Data analytics and machine learning

We deal with the analysis and visualisation of complex data, development of machine learning algorithms and optimisation techniques.

The availability of large amounts of data - such as from databases, streams, or internet of things (IoT) devices - requires efficient methods for facilitating its analysis, categorisation, distribution, and visualisation.

The data analytics branch of our group addresses this challenge using ensemble and federated learning, approximation techniques, and optimised allocation of tasks in distributed computing environments.

The machine learning branch develops algorithms for the prediction and interpretation of diverse datasets ranging from medical images to video streams.

Aims

We aim to facilitate cooperation with research groups outside of the School of Computer Science.

Research

There are two branches to our group.

Data analytics

Our work in data analytics largely focuses on efficient large scale implementation of machine learning models across distributed environment, and effective deployment of machine learning systems across various platforms:

Partitioning machine learning algorithms across distributed environments (such as cloud and IoT) for both real-time (stream processing) and batch learning.
Ensemble and federated learning across distributed systems platforms.
Container frameworks (such as Docker, Kubernetes) and in-network capability (such as Network Function Virtualisation and MiddleBox approaches) to support machine learning.
Approximation techniques to trade off accuracy and execution time (convergence time).

Machine learning

Our expertise in machine learning involves fundamental research on new algorithm development and applied research on solving real data rich problems to benefit economy and society:

Development of novelty detection / anomaly detection algorithms.
Development of algorithms for instance selection and datasets shift detection.
Development of semi-supervised learning algorithms in medical imaging data applications (such as MRI, microscopy).
Development of a machine learning toolbox.
Explainable machine learning for interpreting model results.
Application of machine learning to problems in healthcare, service industries, security, etc.