Student topics

Praeclarus is an open-source software framework that aims to facilitate data pre-processing for process mining. Process mining is specialised data mining focusing on process-data. It is of high interest to industry, with the market doubling every two years (e.g., increasing from $550M in 2020 to $1B in 2022). This market increase has meant that big companies like Microsoft, SAP, and IBM are acquiring process mining vendors such is Minit, Signavio, and myInvenio.Recent process mining surveys show that more than 60% …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Information Systems

Many of Australia's threatened species can only avoid extinction if we keep them on islands or behind fences, where foxes and cats can't kill them all. We call these places "safe havens".Some species can only exist in some safe havens. Maybe they need particular habitats, or particular temperatures, and these can't be found everywhere.Some pairs of species can't live together. Maybe one is a predator of another. Maybe they fight too much.So, we need to find a way to put …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre(s)

Centre for the Environment

Piezoelectricity, which translates to “pressure electricity”, is the phenomenon in which certain materials convert mechanical energy to electrical energy, and vice versa. Such materials are common-place and are used in a variety of applications including sensor, actuator, and energy harvesting technologies. The capabilities of such piezoelectric materials have not yet been fully realised. We plan to use computational structural optimisation to design new piezoelectric materials and components that may contribute to novel sensing technologies for robotics applications. Essentially, robots need …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

Advances in sequencing technologies over the past two decades have led to an explosion in the availability of genomic sequence data and an increasingly urgent need for scalable clustering and search facilities. One approach is to encode sequences as binary vectors in a high-dimensional space, simplifying the comparison and allowing it to be computed very rapidly using bit-level operations.Coupled with these ideas is the need to provide clustering methods and efficient indexing and lookup in response to search queries. One …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Computer Science

Research centre(s)

Centre for Data Science

Traditionally derived from unsustainable petrochemicals, astaxanthin (AX) can also be sustainably produced by microbial fermentation. The yeast Phaffia rhodozyma naturally produces AX as its main fermentation product through sugar assimilation.In previous studies, we improved the bioprocess to produce (upstream) AX in P. rhodozyma. This project aims to investigate the extraction, recovery, and formulation (downstream) of the AX produced in our improved AX production process.AX is a carotenoid pigment and potent antioxidant naturally occurring in some ocean animals such as salmonids …

Study level

Master of Philosophy

Faculty

Faculty of Science

School

School of Biology and Environmental Science

Research centre(s)

Centre for Agriculture and the Bioeconomy

Artificial intelligence (AI) technologies are automating service delivery in many sectors. Businesses have shown interest in using these technologies for delivering complex services in a way that meet the unique needs of customers. The technology gained more popularity particularly during Covid-19 outbreak, as it helped organisations to become more efficient in service delivery and increased service availability for customers / service applicants. However, gaining managers’ and users’ trust in these systems has always been a significant challenge. Particularly, managers and …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Information Systems

Existing machine learning-based intelligent systems are autonomous and opaque (often considered “black-box” systems), which has led to the lack of trust in AI adoption and, consequently, the gap between machine and human being.In 2018, the European Parliament adopted the General Data Protection Regulation (GDPR), which introduces a right of explanation for all human individuals to obtain “meaningful explanations of the logic involved” when a decision is made by automated systems. To this end, it is a compliance that an intelligent …

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Information Systems

Research centre(s)

Centre for Data Science

In the 21st Century, there is an abundance of data, often containing insights that could benefit a number of stakeholders. However, despite this opportunity, it is often the case that the data is sensitive and can not be released by organisations or government agencies due to privacy concerns. One possible solution to the above dilemma is to instead carefully construct a 'twin' data set that contains similar information (and ideally, the same insights) as the original data set, but without …

Study level

Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre(s)

Centre for Data Science

Extracellular vesicles (EVs) are membrane bound packages of information constantly being released by all living cells, including bacteria. There are many types and sizes of EVs. Each EV type contains its own distinctive cargo consisting of characteristic DNA, RNA, and proteins. We are just beginning to understand the many roles of EVs to maintain the health of the cell producing the EVs, and to communicate with other cell types that take up the EVs produced by neighbouring cells. Since EVs …

Study level

Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

In deep learning models, language models and word embedding methods have become popular to understand the context of text data. Popular language models such as BERT have limitations in terms of the token length. There exist some corpora that have longer text with an average of 1000 tokens. Additionally, these corpora are text-heavy and only include some images.In our prior works, we have developed several multi-modality models on social media datasets.

Study level

Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Computer Science

Research centre(s)

Centre for Data Science

In deep learning models, language models and word embedding methods have become popular to understand the context of text data. There exist many variants of these methods and have different limitations. This project will introduce you to the hot topic of language models and the fields of Natural Language Processing and Text Mining. 

Study level

Honours

Faculty

Faculty of Science

School

School of Computer Science

Research centre(s)

Centre for Data Science

Reaction-diffusion waves describe the progression in space of wildfires, species invasions, epidemic spread, and biological tissue growth. When diffusion is linear, these waves are known to advance at a rate that strongly depends on the curvature of the wave fronts. How nonlinear diffusion affects the curvature dependence of the progression rate of these wavefronts remains unknown.

Study level

PhD, Master of Philosophy, Honours

Faculty

Faculty of Science

School

School of Mathematical Sciences

Research centre(s)

Centre for Biomedical Technologies