An educational tool to teach about ethical decision making

Microworlds are a type of computer simulation which have proven to be very powerful tools with which to create effective learning experiences. For example a previous project developed one to teach about nati0nal waste management. Inspired the Trolley Problem,  and guidelines developed in a recent Interactive Digital Media M.Sc. dissertation, this project will involve developing … Read more

A microworld to teach about Electoral Voting Systems

Microworlds are a type of computer simulation which have proven to be very powerful tools with which to create effective learning experiences.  A previous final year project created 0ne to teach how different Electoral Voting systems work. This project will take the earlier one as inspiration and create one which includes the List System (used … Read more

A microworld to teach about the Irish budget

Microworlds are a type of computer simulation which have proven to be very powerful tools with which to create effective learning experiences. For example a previous project developed one to teach about nati0nal waste management. This project will involve developing a microworld in which the learner will act as the Minister for Finance and will … Read more

A GUI Music Composition Tool For Smartphones

Drumsteps was a reasonably successful Windows based tool, developed in-house, for teaching about music using a graphical interface. This project would involve developing, and evaluating, a smartphone based application inspired by the original program. The tool is aimed at Transition Year (TY) students in Irish secondary schools. The project will include an opportunity to have … Read more

Explainable AI (XAI) interfaces for learning

This project will be in the area of Explainable AI (XAI), and specifically building of explanations to support learning and user interfaces for presenting explanations to the end user (learner). The focus will be on the explanations rather than machine learning technology, although the student can use the project as an opportunity to explore these … Read more

Design and analysis of biodiversity experiments

ELIGIBILITY: This project is for a student taking the online MSc in Statistics and Data Science. In biodiversity experiments, typically the number, identity and proportions of species are manipulated across experimental units. Often additional treatments are of interest to test alongside species diversity treatments. The design of these experiments can be challenged by the multiple … Read more

A tool to assist in dissertation writing

CAWriter was a computer supported collaborative working tool designed to assist in the writing of research dissertations.  In particular it provided support for reference management, idea generation and drafting of dissertations. This project will involve looking at the design principles for the tool and implementing some of them using current technology and GenAI in particular. … Read more

Testing the relative importance of species diversity and cutting regime in agricultural grasslands

ELIGIBILITY: This project is for a student taking the MSc in Statistics and Sustainability. In agriculture, grasslands can play an important role in producing feed for animals and maintaining soil health in crop rotations. In recent years, mixing plant species with complementary traits have been proposed to reduce the quantity of synthetic fertiliser required to … Read more

Evaluating Prototype Explanations in Machine Learning

Prototype-based post-hoc explanations aim to make model predictions interpretable by presenting representative examples (prototypes) that illustrate how the model arrives at decisions. Their evaluation often relies on quantitative metrics such as fidelity (how closely prototypes approximate the model’s decision function), coverage (how much of the input space they represent), stability (whether explanations remain consistent under small perturbations), and diversity (ensuring prototypes capture … Read more

Fairness and Robustness in Risk Detection Models

Risk detection models (such as IBM’s Granite Guardian) are increasingly used to flag harmful prompts and responses in large language model pipelines. These systems are trained on human and synthetic data to identify risks across multiple dimensions, but their reliability and fairness are not guaranteed. They may over-flag certain groups, miss subtle harms, or be … Read more