This group has been formed to promote both fundamental and applied research into intelligent pervasive data processing and modelling systems.

Our researchers and collaborators come from multidisciplinary academic areas, industry and international partners. Our work has been funded by bodies such as InnovateUK and the Newton Fund, with impact through KTPs and registered patents.

Data centred modelling methodology

Many social, political and economic structures can be understood through bottom up computational methodologies such as agent-based modelling for decomposing these systems into their various actors and components, modelling their characteristics, and interaction behaviours.

These models are based on both real and increasingly virtual world data sources which are fraught with uncertainties pertaining to noise, human decisions, knowledge perception, reliability, trust and levels of agreement between stakeholders. These sources of uncertainties can be managed and handled using fuzzy and probabilistic representation, aggregation and reasoning methodologies.

New developments in top down algorithms such deep learning approaches can be used to model real world and simulated processes to emulate complex patterns and correlations in dynamic and historical data that can also be used for empirical validation and estimation.

Advances in evolutionary algorithms can be developed for assessing and optimizing policies and strategies in terms of simulating their impact on aspects such as labour and employability modelling complex negotiation processes and improving the syntactic, semantic and search capabilities of evolutionary algorithms for handling multifaceted real-world problems.

These computational techniques can be applied to understand population mobility, economic growth, social behaviour, human sentiment, wellbeing, security and political risk, education, welfare, geopolitics and environmental concerns.


Flood monitoring and forecasting platform for urban development

We are collaborating with Interactive Coventry Ltd (IC) and Coventry University Institute of Future Transport and Cities on an Innovate UK and Newton Fund project developing intelligent urban flood assessment and warning systems with partners in Malaysia.

The system is based on patented deep learning techniques (GB2554038A) developed at IC.

Application of intelligent and pervasive systems for therapy and wellbeing assessment

This collaboration with researchers at the Instituto Tecnologico de Leon (ITL), Mexico will develop novel rule based fuzzy systems for cognitive stimulation therapy to assess cognitive impairment and emotional well-being of dementia patients, in association with the Instituto de la Memoria Fundación Alzheimer de León and Desarrollo Integral de la Familia, supported through CONACyT and TecNM/ITL, Mexico.

A second project is currently involved in developing novel pervasive data driven models for affective computing with respect to wellbeing monitoring using contextual data and environmental parameters.

Key outcomes

J. Navarro, F. Doctor, V. Zamudio, R. Iqbal, A. K. Sangaiah and C. Lino, “Fuzzy adaptive cognitive stimulation therapy generation for Alzheimer’s sufferers: Towards a pervasive dementia care monitoring platform”, Future Generation Computer Systems, Elsevier, vol. 88, November 2018, pp. 479-490.

Commercial development of Big Data and predictive analytics solutions

Commercial involvement with Interactive Coventry Ltd (IC) that is engaged in the development and application of biologically inspired artificial intelligence algorithms, data mining, big data analytics and human behaviour theories to provide customised solutions.

IC’s core technology is based on patented deep learning algorithms capable of processing various forms of input data (structured/unstructured), modelling relationships in the data (spatial /temporal patterns), visualising and predicting information to gain insight and meaning from the data.

Key outcomes

Iqbal, R., Maniak, T., Doctor. F & Karyotis. C. (2019) Fault Detection and Isolation in Industrial Processes Using Deep Learning Approaches, IEEE Transactions on Industrial Informatics, 15(5), pp. 3077 – 3084.

Maniak, T. J., Iqbal, R., & Doctor, F. (2019). IPC No. G05B 23/02 (2006.01). A Method for Monitoring the Operational State of a System. (Patent No. GB2554038A).