Our team pursues a number of research interests in computer science topic areas in addition to working on solution stacks for different domains as described in our Solutions section. These areas are:
Practical Machine Learning
Our research often involves applying state-of-the-art machine learning algorithms and methods in novel application contexts. Topics of interest include deep learning, video analytics, natural language processing, stream mining, hardware acceleration, explainability of machine learning outcomes and privacy-preserving machine learning techniques including privacy filtering of multimedia content.
Agent Modelling and Predictive Simulations
This includes simulation of actor behaviour over long time periods, agent behaviour modelling and general forms of predictive simulation methods.
Graph Data Models and Algorithms
Our interests in graphs for data modelling and data processing include graphs for semantic data representation, graphs for social network representation/analytics and efficient graph algorithms. We are also working on graph representations of real-world social environments, including small world networks and abnormally structured social networks such as criminal networks.
Our research interests in social systems focus on collective awareness platforms, collaboration platforms, digital social innovation, social robotics, decision support and decision-making systems involving groups of users and/or combinations of users and machines.
We are investigating techniques for information visualisation, in particular visualisation of statistical data and the visualisation of results and process information from research systems as described above.