QUT offers a diverse range of student topics for Honours, Masters and PhD study. Search to find a topic that interests you or propose your own research topic to a prospective QUT supervisor. You may also ask a prospective supervisor to help you identify or refine a research topic.
Found 48 matching student topics
Displaying 37–48 of 48 results
Exploring green infrastructure optimisation for climate change adaptation and mitigation
Green infrastructure refers to public and private green spaces in cities that provide water cycle benefits. These green spaces range in the range from single trees on city streets to urban parks, and waterway walkways. Some are natural, such as the remains of native plants, while others are more geometric, for example green roofs and green walls. Green infrastructure can increase the sustainability and vitality of cities through benefits such as greening and cooling, water quality, and managing hotter weather. …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Engineering
- School
- School of Architecture and Built Environment
Combining solar and vibration energy harvesting for rainfall prediction
Rainfall prediction plays a crucial role in various sectors such as agriculture, water resource management, and disaster preparedness. Traditional prediction methods often rely on complex meteorological models and expensive equipment. However, advancements in energy harvesting technology offer the opportunity to develop low-cost and sustainable solutions for rainfall prediction.This project proposes to leverage solar and vibration energy harvesting for rainfall prediction. Combined measurements from both solar and vibration energy harvesting can provide comprehensive data for real-time monitoring of cloud coverage and …
- Study level
- Honours
- School
- School of Information Systems
Artificial intelligence (AI) to balance fluctuations of intermittent renewable energy sources
Artificial intelligence (AI) can play a significant role in analyzing and predicting energy consumption and production patterns from renewable sources such as solar and wind (Lyu & Liu 2021). This is particularly important due to the key challenge of intermittency, where major renewable sources for electricity, such as solar and wind, are subject to the inconsistencies of the weather (Watson et al., 2022).In this project, we investigate how AI and machine learning algorithms can optimize smart grids and other components …
- Study level
- PhD, Master of Philosophy, Honours
- School
- School of Information Systems
- Research centre(s)
- Centre for Data Science
Advanced numerical modeling to study dust deposition mechanisms on photovoltaic panels for the agrivoltaic industry.
The increase in global energy demand necessitates further advancement in photovoltaic (PV) systems. Advancements in PVs could potentially play a role to help meet the Paris Agreement of limiting global temperature increase to below 2 degrees Celsius. In conjunction with the rising demand for clean energy production, the global agricultural industry needs to keep pace with rising food demand which is expected to increase by 50% by 2050 to feed over a projected 10 billion people. The scarcity of fertile …
- Study level
- PhD, Honours
- School
- School of Mechanical, Medical and Process Engineering
Quantum machine learning
Quantum machine learning is the integration of quantum algorithms within machine learning programs with great potential to solve complex problems. For instance, Google’s Sycamore processor (61) performs in 200 seconds a task that would require 10,000 years using a classical computer.
- Study level
- PhD
- School
- School of Electrical Engineering and Robotics
Novel algorithms for microbiome data
Metagenomics data is complex, high-volume data and keeps evolving, requiring novel computational method development as the wetlab approaches changes and databases grow. Thus, novel computational methods are required to take advantage of them.There are several potential projects under this topic, including:using deep learning to improve metagenomics assemblydeveloping better tools to analyse the presence of resistance genes in metagenomics datadeveloping approaches for estimating the quality of genomes from novel generation sequencespredicting the function of small sequences using more than just sequence.Interested …
- Study level
- PhD, Master of Philosophy, Honours
- School
- School of Biomedical Sciences
- Research centre(s)
-
Centre for Microbiome Research
Analysis of professional squash matches
This project concerns computer vision and statistical analysis of performance in professional level matches in the game of squash.The goal is to use computer vision and existing systems to capture and analyse patterns of play, allowing coaches and professional players to develop strategies to improve performance, to counter particular types of play and even to tailor game plans to attack individual opponents.
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Science
- School
- School of Computer Science
- Research centre(s)
- Centre for Data Science
Identifying Indigenous contributions to knowledge
The Australian Census collects data every ten years to reflect who we are as a nation. But the data collected by the Census only tells part of our story.Indigenous people lived in Australia for thousands of years before the arrival of European settlers, accumulating a wealth of knowledge about Australia's land, climate, flora and fauna. Researchers have only begun tapping this knowledge as the basis for modern scientific research.This project will combine machine learning and text-analytics tools to develop a …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Science
- School
- School of Mathematical Sciences
- Research centre(s)
- Centre for Data Science
Development of a machine learning algorithm for high throughput cell response data in drug therapy
High-throughput screening assays are essential for accelerating drug discovery, but current assays often rely on endpoint measurements that do not capture the dynamic response of cells to drug treatment. Machine learning algorithms (MLAs) have the potential to enable real-time, high-throughput monitoring of cell response to drug treatment by analyzing complex datasets generated by multiplexed live-cell assays. This research project aims to develop an MLA for enabling high throughput cell response data in drug treatment. The project will involve three main …
- Study level
- Honours
- School
- School of Computer Science
- Research centre(s)
- Centre for Biomedical Technologies
Centre for Biomedical Technologies
Physics-informed reinforcement learning for complex environments, using graph neural networks
Neglecting to incorporate physics information into world models for reinforcement learning leads to reduced adaptability to dynamic and complex environments and overall learning outcomes.In this project, we endeavour to develop and implement learnable models in reinforcement learning (RL) based on graph neural networks (GNNs). These models will integrate object and relation-centric representations to enable accurate predictions, strong generalization, and system identification in complex, dynamical systems. Additionally, we will focus on leveraging extensive world knowledge or physics information to refine representations …
- Study level
- PhD, Master of Philosophy, Honours
- School
- School of Electrical Engineering and Robotics
Predicting good sleep using computer science: Can we use machine learning to find out 'what's the best bed?'
In the Westernised world a person typically spends one third of their life in bed, with more time spent sleeping in a bed than in any other single activity. Sleep amount and quality of sleep have a direct impact on mood, behaviour, motor skills and overall quality of life. Yet, despite how important restful sleep is for the body to maintain good health, there is a comparatively small amount of studies evaluating key multi-factorial determinants of restful sleep in non-pathological, …
- Study level
- PhD
- Faculty
- Faculty of Engineering
- School
- School of Mechanical, Medical and Process Engineering
- Research centre(s)
- Centre for Biomedical Technologies
Human-in-the-loop techniques to debug machine learning models
Machine learning models are being deployed in critical domains such as healthcare, education and fintech. The current approach to deploying machine learning models is based on considering a data-centric approach where the models are evaluated using performance measures on a test set. However, the high performance of the model on test data is not indicative of its reliability,An important aspect of reliability is in the understanding of what exactly a machine learning model encodes, and to verify if it learns …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Science
- School
- School of Information Systems
Contact us
If you have questions about the best options for you, the application process, your research topic, finding a supervisor or anything else, get in touch with us today.