Projects
Projects being undertaken by our research group.
Ongoing Projects
-
Real-time Internet of Things with Performance Guarantees
This project provides a suite of distributed resource allocation algorithms for real-time Internet of Things (IoT) systems. It develops fundamental performance guarantees for many mission-critical applications, including intelligent transport.
-
Multi-Modal Deep Dictionary Learning Framework for Managing Smart City Assets
This Project aims to provide new digital asset management tools for city councils to improve city services by utilising new sensing and automated learning technologies for recognising, tracking, and auditing of assets.
Smart wireless radio environments for the 6G era
Description
This project aims to revolutionise radio signal propagation and information transfer by developing “smart” wireless radio environments. Using Reconfigurable Intelligent Surface (RIS), the smart wireless network can transmit information without generating new signals but recycling the incoming signal. However, as an emerging technology, fundamental analysis – in terms of rate, reliability, and efficiency – is needed to understand the performance of RIS-empowered wireless networks. Expected outcomes include new communication-theoretic models and the enabling technologies to realise them in practice. These smart environments have the potential to offer ‘greener’ and more ‘seamless wireless connectivity’ for the future wireless network.
Investigators
Project information
FT, 2021–2025
RAINBOW: RAdIo Networks Based On machine learning for situation aWareness
Description
This project aims to develop software-defined and cognitive radio networks (SDR) to detect adversarial communications and achieve situation awareness on radio frequency (RF) spectrum. The project will generate novel SDR architectures and new attack-resistant detection algorithms through innovative approaches combining machine learning and game theory. Expected outcomes include a strategic alliance between the University of Melbourne and the Northrop Grumman Corporation. Among significant benefits, the project will improve cybersecurity of RF spectrum as a national asset, help protect critical infrastructure relying on wireless networks such as telecommunications and defence, and build skills in cybersecurity and Artificial Intelligence.
Investigators
Prof Tansu Alpcan, Prof Christopher Leckie, Dr Sarah Monazam Erfani
Project information
LP190101287, 2020–2023
Adversarial machine learning in distributed settings
Description
This project aims to harness recent advances in adversarial learning to detect, mitigate and prevent malicious attacks against cyber-physical and distributed systems where a subset of data owners can behave maliciously. Novel methods will be developed building upon techniques from adversarial learning, game theory and system theory.
Investigators
Prof Tansu Alpcan, Prof Ben Rubinstein, Dr Seyit Camtepe
Project information
CSIRO/Data61, 2020–2023
CommunSense: integrating communications and sensor technology for future V2X communications
Description
High data rate communication links between vehicles and surrounding objects are needed to enhance advanced driver assistance systems, enable a wider range of infotainment options and pave the way towards fully automated driving. This project aims to develop a novel framework to use millimeter wave frequencies (the newest candidate for 5G cellular) to enable future high data rate vehicle-to-everything (V2X) communication systems. Based on an innovative approach, the project combines communication and sensor technologies in an integrated system that simultaneously reaps the benefits of autonomously sensing the driving environment and cooperatively exchanging information, thus providing significant savings in hardware costs and spectrum usage.
Investigators
Prof Jamie Evans, Dr Rajitha Senanayake, Prof Peter Smith
Project information
DP, 2019–2022
New entropy measures for smart wearable devices
Description
Wearable devices can be very effective in remote and continuous monitoring to detect short or bursty anomalous events. Present devices are unable to detect such events effectively due to limited capability in processing short length signal. Therefore, this project provides computationally efficient algorithms for signal quality analysis and enhanced feature extraction methods in resource constrained wearable devices. This will improve the reliability and performance of wearable devices for adoption in intelligent decision-making systems.
Investigators
Prof Marimuthu Palaniswami, Dr Chandan Karmakar, Prof Dr Thomas Penzel
Project information
DP190101248, 2019–2022
Molecular communication for the future Internet of Bio-NanoThings
Description
Molecular communication, using molecules to transmit information, is a promising new paradigm for enabling nanoscale communications. This project aims to develop new fundamental theories for molecular communication to improve our understanding of molecular information delivery and provide new techniques for realising the information exchange within the nanonetworks. The expected outcomes of the project include frameworks for predicting communication performance and new theoretical models for imperfect transceivers and realistic channels. These outcomes will underpin the future development of nanonetwork applications such as environmental monitoring and air pollution control thus benefitting Australian environments and quality of life.
Investigators
Project information
Doreen Thomas Fellowship
Adaptive, secure and energy efficient wireless communication networks description
This project aims to investigate a novel network architecture that supports ultra-reliable access and coverage for future generation wireless communications. Based on recent developments in fog computing, the project aims to redefine the radio access network of wireless systems to shift from traditional, static cell-centric architecture to a more dynamic cell-free architecture. The intended outcomes of the research are an adaptive network architecture that dynamically forms serving clusters, secure communications protocols that decrease latency and increase communication security and energy-efficient signal processing techniques that support green communications.
Investigators
Project information
DECRA, 2018–2023
Structured codes: novel interference mitigation techniques in networks
Description
The biggest challenge in modern large-scale communication networks is to mitigate interference among numerous active devices. In contrast to conventional wisdom that interference should be avoided, this project aims to harness interference, based on the idea that interference can be viewed as a form of computation, and this computational potential can be exploited advantageously via the so-called structured codes. This project expects to develop theory and novel coding techniques which will deepen our understanding of interference, and significantly increase the network bandwidth efficiency.
Investigators
Information-theoretic analysis of machine learning algorithms
Description
Information theory and statistical learning theory are closely related, as both fields are rooted in statistics. Numerous works have shown that information-theoretic analysis and techniques provide useful insight to machine learning algorithms. Examples include that information measures (eg, mutual information) provide tight bounds for generalisation errors of learning algorithms, and Fano inequalities can be used to give lower bounds on non-parametric regression problems. In this project, we will use both information-theoretic measures and techniques to study learning algorithms. Examples include important machine learning problem as transfer learning and learning with causality consideration.
Investigators
Coded computation for machine learning
Description
Coded computation is an emerging technique which uses error correction codes to improve the reliability of distributed computation systems. Roughly speaking, a big computational task is divided into smaller subtasks along with additional redundancies. Coded computation schemes guarantee that the overall computational tasks can be accomplished even if some of the smaller subtasks are not completed. In this project, we will study the coded computation of general functions using deep neural networks and its application for solving large-scale machine learning problems.
Investigators
Automated tracking of construction materials for improved supply chain logistics and provenance: Phase 1 scoping study
Description
Building industry lacks understanding and capability of using real-time and reliable data, which causes inefficient supply chain logistics and limits how lean construction techniques can be applied. There is a need for secure data that identifies the origin of materials, products, and assemblies. This project will investigate how sensing technologies can provide real-time data to improve project management and validate building compliance through measures used to guarantee the provenance of the supply chain.
Investigators
Prof Tuan Ngo, Dr Wen Li, Prof Marimuthu Palaniswami, Dr Guilherme Tortorella, Dr Aravinda Rao
Project information
Building 4.0 CRC, 2021
Field data collation to support real-time operational management: Scoping Study
Description
One of the significant obstacles to practical project planning on construction sites is leveraging and managing the large volumes of information consistently exchanged amongst many stakeholders. This project investigates the advances of how on-site operation processes are managed by using real-time data to provide greater visibility and understanding of overall construction programs.
Investigators
Prof Tuan Ngo, Dr Aravinda Rao, Prof Marimuthu Palaniswami, Assoc Prof Kourosh Khoshelham
Project information
Building 4.0 CRC, 2021
Design of real-time optimisation methods with guaranteed performance
Description
The project aim is the development of a framework for the advancement of optimisation algorithms operating in real-time applications. This project expects to generate new knowledge in the area of systems theory and optimisation, and its application to time-varying problems. Expected outcomes of this project should lead to a new theoretical and practical framework that aims to ameliorate the shortcomings of the existing approaches that struggle to rapidly respond to new information. This should provide significant benefits. Specifically, this project aims to facilitate a technological leap that generates smaller, faster, and more powerful embedded systems such as broadband services, mobile phones, medical imagining, radar, and avionics.
Investigators
Iman Shames (ANU), Jonathan Manton, Farhad Farokhi, Chris Manzie, Airlie Chapman (The University of Melbourne), Anthony Man-Cho So (Chinese University of Hong Kong), and Salem Said (CNRS).
Project information
Discovery Project, Australian Research Council (ARC) / DP210102454
Safe learning in distributed multi-agent control
Description
To develop and test theoretical results in the area of safe learning and control for multi agent swarm systems. The research will explore, analyse, develop and demonstrate a number of approaches in safe learning of dynamic models for swarm control. These may include the use of barrier certificates for learning Gaussian model uncertainty in linear or nonlinear systems. The topic of safe learning and verifiable learning is of particular interest due to the relatively sparse results available for this topic in the existing literature. Nevertheless, these topics are immense importance for military applications of learning systems.
Investigators
Iman Shames (ANU), Farhad Farokhi (The University of Melbourne), Behzad Zamani and Alex Leong (DSTG).
Project information
DSTG / ID10298
Low latency coding for channels subject to packet loss
Description
This project aims to provide novel erasure codes that provide high reliability with respect to countering packet loss while allowing the decoder to operate with low latency. The work builds on the investigator’s earlier work on convolutional erasure codes based on MDS block codes.
Investigators
Erasure codes for distributed storage
Description
Due to the fast-growing demand for large-scale data storage, storage technology has emerged that distributes data across multiple nodes which are interconnected over a network. This project seeks to develop efficient storage systems based on erasure codes.
Investigators
Margreta Kuijper (University of Melbourne), Julia Lieb (University of Zurich), Diego Napp (University of Alicante)