apply intelligent algorithms to solve learning and/or optimisation problems
- to develop improved or novel intelligent algorithms
- to contribute to the theoretical understanding of computational intelligence.
This research has application in areas such as:
Oil and Gas Industry
- data modelling for rig operations
- automated fault diagnosis and predictive maintenance of subsea control systems
Medical and Biological Informatics
- prediction of pathological staging in prostate cancer
- concurrent mining of neuro-oncological data
- chemotherapy treatment design and optimisation
- care visit scheduling
- agricultural bio-control
Engineering and Logistics Applications
- intelligent instrumentation for unmanned autonomous vehicles
- dynamic and heterogeneous truckscheduling optimisation
- computing in smart grids
Group members interests in field of:
Data modelling and inference using probabilistic graphical models such as Bayesian and Markov network models.
Theory and applications of a wide range of naturally inspired techniques for single- and multi-objective optimisation, including evolutionary algorithms, particle swarms, ant colonies and estimation of distribution algorithms.
Parallel and high performance computing.
- Inferential in Autonomous Systems
- Subsea Diagnostic Fault Analysis
- Dynamic and Heterogeneous Truck Scheduling Optimisation
- A Parallel Distributed Representation of Cellular Intelligence
- Novel Multi-objective Evolutionary Approaches to Optimisation
- Probabilistic Graphical Modelling for Medical Decision Making Under Uncertainty
- Bayesian Network Structure Learning from DataHigh Performance Scientific Modelling
- Parallel and Cloud Computing
- Rig Data Modelling using Bayesian Networks
- Bio-control for Mushroom Farming
- Cancer Chemotherapy Optimisation
- Domiciliary Care Scheduling
- Markov Networks in EDAs
- Modelling Patient Pathways for Prostate Cancer
- Using Machine Learning to Discover Diagnostic Sequence Motifs
- Closed-loop Machine Learning
- Efficient Biological Grammar Acquisition
Andrei's primary research interests lie in the field of Computational Intelligence (CI) - particularly, in the application of CI heuristics.
Inés is interested in the development and application of Artificial Intelligence (AI) techniques to complex problems.
Dr Mohamed Gaber is a Reader in The School of Computing
John is the Director of the IDEAS Research Institute.
Research into advanced data modelling for medical treatment optimisation.
Probabilistic modelling for industrial optimisation.
Researching Markov Networks and Metaheuristic Search.
Research Assistant on working on developing a Parallel Patterns for Adaptive Heterogeneous Multi-core/Many-core Systems, Known as Paraphrase- An EU Funded project under the category of Seventh Framework Programme (FP7)
- Horacio Gonzalez-Velez (National College of Ireland)
- Petr Kopyriulin (Samara State Technical University, Russia)
- Frederic Bouchet (Viper Subsea, Aberdeen)
Past Members and Collaborators
- Noura Al Moubayed (Glasgow University)
- Garry Brindley (Robert Gordon University)
- Deryck Brown• Sandy Brownlee (University of Stirling)
- Chris Bryant (University of Salford, Manchester)
- Daniel Fredouille
- Thierry Mamer (BT Research Centre, Ipswich)
- Siddhartha Shakya (BT Research Centre, Ipswich)
- Yanghui Wu