Honours and Minor Thesis projects

Software testing is a crucial part of the software development process, ensuring that the developed software is of high quality and meets the requirements of the users. However, testing can be a complex and time-consuming task, especially when it comes to testing software in multiple languages. ChatGPT is trained in multiple languages, making it easier for understanding and detect bugs in multilingual software.

Product teams always need to conduct a user study with real and targeted users once the product is developed to test the usability and potential bugs in the products; however, this process is always time-consuming and costly. The team may need to find people of different backgrounds, train them, and then spend time with the users when they are doing the study. Moreover, they always need to conduct several rounds of usability tests every time they iterate the product based on the feedback from the previous study or because of the new requirements from product managers.

Jupyter notebooks have become a popular platform for data scientists to develop and test their code. However, as the number of code cells and markdown cells increase in a notebook, it can become challenging to maintain code quality and refactoring. While integrated development environments (IDEs) like PyCharm and VSCode have code assistants like Copilot, these features are not widely available in Jupyter notebooks.

Recently, large language models (LLM) gained popularity for their emerging powerful capabilities. For example, when given appropriate prompts, they could execute a task following instructions or demonstrations. In this project, we focus on generating chain-of-thought (CoT) prompts, using a codebank filled with basic sketches, to measure LLMs’ ability in automatic debugging.

IT Forensics is the art of extracting digital pieces of evidence also known as (aka) artifacts in a forensically sound manner, that is presentable to a court of law. In doing this it covers a range of conceptual levels, from high-level operating systems and computer theory down to computer networking. 
 

The specific objective(s) of this project is to look at an encrypted piece of data and distinguish what encryption algorithm is used/employed. This would benefit IT Forensics researchers/investigators attacking encrypted volumes, files, folders, etc.

Medical guidelines provide human experts with steps on conducting diagnosis. While existing online knowledge graphs such as Unified Medical Language System (UMLS) [1] provide a wide coverage of various biomedical entities, their coverage is limited in certain specific domains such as Ophthalmology. In this project we will build an automated system that convert the offline medical guidelines of Glaucoma [2] and Diabetic Retinopathy [3] to machine readable knowledge graphs.

Massive Open Online Courses (MOOCs), as one of the available options, are endowed with the mission to educate the world. MOOCs refer to online courses that are designed for an unlimited number of participants. In MOOCs, the learning materials are distributed over theWeb, which can be accessed by learners with internet connections anytime and anywhere. MOOCs are becoming increasingly popular. According to Class Central, by the end of 2022, there have been over hundreds of million learners enrolled in MOOCs in various MOOC platforms including edX, Coursera, etc.

Recently large-scale pre-trained language models, such as GPTs or BART have achieved successful performances in generating grammatically fluent text and capturing knowledge present in training corpus. However, it is pointed out that generating multi-sentence text (i.e., stories, narrations) with internal logical consistency is still far from being solved [1], with existing solutions merely scratching the surface in simple settings [2].

Linguistic phenomena have emerged and evolved over the span of thousands of years leading to many variations. Through this evolution, many linguistic structures and compositions have emerged or disappeared. In this project we will deploy an information-theoretic perspective to investigate the connections between linguistic phenomena (survival), and communication efficiency and emergence.

Since the 1990s, researchers have known that commonly-used public-key cryptosystems (such as RSA and Diffie-Hellman systems) could be potentially broken using efficient algorithms running on a special type of computer based on the principles of quantum mechanics, known as a quantum computer. Due to significant recent advances in quantum computing technology, this threat may become a practical reality in the coming years. To mitigate against this threat, new `quantum-safe’ (a.k.a.