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 18 matching student topics
Displaying 1–12 of 18 results
Learning complex dynamics from multimodal time-series data
Modelling non-stationary dynamics from high-frequency time-series data remains challenging. These signals often exhibit complex temporal and spectral structure, while observations are typically noisy, incomplete, and affected by changing operating conditions, making reliable prediction and representation learning difficult.This PhD project, offered at Queensland University of Technology (QUT) in collaboration with industry partners, focuses on learning representations and dynamics from multimodal time-series data.The research will explore deep approaches including sequence models, transformer-based architectures, anomaly detection, graph neural networks, and self-supervised learning, with …
- Study level
- PhD
- Faculty
- Faculty of Engineering
- School
- School of Electrical Engineering and Robotics
SLAM inside the human body: camera tracking and 3D reconstruction for medical procedures
Minimally invasive surgery and endoscopic interventions rely heavily on the clinician’s ability to understand and navigate complex internal anatomy using only a narrow and often restrictive field of view. Having access to an accurate and dynamic 3D reconstruction of the endoscopic scene, together with reliable camera pose estimation can significantly improve spatial awareness and navigation during procedures. The generated map can be used alongside the device’s estimated location to help clinicians better orient themselves within the patient, and it also …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Engineering
- School
- School of Electrical Engineering and Robotics
Physics informed machine learning for energy forecasting
Accurate forecasting is at the heart of many modern industries from energy and transport to retail, supply chains, finance, climate, and health. This research project explores deep learning approaches for time-series forecasting, investigating how modern architectures such as recurrent neural networks, LSTMs, Temporal Convolutional Networks, transformers, and multimodal foundation models can shape the next generation of forecasting systems.The overarching goal is to develop robust, interpretable, and scalable forecasting models that outperform classical methods and work effectively in real-world settings, including …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Science
- School
- School of Mathematical Sciences
- Research centre(s)
- Centre for Data Science
Energy Transition Centre
Enhancing 3D visual understanding through multimodal data fusion
The demand for 3D scene understanding through point clouds is rapidly growing in diverse applications, including augmented and virtual reality, autonomous driving, robotics, and environment monitoring. However, the field faces challenges due to limited data availability and predefined categories. Training deep 3D networks effectively for sparse LiDAR point clouds requires significant amounts of annotated data, which is both time-consuming and expensive. Building on the advancements in 2D models that leverage the power of image and language knowledge, our project aims …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Engineering
- School
- School of Electrical Engineering and Robotics
Re-localisation in natural environments
Re-localisation in robotics involves the process of determining a robot's current pose, consisting of its position and orientation. This can either be within a previously mapped and known environment (i.e. prior map) or relative to another robot in a multi-agent setup. Re-localisation is essential for enabling robots to perform tasks such as autonomous monitoring and exploration seamlessly, even when they encounter temporary challenges in precisely tracking their location in GPS-degraded environments. For instance, consider the 'wake-up' problem, where a robot …
- Study level
- PhD
- Faculty
- Faculty of Engineering
- School
- School of Electrical Engineering and Robotics
Investigating the application of sustainable AI practices in construction
The construction industry plays a vital role in the global economy and there is a growing interest in utilising artificial intelligence (AI) to improve its productivity and efficiency. Despite the industry's significant contribution to the economy, it has faced challenges such as large cost overruns, extended schedules, and quality concerns. Nevertheless, AI is making significant strides to remove these issues by revolutionising various aspects of the construction industry. This is evident from enhancing project planning and design to improving construction …
- Study level
- PhD, Master of Philosophy, Honours
- Faculty
- Faculty of Engineering
- School
- School of Architecture and Built Environment
Mapping the world: understanding the environment through spatio-temporal implicit representations
Accurately mapping large-scale infrastructure assets (power poles, bridges, buildings, whole suburbs and cities) is still exceptionally challenging for robots.The problem becomes even harder when we ask robots to map structures with intricate geometry or when the appearance or the structure of the environment changes over time, for example due to corrosion or construction activity.The problem difficulty is increased even more when sensor data from a range of different sensors (e.g. lidars and cameras, but also more specialised hardware such as …
- Study level
- PhD
- Faculty
- Faculty of Engineering
- School
- School of Electrical Engineering and Robotics
- Research centre(s)
- Centre for Robotics
Fine-grained software vulnerability detection using deep learning techniques
Software vulnerability is a major threat to the security of software systems. Thus, the successful prediction of security vulnerability is one of the most effective attack mitigation solutions. Existing approaches for software vulnerability detection (SVD) can be classified into static and dynamic methods. Powered by AI capabilities, especially with the advancement of machine learning techniques, current software has been produced with more sophisticated methodologies and components. This has made the automatic vulnerability proneness prediction even more challenging. Recent research efforts …
- Study level
- PhD, Master of Philosophy
- Faculty
- Faculty of Science
- School
- School of Computer Science
Overcoming the challenges of sensitive data via synthetic data generation (case study)
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
Multi-modal sentiment analysis
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
Evaluation of language models and word embedding methods for natural language processing applications
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
Building explainable and trustworthy intelligent 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
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.