Honours and Minor Thesis projects

This project will analyse a large corpus of mobile apps software artefacts including source code, and then use machine learning/rule-based techniques to develop an "app feature values miner" that analyses this corpus to identify potential human values in the app, potential app features that relate to these values, and relationships between features at different levels of granularity and the end-user human values.

In navigating complex public spaces such as museums, floor plan is a commonly used guidance tool.  This research aims to develop an adaptive version of these floor plans that caters challenged users special needs (i.e sight, motor, cognitive, other physical challenges, etc). You can develop an adaptive SVG floor plan and present using a UI developed with JS/ HTML /Django (Python for Web). 

Deep learning has achieved ground-breaking performance in many 2D vision tasks in the recent years. With more and more 3D data available such as those captured by Lidar, the next research trend is doing advanced perception on 3D data. The objective of this project is to study the state-of-the-art object detection techniques for 3D point clouds such as PointNet and PointVoxel.

Computational creativity is a subfield of AI that aims at studying theoretical and practical issues of creative behaviour by computational agents. An interesting aspect of creative behaviour is that it involves intrinsic factors such as motivations, intentions, struggle, etc. With this project we are interested in studying such intrinsic factors in a computational setting through the use of the Belief-Desire-Intentions (BDI) model. The project involves carrying out a survey of existing work on the use of the BDI model in AI in general and computational creativity in particular.

Within the faculty's Centre for Organisational and Community Informatics, the Archives and the Rights of the Child Research Program is investigating ways to re-imagine recordkeeping systems in support of responsive and accountable child-centred and family focused out-of-home care. Progressive child protection practice recognises the need, where possible, to support and strengthen parental engagement in the system in order to ensure the best interests of the child. 'No single strategy is of itself effective in protecting children.

Planning is the reasoning side of acting in Artificial Intelligence. Planning automates the selection and the organization of actions to reach desired states of the world as best as possible. For many real-world planning problems however, it is difficult to obtain a transition model that governs state evolution with complex dynamics.

The last two decades have witnessed a sharp rise in the amount of data available to business, government and science. Data visualisations play a crucial role in exploring and understanding this data. They provide an initial grasp of the data and allow the assessment of findings of data analytics techniques. This reliance on visualisations creates a severe accessibility issue
for blind people (by whom we mean people who cannot use graphics even when magnified).

Rational Verification is the problem of checking temporal logic properties of multi-agent systems modelled as multi-player games. Typically, in rational verification, we want to check whether a temporal logic formula is, or is not, satisfied on some or all equilibria of the game, assuming non-cooperative behaviour, for instance, as given by the Nash equilibria of the game.

XCC is a subfield of Explainable AI (XAI) that investigates the design of Computational Creativity (CC) systems that can communicate and explain their processes, decisions and ideas throughout the creative process in ways that are comprehensible to both humans and machines. With this project we will explore the subject of explanations in computational creativity within the frame of three CC systems from three different domains.

Reinforcement Learning (RL) systems can be represented as Markov Decision Processes (MDPs), which are graph-based models of probabilistic behaviour. Typically, a logic over MDPs predicates only about temporal or epistemic properties of such systems, but fails to express properties about the learning behaviour that such systems may represent. In this project, the aim is to investigate extensions of temporal and epistemic logics to be able to express learning properties of RL systems consisting of multiple agents.