Research projects in Information Technology

This project involves the automated generation of textual descriptions for audio content, such as spoken language, sound events, or music. This process typically employs deep learning techniques, such as recurrent neural networks, transformer models, and so on, to analyse audio signals and generate coherent captions. By training on large datasets that include both audio recordings and corresponding textual descriptions, these models learn to recognize patterns and contextual meanings within the audio.

This project focuses on identifying and distinguishing between authentic audio recordings and those that have been artificially generated or manipulated. As voice cloning technology advances, creating realistic audio deepfakes has become easier, raising concerns about misinformation and privacy. To combat this, this project aims to develop machine learning models to analyse audio features such as pitch, tone, cadence, and spectral characteristics. These techniques are implemented to detect subtle anomalies that may indicate manipulation, even in high-quality deepfake audio.

This project aims to develop a computer vision system capable of detecting and classifying domestic geographic landmarks in images and video content. By categorizing locations such as “childcare centre”, “school”, “shopping centre”, “hotel”, “bus stop”, “train station”, and so on, the system provides a reliable way to identify key landmarks in urban and suburban environments. Using advanced machine learning techniques, the model processes visual data to recognize distinct architectural features, signage, and contextual cues associated with each landmark type.

This project focuses on developing a gait detection system leveraging computer vision techniques to recognize individuals in security footage, even when their faces and skin are obscured. Criminals often cover their faces to avoid recognition, making traditional facial recognition unreliable. By analyzing key features of an individual’s gait, such as walking style, speed, and direction, this system provides a robust alternative for visual attribution.

This project focuses on simulating the organic growth of criminal communication networks by leveraging techniques such as Reinforcement Learning and Graph Theory. The goal is to curate a synthetic dataset that models the evolving structure and dynamics of illegal networks, taking into account factors like social connections, communication patterns, and resource allocation. By using graph-based models, the project aims to create realistic representations of how criminal groups form, expand, and operate under various conditions.

This project aims to develop foundation models for detecting anomalies in time series data. Anomalies, such as unusual patterns or unexpected events, can signal critical issues in systems like healthcare, finance, or cybersecurity. Current methods are often limited by scarcity of anomaly labels. By leveraging advanced machine learning techniques, this project seeks to create robust models that can generalize across diverse time series scenarios. The expected outcomes include improved accuracy in detecting anomalies.

In many branches of science (e.g., Artificial Intelligence, Engineering etc.), the modelling of the problem is done through the use of functions (e.g., f(x) = y). On a very high-level, we can think of Machine Learning as the problem of approximating function f from the pair of measurements (x,y), and Optimization as the problem of finding the value of input x that maximizes the output y given function f.

Overview

This project proposes a novel quantum-enhanced learning analytics framework for higher education, focusing on early identification of at-risk students and optimisation of intervention strategies using hybrid quantum-classical approaches. While current learning analytics systems rely on classical statistical and machine learning techniques, they often struggle to capture the complex, uncertain, and multi-dimensional nature of student learning behaviours.

Background and Motivation

Modern deep learning models have achieved remarkable success in computer vision and natural language processing. However, they typically produce overconfident predictions and lack reliable mechanisms to quantify uncertainty. This limitation becomes particularly problematic in high-stakes applications, such as healthcare diagnosis, autonomous systems, and scientific discovery.

Project Background & Motivation