Data Analytics and Artificial Intelligence
The Data Analytics and Artificial Intelligence Research Group and develops advanced machine learning and optimisation methods, applying multi-agent systems to smart cities and digital health. The group's main focus is machine learning techniques and applications. Research in this group brings together a number of areas closely related to this core focus.
Machine learning is a branch of artificial intelligence that focuses on leveraging the large repositories of data to find patterns of interest. With the potential of transforming businesses and accelerating scientific discoveries, machine learning systems are set to play an increasingly important role in the foreseen future. The group brings a strong track record in conducting research developing novel machine learning methods, and adopting state-of-the-art techniques in a number of healthcare and smart city related applications.
Areas of Activity
- Ensemble learning
- Deep learning
- Data stream mining
- Time series analysis
- Mobile and embedded machine learning
- Text mining
Evolutionary computation is the set of nature-inspired methods used for global optimisation adopting techniques stemmed from the study of biological evolution. The group has a track record of applying these methods to a range of problems, and also a track record of enhancing a number of evolutionary methods applied to benchmark problems. Genetic algorithm and programming have been the focus of previous work conducted by the group. Current work using Particle Swarm Optimisation (PSO) in real-time machine learning is being experimented by the group.
Multi-agent systems are a set of techniques and models that are used to simulate the interaction of different typically intelligent entities, and to solve complex computational problems. The group has extensive expertise in using multi-agent systems and agent-based models in applications related to healthcare and smart cities.
Knowledge representation is a core artificial intelligence area that has attracted the attention of researchers for over 70 years, and remains an active area of research until today. Ontology is a structure that organises the knowledge-base for faster and intelligent retrieval. The group has expertise in both using ontology in information retrieval and e-learning systems, and automatic ontology engineering from text.
- Fatima Abdallah Agent-based Modelling to Simulate Energy Consumption in Residential Buildings
- Diana Haidar Opportunistic Machine Learning Methods for Insider Threat Detection
- Mona Demaidi Ontology-based Personalised Feedback in Virtual Learning Environments
- Hossein Ghomeshi An Evolutionary Approach to Seamless Adaptation to Concept Drifts in High Velocity Big Data
- Asim Majeed Modelling Mobile Edge Computing Systems for Mobile Crowdsensing Applications
- Amna Dridi A Machine Learning Approach to Analysis & Prediction of Scientific Trends
- Julian Hatwell White-boxing Ensemble Machine Learning Methods
- Richard Davies Edge Deep Learning Systems
- Oliver Batty Mapping Coordination Patterns and Quality of Movement to Mental and Emotional States
- Khadija Hanga A Personalised Recommender System to Support People with Diabetes
- Aliyu Sambo Leveraging Parallel Computing to automatically produce efficient Computer Code/Computational Models for Applications in Health Science and Biomedical Engineering
- Besher Alhalaby Designing lightweight machine learning algorithms for IoT solutions for energy efficient predictive building control
- Fouad, S., Randell, D., Galton, A., Mehanna, H., & Landini, G. (2017). Unsupervised morphological segmentation of tissue compartments in histopathological images. PloS one, 12(11), e0188717.
- Kovalchuk, Y., Stewart, R., Broadbent, M., Hubbard, T. J., & Dobson, R. J. (2017). Analysis of diagnoses extracted from electronic health records in a large mental health case register. PloS one, 12(2), e0171526.
- Lane, F., Azad, R. M. A. & Ryan, C. (2017). DICE: exploiting all bivariate dependencies in binary and multary search spaces. Memetic Computing, 1-11.
- Elyan, E., & Gaber, M. M. (2017). A genetic algorithm approach to optimising random forests applied to class engineered data. Information sciences, 384, 220-234.
- Adedoyin-Olowe, M., Gaber, M. M., Dancausa, C. M., Stahl, F., & Gomes, J. B. (2016). A rule dynamics approach to event detection in twitter with its application to sports and politics. Expert Systems with Applications, 55, 351-360.
- Abdallah, Z. S., Gaber, M. M., Srinivasan, B., & Krishnaswamy, S. (2015). Adaptive mobile activity recognition system with evolving data streams. Neurocomputing, 150, 304-317.
- Basurra, S. S., De Vos, M., Padget, J., Ji, Y., Lewis, T., & Armour, S. (2015). Energy efficient zone based routing protocol for MANETs. Ad Hoc Networks, 25, 16-37.