Honours and Masters project

Description:

Magnetic Resonance Imaging (MRI) stands as a cornerstone in medical imaging, providing non-invasive, high-resolution images of the human body's internal structures.  Brain tumor segmentation from MRI scans is essential for precise diagnosis and treatment planning. MRI provides detailed views of brain structures and abnormalities, but challenges like image noise, contrast imperfections and tumor variations can make segmentation difficult.

Description:

The early detection of neurological abnormalities through Magnetic Resonance Imaging (MRI) is crucial in the medical field, potentially leading to timely interventions and better patient outcomes. However, the traditional diagnostic process is often time-consuming and subject to human error. This project seeks to improve this aspect by employing deep learning for anomaly detection in MRI scans, exclusively using images from healthy participants for model training [1].

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.

In our current day and age, there is an exponential growth in multimodal data, especially the transition of social media from text-based communications to video formats which can be observed with the rise of TikTok, Youtube, and Instagram Reels. This shift requires a shift in how we analyze multimodal data as we will have to move away from traditional text sentiment analysis such as TextCNN. Multimodal data presents us the opportunity to improve on text-based analysis given the new information that is coded in speech and visuals that can provide additional context for a sentiment.

Multimedia content such as audio, image, and video are stored and transported in compressed forms. Various standards are designed to encode the content at the highest possible level while minimizing distortion. Some commonly used compression standards include MP3 for audio, JPEG for still image, H.264/AVC for video. Despite the vast differences in signal characteristics, most compression standards have two things in common: transformed-quantized coefficients and scale factor (quantization table in JPEG and AVC). The coefficients are usually coded as a product of sign_bit and magnitude.