TBA
Honours and Masters project
Displaying 281 - 287 of 287 honours projects.
Deep Self-Supervised Learning of Bayesian Network Structures through Graph and Data Masking
Bayesian Networks (BNs) are widely used for modelling uncertainty and causal relationships in domains such as healthcare, finance, cyber security and decision support. However, learning the optimal BN structure directly from observational data remains computationally challenging due to the super-exponential search space of possible graphs.
Designing Human-Centred Digital Twins for Reliable and Resilient Energy Networks
Future electricity networks are becoming increasingly complex due to the rapid growth of distributed energy resources (DERs), batteries, renewable generation and intelligent infrastructure. Although modern networks collect large volumes of operational, asset and maintenance data, this information is often distributed across multiple systems, making it difficult for engineers and operators to understand the true reliability and resilience of the network or identify emerging risks before failures occur.
Quantifying superintelligence - anticipating and possibly avoiding loss of control
Discussion of dangers of artificial intelligence (or artificial superintelligence, ASI) being an ambitious subordinate and ultimately taking over control from humans goes back at least as far as R J Solomonoff (1967). R J Solomonoff (1985) gives an approximate time-frame in which this might occur.
An Explainable Epidemiology System for Vaccine Safety and Proactive Care
This project aims to develop an explainable epidemiology system that combines generative AI, biostatistics, and epidemiological reasoning to support healthcare analysis and decision-making. The system will take structured health data as input, analyse it multimodally, and build a knowledge base that can be queried by epidemiologists and health researchers.
Bioinformatics analysis of spatial data in congenital heart diseases
Congenital heart disease affects 1 in 100 babies. Spatial gene expression patterns are critical to understand how the heart develops and what underlying genetic patterns are behind heart malformation. High-throughput spatial temporal data have been recently generated with spatial transcriptomics technologies. Capitalising on these rich datasets, we aim to build a custom analysis workflow in which the cells are profiled with precise spatial gene expression information. The student will provide fundamental contribution to of this project, by: