Visualising Risk in Elder Care introducing computational intelligence approaches to data analysis

Applications are invited for a DfE funded PhD studentship tenable in the Faculty of Arts, Humanities & Social Sciences, located at the Intelligent Systems Research Centre, Magee.

Project Summary:
A recent research project at the University on Risk Communication in Dementia (Stevenson & Taylor, in press; http://www.socsci.ulster.ac.uk/irss/risk.html) highlighted the potential for communicating about care risks through visual means rather than only words or numbers to convey likelihood or seriousness of possible harm. The community care risks being considered include causing a cooker fire, falling, medicines management, unwanted callers, abuse (including financial scams), having a car accident or wandering by people with dementia. Analysis of a situation and prediction of the level of associated harm is conducted by humans who assess the situation by gathering information and relating this to experience, research and theory to make a judgement (Taylor, 2017). However the relevant research data is very diverse, and difficult to access.

Computational intelligence seeks to develop models that can reason, understand or learn like a human (Gerlein, et al., 2016). The ability to spot patterns, adapt to new and unusual data, account for uncertainty, and to be robust to non-perfect and incomplete data are hallmarks of computational intelligence methods. These objectives dovetail neatly with the needs of a social work professional and the judgements they make. They want to spot trends in past data to provide information to guide managing the future; they want a model which can adapt to changing social conditions in a controlled, easy to understand fashion; and they want a model that will not completely fail due to unknown variables or potentially noisy data or outliers.
This project aims to introduce computational intelligence approaches to data analysis, to predict an associate harm level and hence provide decision support for the health and social care professional in communicating about risk (Taylor & Moorhead, in press). The algorithm will take as inputs the factors that a health and social care professional would consider important in such a situation and calculate a harm level with associated confidence. Existing and experiential data will form the ground truth data for algorithmic training and testing, and performance will be tested and validated against expert opinion. The model developed will be translated into a computerized visual format for ease of use.

Entrance Requirements:
Candidates should have ordinary UK residence to be eligible for both fees and maintenance. Non UK residents who hold ordinary EU residence may also apply but if successful will receive fees only. All applicants should hold a first or upper second class honours degree in computer science or psychology or a cognate area. The role will require knowledge and skills in quantitative data analysis and computer programming, and an interest in health and social care services. Applications will be considered on a competitive basis with regard to the candidate’s qualifications, skills experience and interests. Successful candidates will enrol as of 1 October 2017, on a full-time programme of research studies leading to the award of the degree of Doctor of Philosophy.
The studentship will comprise fees together with an annual stipend of £14,553 and will be awarded for a period of up to three years subject to satisfactory progress.

If you wish to discuss your proposal or receive advice on this project please contact:-

Supervisors:
Prof Brian Taylor, [Email Address Removed] Professor of Social Work, School of Social Sciences
Prof Sonya Coleman, [Email Address Removed] Professor of Vision Systems, School of Computing and Intelligent Systems
Dr Dermot Kerr, [Email Address Removed] Lecturer in Computer Science, School of Computing and Intelligent Systems
Dr Anne Moorhead, [Email Address Removed] Lecturer in Health Communication, School of Communication

External Collaborator:
Dr Michelle McDowell, Research Scientist, Harding Centre for Risk Literacy at the Max Planck Institute for Human Development, Berlin

Procedure
For more information on applying go to ulster.ac.uk/research
Apply online ulster.ac.uk/applyonline
The closing date for receipt of completed applications is Wednesday 3 May 2017
Interviews will be held in May 2017.