Honours and Masters project

As the number of mental health patients increases, the demand for qualified counselors is on the rise. However, training/practice sessions with actual patients are often limited, let alone meeting a sufficient number of patients of different personalities. This project aims to use large language models to simulate therapy sessions under certain predefined circumstances. This project is co-supervised by a collaborator from the Psychology department in Jeffrey Cheah School of Medicine and Health Sciences.

Machine learning (ML) training and evaluation usually involve large-scale datasets and complicated computation. To process data efficiently, a promising solution is to outsource the processes to cloud platforms. However, traditional approaches of collecting users' data at cloud platforms are vulnerable to data breaches. Specifically, during the ML model training or inference service offering, the cloud server could learn the input data used to train the model, model structures, user queries and inference results, which may be sensitive to users or companies. 

This project is based on the paper "Academic Journals, Incentives, and the Quality of Peer Review: A Model", in which we analyse strategic interactions between scientists and science journals.  Our results shed light on how different objectives for journals shape the strategies that scientists adopt when aiming to publish their work. In this project, we aim to extend this model to include the influence of different environmental factors such as prestige, affiliations or career stage of the scientists.

The tennis tour is a series of tennis tournaments played globally over a calendar year, where professional tennis players compete for prize money and ranking points. The structure of the tennis tour is organised into different tiers for both men and women, including grand slam tournaments and ATP/WTA tour events. In this project we use stochastic processes to model and simulate the tour under different experimental rules.

This project will apply feature selection techniques for identifying features that can effectively predict the Logistics Performance Index (LPI), building upon our previously published work [1].

This project aims to analyse the comments of Twitter  on non-communicable diseases.  Students are expected to carry out Aspects Detection to identify the specific aspects discussed in the tweets e.g., causes, transmission and symptoms. Subsequently,  students are expected to conduct sentiment analysis utilizing tools like TextBlob or VADER, while also taking into account the importance of considering emojis to enhance classification accuracy. Students also need to provide solutions to the problem of ironic  tweets (e.g., seem positive but actually negative) and misinformation.

SCIPPlan is a mathematical optimisation based automated planner for domains with i) mixed (i.e., real and/or discrete valued) state and action spaces, ii) nonlinear state transitions that are functions of time, and iii) general reward functions. SCIPPlan iteratively i) finds violated constraints (i.e., zero-crossings) by simulating the state transitions, and ii) adds the violated constraints back to its underlying optimization model, until a valid plan is found. The purpose of this project is to improve the performance of SCIPPlan.

Cybersecurity researchers are contemplating how to best use the currently trending AI techniques to aid cybersecurity, beyond just for classification. 

The aim of this Honours project is to get the student to work with the supervisors on the latest AI techniques to adapt them over for cybersecurity, building first on baseline approaches for which code is available.

The student is free to discuss with the supervisor on any specific aspects of his/her choice and interest.

Cryptographic applications require a careful implementation to avoid side-channel attacks that reveal secret information to an attacker (e.g. via run-time measurements). In particular, for floating point arithmetic it is known that the timing of some basic arithmetic operations and functions on some CPUs depends on the input values [1], and thus the timing may leak secret information when the input contains secret values. Constant-time implementation tries to mitigate such run-time timing leakage on typical devices.

Following the success of the Human Genome Project, the entire scientific community witnessed a large data explosion in genomics, which was also aided by advances in molecular biology technologies such as next-generation sequencing. These high-throughput technologies enable comprehensive molecular profiling of cancer cell lines, including gene expression. Regardless of the use of gene-based assays, they provide abundant genomic information for identifying participating genes (biomarkers) that contribute to the chemoresistance process in cancer cells.