Electrical and computer engineering internships

Supervisor: Professor Daniel Quevedo

Eligibility: WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application.

Project Description:

Many practical control systems are operated using wireless communication networks. Typical examples include uncrewed vehicles, robotic systems and critical infrastructure. Systems of this kind crucially use wireless networks to transmit sensor and actuator signals. However, wireless communications are unreliable. This raises significant challenges for the design of such cyberphysical systems.

This project is aimed at developing novel methods for estimation and control systems where signals are transmitted over unreliable communication channels. A key feature of the situations to be studied is that at each transmission instant, one out of a number of communication channels can be chosen for transmission. This then raises the issue of quickly finding out which channel is the best one. Unfortunately, channel qualities (i.e., statistics) are unknown and need to be learned during operation.

Requirement to be on campus: No

Supervisor: Associate Professor Zihuai Lin, Professor. Branka Vucetic

Eligibility: Up to 2 students are required for this project. The students participating in this project should have good knowledge on NLP and AI. Programming skills are essential..

Project Description:

The project focuses on developing specialised Large Language Models (LLMs) for efficiently extracting Hospital-Acquired Pressure Injuries (HAPI) information from clinical notes. The students are required to address the challenge of scarce labelled data and privacy concerns in healthcare by creating a synthetic dataset of clinical texts, which served as a foundation for training and evaluating four advanced NLP models: LLaMA Base, Alpaca, MedAlpaca, and Asclepius.

A significant part of the thesis project lies in the comprehensive analysis and benchmarking of the models against real-world data, setting a new standard in the field of large language models in clinical settings. The students must work closely with Westmead Local Health District clinicians, ensuring that the synthetic notes accurately represent clinical scenarios and fine-tuning the project's output with practical insights.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: Associate Professor Zihuai Lin, Professor Branka Vucetic

Eligibility: Up to 3 students are required for this project. The students participating in this project should have good knowledge on smart phone APP development. Programming skills are essential.

Project Description:

This project will invent, train, and deploy AI models that produce accurate, comprehensive matching feedback of a patient’s clinical trial outcomes—which we call Patient recruitment system for global medicine companies

1. Computer program development based on server system - Develop AI based computer software which can automatically output clinical trial matching score. The java or .C# programming is necessary, priority is given to whom familiar with server programming.
2. PC & APP UI development based on HTML5 - Similar to the first project, now the platform is multi-platform crossed, specially co-development for user interface.
3. Development & deployment of LLM algorithm - Developing and deploying LLM generative AI to clinical trial recruitment system, priority is given to whom familiar with NLP or LLM programming experience.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: Professor Associate Professor Zihuai Lin, Professor Branka Vucetic

Eligibility: Up to 3 students are required for this project. The students participating in this project should have good knowledge on wireless cellular networks, communication theory and signal processing. Matlab, C++ and Python programming skills are essential. Students with average marks above 75 are preferred.

Project Description:

The ambient backscatter communications (AmBC) technology used in IoT systems is a practical application of energy harvesting from ambient radio frequency (RF) signals. In a typical AmBC-empowered IoT system, a passive or semi-passive IoT device harvests RF energy from the ambient RF source (e.g., a cellular network base station (BS) or a Wi-Fi router) to power its circuits, and then the IoT device modulates its information bits onto a sinusoidal signal by intentionally changing its amplitude and/or phase. In this project, we will build an AmBC-empowered battery-free IoT device prototype.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: Associate Professor Zihuai Lin, Professor Branka Vucetic

Eligibility: Up to 2 students are required for this project. The students participating in this project should have good knowledge of radio frequency engineering. Programming skills are essential. The students with average marks above 75 are preferred.

Project Description:

In this project, we aim to develop a low cost X-ray vision wireless hand-held device. The developed hand-held device can be used to see through walls to track moving human bodies. The technique would be based on a concept similar to radar and sonar imaging, instead of using high power signal, this one would use low power Wi-Fi or mmWave/THz, UWB signals to track the movement of people behind walls and closed doors. When an RF signal is transmitted towards a wall, due to the absorbing property of the walls, only a small part of the signal can be penetrated through the wall and can be reflected back when the signal reaches any objects that happen to be moving around in the other room. Based on the reflected signal, we can detect the moving objects.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: Associate Professor Zihuai Lin, Dr Audrey Wang, Professor Branka Vucetic

Eligibility: Up to 3 students are required for this project. The students participating in this project should have good knowledge on hardware development. Programming skills are essential. The students with average marks above 75 are preferred.

Project Description:

This project will develop novel solutions for IoT based pressure injury monitoring to enable smart hospitals, smart healthcare and provide in-patients with good treatment experience. IoT is a key enabler for our future smart hospital and healthcare to effectively overcome the major problems, such as nursing staff shortness, impractical physical care environments and difficulties in identifying patents’ needs, etc. In order to enable a fast uptake of the IoT pressure injury monitoring systems, key issues, such as data collection and sensing, pressure injury prediction modelling and hospital validation, should be addressed.

These problems are the major technological obstacles which are preventing industrial partners from further expanding their business in the hospital IoT area. We will develop a smart mat for pressure injury monitoring. The proposed smart mat consisting of a pressure sensor array and a moisture sensor array will be tested and validated in the Westmead hospital. The collected data will be transmitted to the cloud via WiFi or other wireless networks for data processing and analysis. The developed deep learning algorithms for smart mat will be used to obtain the weight and moisture distribution of the inpatient’s body as well as the respiratory rate.

Requirement to be on campus: Yes *dependent on government’s health advice

Supervisor: Professor Yonghui Li, Haiyao Yu, Professor Branka Vucetic

Eligibility: - Proficiency in Python and familiarity with PyTorch. - Understanding of wireless signal processing and WiFi-based localization. - Experience with MATLAB for signal analysis is a plus. - Strong analytical and problem-solving skills.

Project Description:

This project focuses on passive WiFi tracking for device-free human localization using commercial-off-the-shelf (COTS) WiFi devices. The system extracts channel state information (CSI) to estimate Doppler frequency shifts (DFS), angle-of-arrival (AoA), and human reflection distance for accurate real-time tracking. This system addresses major challenges such as transceiver clock synchronization, multipath interference, and hardware-related phase differences. It enables real-time tracking within 1m error in complex indoor environments. The project will involve developing and optimizing the system framework, implementing machine learning-based tracking algorithms, and testing in real-world environments. Students will gain expertise in wireless sensing, signal processing, and machine learning for localization applications.

Requirement to be on campus: Yes, work in research lab *as per government’s health advice.

Supervisor: Professor Yonghui Li, Haiyao Yu, Professor Branka Vucetic

Eligibility:
- Proficiency in Python and familiarity with PyTorch.
- Understanding of machine learning algorithms.
- Strong analytical and problem-solving skills.

Project Description:

This project focuses on developing an advanced indoor localization system that leverages WiFi round trip time and deep learning-based methods for precise mobile device positioning. The proposed framework eliminates the need for real-world measurements in new environments through a zero-shot learning approach. It integrates WiFi-based round-trip time (RTT) and received signal strength measurements, processing to enhance localization accuracy. The developed system has the potential to improve the model's generalization to different indoor settings. The project will involve implementing, testing, and optimizing the system in real-world scenarios. By participating, students will gain hands-on experience in machine learning, computer vision, and wireless communication technologies, contributing to next-generation indoor positioning systems.

Requirement to be on campus: Yes *as per government’s health advice.

Supervisor: Professor Yonghui Li, Litianyi Zhang, Professor Branka Vucetic

Eligibility: Familiar with networking protocols, including LoRaWAN and Wi-Fi standards, and experience with embedded systems programming. Preferable skills include knowledge of energy-efficient protocol design and simulation tools (e.g., NS-3, MATLAB). Proficiency in Python programming, data processing, analysis, deep learning, and network simulation frameworks is also highly desirable.

Project Description:

This project aims to develop an innovative energy-efficient protocol for hybrid LoRa-WiFi IoT networks, specifically designed to optimise data transmission while conserving power. By intelligently switching between LoRa for long-range, low-power communication and Wi-Fi for high-speed, localised data exchange, the protocol will enhance network performance without compromising energy efficiency.

The proposed system will dynamically adapt to varying network conditions and energy availability, thereby ensuring reliable connectivity even in harsh environments. This research will include simulation and real-world testing to validate protocol effectiveness. The results are expected to significantly improve IoT communication for applications such as environmental monitoring, precision agriculture, and disaster management in rural and remote settings.

Requirement to be on campus: Yes *as per government’s health advice.

Supervisor: Professor Yonghui Li, Litianyi Zhang, Professor Branka Vucetic

Eligibility: Familiar with Wi-Fi standards, and experience with embedded systems programming. Preferable skills include knowledge of protocol design and simulation tools (e.g., NS-3, MATLAB). Proficiency in Python programming, data processing, analysis, deep learning, and network simulation frameworks is also highly desirable.

Project Description:

The project aims to develop advanced coverage extension and dynamic resource allocation techniques for WiFi 7-enabled IoT networks, ensuring seamless connectivity over large areas. Utilising Multi-Link Operation (MLO), the project will optimise resource allocation based on real-time user density, signal strength, and network conditions. By combining directional beamforming and channel bonding, it seeks to extend coverage without compromising signal quality or bandwidth efficiency. The proposed approach will dynamically adjust resource distribution to accommodate fluctuating traffic demands and maintain consistent Quality of Service (QoS) in dense and expansive IoT environments. Additionally, adaptive algorithms will be employed to reduce interference and minimise latency, particularly in dynamic topologies and challenging propagation conditions.

Requirement to be on campus: Yes *as per government’s health advice.

Supervisor: Professor Yonghui Li, Yunkai Hu, Professor Branka Vucetic

Eligibility: Proficiency in Python programming, machine learning, and deep learning. Expertise in deep learning, particularly with frameworks like TensorFlow or PyTorch.

Project Description:

This project aims to develop a non-intrusive system that utilizes Wi-Fi signals to accurately recognize human postures and detect falls in indoor environments. By analyzing the variations in Wi-Fi Channel State Information (CSI) caused by human movements, the system can monitor activities without the need for wearable devices or cameras, thereby preserving privacy and ensuring continuous monitoring.

Requirement to be on campus: Yes *as per government’s health advice.

Supervisor: Professor Yonghui Li, Yunkai Hu, Professor Branka Vucetic

Eligibility: Proficiency in Python programming, machine learning, and deep learning. Expertise in deep learning, particularly with frameworks like TensorFlow or PyTorch.

Project Description:

This project aims to develop a non-intrusive health monitoring system that utilizes existing Wi-Fi signals to continuously track respiratory and heart rates without the need for wearable devices. By analyzing variations in Wi-Fi Channel State Information (CSI) caused by chest movements during breathing and heartbeats, the system can accurately monitor vital signs in real-time. This approach offers a cost-effective and privacy-preserving alternative to traditional monitoring methods.

Requirement to be on campus: Yes *as per government’s health advice.

Supervisor: Thomas Chaffey

Eligibility: Taking or have taken a course in control systems. Familiarity with the Fourier transform. Ability to code in a high-level language such as Julia or Python

Project Description:

The Scaled Relative Graph is a recently introduced graphical tool, which generalises the Nyquist diagram of a linear, time invariant dynamical system. It allows a control engineer to read off important system properties, such as stability and passivity, directly from the plot, and establish stability of a feedback interconnection from the non-intersection of the SRGs of the individual components. This project will develop an open source software tool for computing and visualising the Scaled Relative Graph of a system, from its Fourier transform, in three natural geometries: the Argand diagram, the Riemann sphere and the Poincaré disc. Algorithms for computing the Minkowski sums of convex polygons will be adapted to compute the SRGs of parallel and series interconnections of systems, and a method of sampling the SRG of a black-box system will be developed which seeks out worst-case conditions for control design.

Requirement to be on campus: No

Supervisor: Dr Sid Assawaworrarit

Eligibility: WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application.

Project Description:

This project aims to design silicon-based devices that can control the absorption and emission of mid-infrared thermal radiation. Potential applications for this device include energy generation from waste heat, radiative cooling, and sensing. In this project, you will use computational tools like COMSOL to analyse the spectral absorption and emission characteristics of common silicon devices, such as p-n diodes and MOS capacitors, in the mid-infrared region and to analyse how the absorption and emission properties of these devices can be adjusted by an externally applied voltage. You will then incorporate photonic designs, such as gratings or photonic crystals, to shape the spectral profile of the radiation absorption/emission. Finally, you will incorporate manufacturability to your designs to ensure they are realistic for manufacturing. Useful knowledge: Semiconductor devices, Light absorption calculation

Requirement to be on campus: Yes, preferred *dependent on government’s health advice.

Supervisor: Dr Sid Assawaworrarit

Eligibility:WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application.

Project Description:

This project explores the design of nanoparticles for cool paint or coatings that can minimise heat absorption from solar radiation while providing an appealing colour appearance and efficiently emitting cooling thermal radiation. This innovation seeks to reduce reliance on air conditioning and promote energy efficiency, particularly beneficial in hot climates. The project will use computational tools such as Python light scattering calculations and COMSOL to model the behaviour of silicon-based nanoparticles. These tools will be used to study: (i) their light absorption characteristics within the solar spectrum, which determine the heat generated when exposed to sunlight; (ii) their light scattering properties, which contribute to colouration; and (iii) how the dimensions of nanoparticles can be adjusted to tune their colour appearance. Both individual particles and ensembles integrated into paint or coatings will be examined to understand how these properties evolve from single particles to a dense collection in the final product.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Associate Professor Steve Shu

Eligibility: Familiarity with deep learning frameworks, Signal processing and analysis and mathematical modelling

Project Description:

Deep learning-based diffractive imaging technology, such as PtychoNN, offers phase recovery hundreds of times faster than traditional algorithms (like Ptycholib). However, the latest synchrotron instruments, with their significantly increased data rates, demand approximately PFLOPs of computation for phase retrieval, posing a challenge for real-time imaging. To meet this challenge without compromising performance, this project aims to optimize lightweight networks for inverse imaging via pruning, quantization, and knowledge distillation, thereby accelerating phase recovery tasks.

Reference: [1] Pan, Xinyu, et al. "An efficient ptychography reconstruction strategy through fine-tuning of large pre-trained deep learning model." Iscience 26.12 (2023). /p>

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Associate Professor Steve Shu

Eligibility:Familiar with Verilog or CUDA acceleration and data architecture; proficient in programming languages (C/C++, Matlab or Python)

Project Description:

This project explores advanced computational techniques to accelerate phase retrieval algorithms in ptychography, a high-resolution imaging method. We will investigate optimization strategies such as GPU acceleration or iterative methods to improve convergence speed and accuracy. The project involves implementing and benchmarking different approaches on simulated and experimental datasets. Reference: [1] J. Dong, et al., "Phase Retrieval: From Computational Imaging to Machine Learning: A tutorial", IEEE Signal Processing Magazine ( Vol.: 40, Issue: 1, Jan 2023) [2] Z. Dong, et al. “High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs.” 2018 New York Scientific Data Summit (NYSDS) (2018): 1-5.

Requirement to be on campus:Yes *dependent on government’s health advice.

Supervisor: Associate Professor Steve Shu

Eligibility: Fundamentals of optoelectronics; proficient in programming languages (Matlab or Python)

Project Description:

Ptychography is a revolutionary imaging technique that combines optics, electronics, and advanced computation to achieve ultra-high-resolution imaging beyond traditional optical limits. This project is designed for students with an optoelectronics background, focusing on the integration of coherent light sources, diffraction optics, and computational phase retrieval: 1) Design and optimize a laser-based illumination system for coherent diffraction imaging; 2) Implement phase retrieval algorithms like the ePIE (Extended Ptychographic Iterative Engine) to reconstruct high-fidelity images.

Reference: [1] C. Chen, et. al, "Resolution-enhanced reflection ptychography with axial distance calibration", Optics and Lasers in Engineering 169:107684, 2023 [2] C. Chen, et. al., "Ultra-broadband diffractive imaging with unknown probe spectrum", Light Science & Applications 13(1), 2024

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Associate Professor Dong Yuan

Eligibility: Good programming skill. Familiar with UE5 and C++ are preferrable.

Project Description:

Wireless technology as the backbone of mobile applications has become essential in our daily lives. However, signal fluctuations caused by the unpredictable nature of factors such as moving crowds and improvised events in wireless and mobile applications amplify the complexity of their comprehensive evaluation across diverse real-world environments. To address these challenges, we developed a digital twin system with learning-based calibration and ray-tracing based real-time wireless propagation simulation capabilities for WMAs. The system can learn the latent state of the environment from real data for high-precision calibration and accurately simulate wireless systems in realistic 3D environment. The candidate will work on the applications of this system, e.g., autonomous driving and smart manufacturing, which will use measurement of wireless signals for training AI models.

Requirement to be on campus: No

Supervisor: Dr Wibowo Hardjawana

Eligibility: A strong background in wireless communication and a deep learning background equivalent to the one covered in ELEC5508 Wireless Engineering is required. Python and Matlab expertise are required.

Project Description:

Each generation of cellular communication systems is marked by a defining disruptive air interface technology of its time, such as orthogonal frequency division multiplexing (OFDM) for 4G or Massive multiple-input multiple-output (MIMO) for 5G, leading to advancement in signal processing. Since artificial intelligence (AI) is the defining technology of our time, it is natural to ask what role it could play in 6G signal processing.

The project aims to study the benefit of end-to-end 6G air-interface signal processing where AI replaces communication processing blocks at the transmitter and receiver and is jointly optimised. The specific tasks of the project are to modify and/or add existing wireless communication reference design to facilitate end-to-end learning by including AI in the wireless air interface. Students will do mini-research and have a choice to go in-depth on different 6G air-interface, ranging from MIMO, OFDM or OTFS and specific AI signal processing techniques ranging from generative and discriminative types.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Dr Huaming Chen

Eligibility: Students should have knowledge about testing and ideally come from software engineering background.

Project Description:

The rapid advancement of artificial intelligence (AI) in domains such as autonomous driving, healthcare, and finance has accelerated its widespread adoption. However, deploying robust AI solutions in real-world, resource-constrained environments presents unique engineering and quality assurance challenges. This project aims to address these challenges by developing novel testing methodologies tailored specifically for evaluating Large Language Models (LLMs) in low-resource scenarios.

The research will focus on creating efficient testing strategies to identify model limitations, robustness issues, and reliability under limited computational capacity, minimal data availability, and restricted infrastructure. Specifically, it will explore zero-shot evaluation frameworks, lightweight mutation testing, and resource-aware fuzz testing techniques to rigorously assess the suitability of LLMs for constrained applications. The outcomes will significantly enhance the reliability and practicality of deploying advanced AI systems, ensuring their safe and effective use even when computational or data resources are severely limited.

Requirement to be on campus: No

Supervisor: Dr Huaming Chen

Eligibility: Students should have knowledge about testing, and ideally come from software engineering background.

Project Description:

Multimodal Large Language Models (LLMs), which integrate text, images, and audio, have significantly advanced AI capabilities across diverse applications, including autonomous driving, healthcare diagnostics, and human-computer interaction. However, their increased complexity and multimodal nature introduce critical vulnerabilities, particularly through adversarial prompt attacks. This project will systematically investigate prompt-based security vulnerabilities unique to multimodal LLMs, focusing on identifying, characterizing, and mitigating attacks that exploit input prompts across multiple modalities.

Key research activities include developing robust multimodal prompt-attack benchmarks, analyzing vulnerability propagation across different modalities, and creating novel defensive strategies to enhance model robustness. Outcomes will deliver comprehensive insights into the security landscape of multimodal LLMs, establish guidelines for secure prompt engineering practices, and produce effective methodologies to safeguard these models against sophisticated prompt attacks. This research ensures the reliability and secure deployment of multimodal AI systems in safety-critical and high-stakes scenarios.

Requirement to be on campus: No

Supervisor: Professor Branka Vucetic, Professor Yonghui Li, Chentao Yue

Eligibility:

- Background in wireless communications or signal processing

- Programming experience in Python

- Knowledge of deep learning frameworks (PyTorch or TensorFlow)

- Interest in AI applications for wireless communications

Project Description:

This research project aims to develop novel semantic wireless communication systems by integrating physical layer wireless technologies with AI. Specifically, we will explore how large language models (LLMs) and computer vision algorithms can be leveraged to enable semantic and goal-oriented communications that significantly reduce transmission bandwidth while preserving meaning and reliability.

Students will investigate joint source-channel coding techniques optimized for semantic information, design AI-driven encoders and decoders for wireless channels, and evaluate performance metrics beyond traditional bit error rates. The project combines wireless communications theory with cutting-edge AI to achieve high-rate, low-latency semantic transmission across bandwidth-constrained channels. This interdisciplinary approach has potential applications in next-generation IoT networks and autonomous vehicle communications where efficient transmission of meaningful information is critical.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Professor Branka Vucetic, Gaoyang Pang

Eligibility: This project is open to students in Electrical Engineering, Computer Engineering, or related disciplines with a strong interest in wireless communications and machine learning. Prior experience with Python programming and basic knowledge of deep learning or signal processing is desirable.

Project Description:

Traditional communication systems focus on transmitting bits accurately, regardless of their meaning. In contrast, semantic communication aims to transmit only the information that is meaningful for the task at hand, reducing bandwidth usage and improving efficiency. This project will explore machine learning techniques—such as deep representation learning and attention mechanisms—to design semantic encoders and decoders that can identify, preserve, and recover task-relevant content under various channel conditions.

The student will assist in developing simulation models to test semantic compression, semantic noise robustness, and semantic fidelity metrics. Applications include efficient video transmission for remote education, edge AI for smart factories, and human-intent recognition in human-machine collaboration. The internship will provide hands-on experience with cutting-edge research in AI-driven communications, foster technical skills in Python and ML frameworks, and offer valuable mentoring for students considering research careers or postgraduate study.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Associate Professor Dong Yuan

Eligibility: Familiar with PyTorch and Nvidia CUDA; programming with Python and C++.

Project Description:

Recent advances in deep neural networks (DNNs) have substantially improve the accuracy and speed of video analytics. The maturity of cloud computing, equipped with powerful hardware like GPU, becomes a typical choice for such kind of computation intensive DNN tasks. One obstacle, however, is the large amount of data volume of video streams. For example, a self-driving car can generate up to 750 megabytes of sensed data per second, but the average uplink rate of 4G, fastest existing solution, is only 5.85 Mbps. In order to avoid the effects of network delay and put the computing at the proximity of data sources, edge computing emerges. Nevertheless, edge computer itself is limited by its computing capacity and energy constraints, which cannot fully replace cloud computing. This project will investigate the efficient parallel algorithms for DNN inference tasks on the edge server that equipped with GPUs.

Requirement to be on campus: No

Supervisor: Professor Jianguo Zhu

Eligibility: - Bachelor's degree in electrical engineering - Outstanding transcript (WAM>75) - Good knowledge of electromagnetics - Skilful with MATLAB/Simulink or other programming languages - Research experience with a publication record in electrical engineering (preferred)

Project Description:

Electricity market price varies dramatically due to various factors and can be predicted with reasonable precision using artificial intelligence models [1,2]. To track the influence of these factors on electricity price variations, large language models are attracting significant attention in intelligent electricity price preprocessing and forecasting [3]. This project aims to tracking these factors using large language models for long- and short-term electricity price predictions.

[1] Xin Lu, Jing Qiu, Gang Lei, Jianguo Zhu, "Scenarios modelling for forecasting day-ahead electricity prices: Case studies in Australia", Applied Energy 308 (2022) 118296, DOI: 10.1016/j.apenergy.2021.118296 [2] Xin Lu, Jing Qiu, Gang Lei, Jianguo Zhu, "An Interval Prediction Method for Day-Ahead Electricity Price in Wholesale Market Considering Weather Factors", IEEE Transactions on Power Systems, Vol.39, No.2, pp.2558-2569, March 2024, DOI: 10.1109/TPWRS.2023.3301442 [3] Yutian Huang, Linghan Huang, Yachao Zhu, Gang Lei, Allen Wang, Jianguo Zhu, "Application of Large Language Models in Intelligent Preprocessing and Forecasting of Electricity Price", International Conference on Smart Grid and Green Energy (ICSGGE2025), 28 Feb. - 2 March 2025, Sydney, Australia

Requirement to be on campus: No

Supervisor: Associate Professor Luping Zhou

Eligibility: WAM>75 and Undergraduate candidates must have already completed at least 96 credit points towards their undergraduate degree at the time of application.

Project Description:

Automated radiology report generation leverages AI to produce structured reports from medical images, reducing radiologists’ workload and improving diagnostic efficiency. While deep learning and large language models (LLMs) have advanced this field, ensuring clinical accuracy remains a major challenge. Current models often hallucinate findings, misinterpret subtle abnormalities, or fail to localize pathologies, limiting their reliability. Moreover, these models primarily learn from training data without explicitly incorporating expert knowledge, leading to inconsistent and non-transparent reports that reduce clinical trust.

This project aims to improve clinical accuracy and interpretability in AI-driven radiology report generation by integrating enriched prior knowledge. For example, we will incorporate fine-grained anatomical structures, enhancing the model’s spatial understanding to improve pathology localization. Another prior knowledge could come from radiologists’ attention patterns via eye-tracking data while reading image, which will be leveraged to guide AI models toward clinically relevant image regions. By integrating anatomical insights and expert attention patterns, this research seeks to bridge the gap between AI-generated and expert-authored reports, enhancing trust, accuracy, and clinical adoption of automated radiology reporting systems.

Requirement to be on campus: No

Supervisor: Professor Xiaoke Yi, Associate Professor Liwei Li

Eligibility: Year 3/4/5 or Master students. Electrical engineering, mechatronics, computer engineering, software engineering or computer science

Project Description:

Join us in exploring the new applications of radio frequency (RF) photonics in real-world 6G and satellite communication systems, working alongside industrial experts to design, test, and integrate innovative RF photonic systems. We will investigate the potential of RF photonics to overcome traditional system limitations, analyse and optimize system performance, and contribute to novel solutions to solve industrial challenges.

Through this project, you'll gain hands-on skills, enhance your knowledge of photonics, RF systems, and communication engineering, and develop your analytical, problem-solving skills.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Professor Xiaoke Yi, Associate Professor Luping Zhou, Associate Professor Liwei Li

Eligibility: Year 3/4/5 or Master students. Electrical engineering, Mechatronics, Computer engineering, Software engineering or Computer science

Project Description:

The state-of-the-art sensing technology is rapidly growing and will play a critical role in the near future. For instance, smart phones, which play a significant role in our daily life, have a fingerprint identity sensor that makes it easy for us to access the device, and they also use an ambient brightness sensor to adjust the display brightness, etc.

The project is to deliver the superior, advanced sensing platforms assisted by machine/deep learning to address the important challenges across a diverse range of applications in various fields, particularly in lab-on-chips, Internet of Things, broadband communications and biomedical applications. The internship project focuses on electrical circuits design and data processing as well as machine learning and software programming. The aim is to realize ultra-sensitive, high resolution and extreme-range sensing.

The intern will closely work with a research team including PhD students and postdoctoral research associates. Innovative signal processing and design in both hardware and software will be carried out during the project.

Requirement to be on campus: Yes *dependent on government’s health advice.

Supervisor: Associate Professor Craig Jin and Associate Professor Cate Madill

Eligibility: We are looking for software/computer engineering students with python programming experience and some experience developing apps for a mobile platform.

Project Description:

We are developing the Unified Voice Registry - a research program to create a pathway to integrate vocal analysis as a health biomarker within Australia’s clinical framework. The data we collect will help define the feasibility of using vocal analysis for screening, early diagnosis, and remote monitoring of chronic conditions, including neurological degenerative diseases, cardiovascular disease, and mental health conditions. You will assist us will developing an automated data collection app for the clinical setting with a view looking towards a design for a mobile device. As a starting point we are using Python within a PsychoPy Framework. We would like to improve the user-interface and explore integrating machine learning into the data collection setting.

Requirement to be on campus: Yes *dependent on government’s health advice. We require only partial on campus involvement.

Supervisor: Associate Professor Craig Jin and Associate Professor Cate Madill

Eligibility: We are looking for software/computer engineering students with Python and Matlab programming experience and some background in image processing.

Project Description:

Real-time MRI is a new imaging modality for the human vocal tract. We are the first group in Australia to pursue this imaging procedure and are collecting MRI data at Westmead Hospital. Within this context, we are developing analysis tools for real-time MRI images of the human vocal tract. We are currently exploring linking volumetric and real-time MRI images, numerical acoustic simulations, machine learning algorithms to individualize text-to-speech using MRI images, and phonetic analyses of the data using MATLAB/Python. You will assist us with developing our analytical tools based on your skill set.

Requirement to be on campus: Yes *dependent on government’s health advice. We require only partial on campus involvement.