Dr Ian Kenny

Professional biography

My research interests include:

• Adaptive data driven models applied to real-world data to obtain useful predictions
• Developing innovative techniques to use heuristics to work on smaller datasets e.g. small climate science datasets were historical data does not represent recent climate change.
• Mobile and wearable devices to gather patient-centric health data which can be used to better inform clinical decisions for the patient.
• Exploring small world networks in data
• Computational human behaviour models
• Fairness in AI
• Machine Learning applications for Algorithmic Game Theory

I’m particularly interested in applying machine learning techniques to domains which are less accessible to brute force, large dataset, modeling, or where the dataset is niche. For example, where the there is a lack of data and the heuristic needs to become more adaptive to a changing or adaptive data environment. Examples of such an environment would be, climate change science where historical data does not necessarily represent current experience, making it difficult to make predictions from the historical data. Alternatively in the healthcare field where patient-centric approaches to healthcare require a more adaptive heuristic approach to deliver more personalised health information back to the clinician.

I’m also interested in the theoretical underpinnings of computation, in particular the implications of the No Free Lunch theorem to NP versus P

This is my ResearchGate profile

PhD Studentships

 Along with my colleague Dr Dhouha Kbaier, we are currently offering the following PhD studentships:

• Game-Theoretic Approaches to Environmental Risk with the University of Bath
• ADAPTIVE CONTINUOUS LEARNING
• EXPLORING MACHINE LEARNING AND COMPUTATIONAL TECHNIQUES TO INFORM RAPID ADAPTIVE CLIMATE CHANGE
• HOW DO YOU HAVE AN AI FORGET - RESPONSIBLY?

Please get in touch with either one of us, if you're interested. If you have an idea for a PhD proposal that falls within my interests, please also get in touch.

Previous Research Projects

ADMINS: An AI based bot within the Open University, called Taylor, to assist disabled students assess their additional study needs.

BBC Heat Data Project: In conjunction with BBC Spring Watch 2020 programme the BBC asked people about their experience of heat.

Mental Health Foundation/nQuire: Working with the Mental Health Foundation to develop the platform to make it more inclusive. A six-month project for young people with mental health problems as a way of demonstrating the benefits of democratising research. The project included holding six weeks of online workshops which enabled the participants to develop a research proposal and then carry out the research.

Climate Focused Virtual Study Group (VSG) hosted by the University of Bath – entitled Environmental Risk Post COVID-19

The VSG considered three topics:

• How to shift from carbon-intensive flights to other transport routes for tourists
• Wildfire Risk Management
• Game theoretic approaches to environmental risk.

Rapid Adaptive Climate Change Model Discovery:  The goal was to produce an iterative model which continues to inform the changing climate by means of the difference between the current model and the observed data within the specified time period. By doing this we anticipate achieving model which can produce forecasts without relying on large datasets collected over a longer period time. The Rapidly Adaptive Climate Change (RACC) model expected to be particularly useful given the increasing rapidity of climate change. As an initial step towards this goal, we intend to build a model which integrates the atmospheric data with the hydrospheric data with the intent of allowing the model to derive its own relationship between the heat cycle within the hydrosphere  and the effect on the global mean atmospheric temperature. Our RACC approach of building models at different layers preserves the abstraction needed to keep individual datasets distinct whilst at the same time relating them in a way which could be brought together to produce forecasts.

OSC Funded: Game-Theoretic Approaches to Environmental Risk​

• Applying game theory to analyse and mitigate environmental risks​
• Research Focus: Investigating game-theoretic models and strategies for addressing environmental risks and uncertainties​
• Collaboration: Collaborative project with the, Institute for Mathematical Innovation, University of Bath,  involving interdisciplinary research, collaboration with experts in environmental science and policy, and engagement with relevant interested parties, such as NGOs

Potential Research Collaborations

I'm currently looking to build relationships with NGOs or policy think tanks who are involved in influencing governmental decision-making on or public perceptions of climate change. Please get in touch with me if this is of interest.

Ask the Expert: why is the discussion about climate models important? - June 8 2022: A live stream broadcast for school children on YouTube and Facebook to discuss the importance of climate models, and how these models are derived. This included a description of the RACC model described above and a Q&A.

Available here

British Science Week -presentation of Taylor, AI technology - March 20-27 2023: Presentation and discussion of the technology behind Taylor, the AI bot for disability disclosure used by the OU, including Q&A.