Potential PhD Projects

There are opportunities for talented researchers to join the School of Computer Science and Engineering, with projects in the following areas: 

  • Artificial Intelligence 
  • Biomedical Image Computing
  • Data and Knowledge Research Group 
  • Embedded Systems 
  • Networked Systems 
  • Programming Languages & Compilers 
  • Service Orientated Computing 
  • Trustworthy Systems 
  • Theoretical Computer Science 
Artificial Intelligence
3D Visualisation of Robot Sensor Data

Supervisory team: Professor Claude Sammut 

Project Summary: Our rescue robot has sensors that can create 3D representations of their surroundings. In a rescue, it is helpful for the incident commander to have a graphical visualisation of the data so that he or she can reconstruct the disaster site. The School of Computer Science and Engineering and the Centre for Health Informatics have a display facility (VISLAB) that permits users to visualise data in three dimensions using stereo projection onto a large 'wedge' screen. 

This project can be approached in two stages. In the first stage, the data from the robot are collected off-line and programs are written to create a 3D reconstruction of the robot's surroundings to be viewed in the visualisation laboratory. In the second stage we have the robot transmit its sensor data to the VISLAB computers for display in real-time. 

This project requires a good knowledge of computer graphics and will also require the student to learn about sensors such as stereo cameras, laser range finders and other 3D imaging devices. Some knowledge of networking and compression techniques will be useful for the second stage of the project. 

A scholarship/stipend may be available. 

For more information contact: Prof. Claude Sammut (c.sammut@unsw.edu.au

Biomedical Image Computing
Deep Learning for Pattern Analysis in Microscopy Images

Supervisory Team: Dr Yang Song

Project Summary: Various types of microscopy images are widely used in biological research to aid our understanding of human biology. Cellular and molecular morphologies give lots of information about the underlying biological processes. The ability to identify and describe the morphological information quantitative, objectively, and efficiently is critical. In this PhD project, we will investigate various computer vision, machine learning (especially deep learning), and statistical analysis methodologies to develop automated morphology analysis methods for microscopy images.

More research topics in Computer Vision and Biomedical Imaging can be found at http://www.cse.unsw.edu.au/~ysong/

A scholarship/stipend may be available.

For more information contact: Dr Yang Song (yang.song1@unsw.edu.au)

Computer Vision and Deep Learning for Cell-Image Based Drug Screening

Supervisor Team: Professor Erik Meijering and Dr John Lock

Project Summary: Biologists use multiparametric microscopy to study the effects of drugs on human cells. This generates multichannel image data sets that are too voluminous for humans to analyse by eye and require computer vision methods to automate the data interpretation. The goal of this PhD project is to develop, implement, and test advanced computer vision and deep learning methods for this purpose to help accelerate the challenging process of drug discovery for new cancer therapies. This project is in collaboration with the School of Medical Sciences (SoMS) and will utilise a new and world-leading cell image data set capturing the effects of 114,400 novel drugs on the biological responses (phenotypes) of >25 million single cells.

A scholarship/stipend may be available.

For more information contact: erik.meijering@unsw.edu.au, john.lock@unsw.edu.au

Medical Image Computing for Whole-Organ Assessment Using 3D Ultrasound

Supervisor Team: Professor Erik Meijering and Professor Arcot Sowmya

Project Summary: Current commercial 3D ultrasound systems for medical imaging studies often do not provide the ability to record volumes large enough to visualise entire organs. The first goal of this PhD project is to develop novel computational methods for fast and accurate image registration to digitally reconstruct whole organs from multiple ultrasound volumes. The second goal is to develop computer vision and deep learning methods for automated volumetric image segmentation and downstream statistical analysis. This project will be in collaboration with researchers from the UNSW School of Women’s and Children’s Health to improve monitoring organ development during pregnancy to support clinical diagnostics.

A scholarship/stipend may be available.

For more information contact: erik.meijering@unsw.edu.au, a.sowmya@unsw.edu.au

Deep Learning and Decision Support for Colon disease assessment

Supervisor Team: Prof Arcot Sowmya, A/Prof Lois Holloway (Ingham Medical Research Institute, Liverpool Hospital)

Project Summary: Decisions on the most appropriate treatment for diseases such as colorectal cancer and diverticulitis can be complex. Advanced imaging such as MRI and CT can provide information on the location of the disease compared to other anatomy and also functional information on the disease and surrounding organs. There is also the potential to gain additional information from these images using techniques such as radiomics. At Liverpool hospital there is a database of previous patient histories, including outcome as well as imaging information which we can use utilise in collaboration with medical specialists. This project will use machine learning and deep learning approaches to determine anatomical and disease boundaries and combine them with clinical and response data to model treatment response and develop treatment decision support tools. The incoming PhD student should ideally have a computer science qualification with research skills and an interest to develop deep learning and decision support techniques in the medical imaging field. Research in this area are subject to ethics approvals and institutional agreements.

A scholarship/stipend may be available.

For more information contact: a.sowmya@unsw.edu.au, lois.holloway@unsw.edu.au

Predicting the onset and progression of myopia (short-sightedness) using data mining, image analysis and deep learning techniques

Supervisor Team: Prof Arcot Sowmya, Prof Padmaja Sankaridurg (Brien Holden Vision Institute)

Project Summary: The prevalence of myopia (short sightedness) is expected to rise dramatically to affect nearly 50% of the global population by the year 2050. With the increase in myopia, the prevalence of high myopia, which is associated with greater risks of permanent ocular complications, is also expected to rise significantly and reach a global prevalence of 9.5% by the year 2050. Due to the increasing burden of the myopia epidemic, there is a need to identify children at risk of myopia and high-myopia so as to intervene early. A large amount of data is being collected for studying the incidence and progression of myopia in children, which has created an opportunity to analyse the multi-modal data using data mining, image analysis and deep learning techniques. The aim of the PhD project is to use the multimodal data sources and advanced data mining techniques to predict the onset and progression of myopia. The incoming PhD student should ideally have a computer science qualification with research skills and an interest to apply data mining and deep learning techniques in the ocular field. Research in this area are subject to ethics approvals and institutional agreements.

For more information contact: a.sowmya@unsw.edu.au, p.sankaridurg@bhvi.org

Health profiles and trajectories in late-life depression and suicide – a machine-learning approach

Supervisor Team: Prof Arcot Sowmya and Dr Simone Reppermund

Depression and self-harm represent substantial public health burdens in the older population. Depression is ranked by the WHO as the single largest contributor to global disability and is a major contributor to suicide. This project will use large linked administrative health datasets to examine health profiles, service use patterns and risk factors for suicide in older people with depression. Given the vast amount of data included in linked datasets, new ways of analysing the data are necessary to capture all relevant data signals. This project will generate a sound epidemiological and service evidence base that informs our understanding of health profiles and service system pathways in older people with depression and risk factors for trajectories into suicide.

For more information contact: a.sowmya@unsw.edu.au, s.reppermund@unsw.edu.au

Data & Knowledge Research Group
Large Scale Graph Data Processing

Supervisory team: Xuemin Lin, Wenjie Zhang 

Project Summary: Efficient Processing of Large Scale Multi-dimensional Graphs 

This project aims to develop novel approaches to process large scale graphs such as social networks, road networks, financial networks, protein interaction networks, etc. The project will focus on the three most representative types of problems against graphs, namely cohesive subgraph computation, frequent subgraph mining, and subgraph matching. The applications include anomaly detection, community search, fraud and crime detection.  

For more information contact: lxue@cse.unsw.edu.au or wenjie.zhang@cse.unsw.edu.au  

A scholarship/stipend may be available. 

Next-Generation Search on Social Networks

Supervisory team: Wei Wang, Xin Cao 

Project Summary: The immense popularity of online social networks has resulted in a rich source of data useful for a wide range of applications such as marketing, advertisement, law enforcement, health, and national security, to name a few. Ability to effectively and efficiently search required information from the huge amounts of social network data is crucial for such applications. However, current search technology suffers from several limitations such as inability to provide geographically relevant results, inadequately handling uncertainty in data and failing to understand the data and queries resulting in inferior search experience. This project aims to develop a next-generation search system for social network data by addressing all these issues. 

A scholarship/stipend may be available. 

For more information contact: weiw@cse.unsw.edu.au or xin.cao@unsw.edu.au  

Embedded Systems
Effects of Architecture Level Fault Injection in Embedded Processors 

Supervisory team: Sri Parameswaran 

Project Summary: Reliability is becoming an essential part in embedded processor design due to the fact that they are used in safety critical applications and they need to deal with sensitive information. The first phase in the design of reliable embedded systems involves the identification of faults that could be manipulated into a reliability problem. A technique that is widely used for this identification process is called fault injection and analysis. The aim of this project is to develop a fault injection and detection engine at the hardware level for an embedded processor. 

A scholarship/stipend may be available. 

For more information contact: sridevan@unsw.edu.au 

Networked Systems and Security
Aiolos

Supervisory team: Sanjay Jha, Salil Kanhere 

Project Summary: This project aims to develop scalable and efficient one-to-many communication, i.e., broadcast and multicast, algorithms in the next generation of WMNs that have multi-rate multi-channel nodes. This is a significant leap compared with the current state of the art of routing in WMNs which is characterised by unicast in a single-rate single-channel environment. 

A scholarship/stipend may be available. 

For more information contact: sanjay.jha@unsw.edu.au

Swimnet

Supervisory team: Mahbub Hanssan 

Project Summary: A major focuses of the Swimnet project will be to look at a QoS framework for multi-radio multi-channel wireless mesh networks. We also plan to develop Traffic engineering methodologies for multi-radio multi-channel wireless mesh networks. Guarding against malicious users is of paramount significance in WMN. Some of the major threats include greedy behaviour exploiting the vulnerabilities of the MAC layer, location-based attacks, and lack of cooperation between the nodes. The project plans to look at a number of such security concerns, and design efficient protection mechanisms (Mesh Security Architecture). 

A scholarship/stipend may be available. 

For more information contact: mahbub.hanssan@unsw.edu.au  

SENSAR

Supervisory team: Wen Hu  

Project Summary: The mission of the SENSAR (Sensor Applications Research) group is to investigate the systems and networking challenges in realising sensor network applications. Wireless sensor networks are one of the first real-world examples of "pervasive computing", he notion that small, smart and cheap, sensing and computing devices will eventually permeate the environment. Though the technologies still in its early days, the range of potential applications is vast - track bush fires, microclimates and pests in vineyards, monitor the nesting habits of rare sea-birds, and control heating and ventilation systems, let businesses monitor and control their work spaces etc. 

A scholarship/stipend may be available. 

For more information contact: wen.hu@unsw.edu.au

Service Orientated Computing
Cognition and Conversational AI-Enabled Services

Supervisory Team: Boualem Benatallah, Lina Yao, Fabio Casati

Project Summary: This project investigates the significant and challenging issues that underpin the effective integration of software-enabled services with cognitive and conversational interfaces. Our work builds upon advances in natural language processing, conversational AI and services composition.

We aim to advance the fundamental understanding of cognitive services engineering by developing new abstractions and techniques. We’re seeking to enable and semi-automate the augmentation of software and human services with crowdsourcing and generative model training methods, latent knowledge and interaction models. These models are essential for the mapping of potentially ambiguous natural language interactions between users and semi-structured artefacts (e.g., emails, PDF files), structured information (e.g., indexed data sets), apps and APIs.

For more information contact: b.benatallah@unsw.edu.au or lina.yao@unsw.edu.au

Exploration of a Hierarchy of Learning Models in Relation to Goals

Supervisory Team: Lina Yao and Defence Science & Technology Group

Project Summary: This research is supported by the Defence Science and Technology Group. It aims to develop intelligent methodologies to capture the environment in sufficient fidelity to evaluate (model and predict) what application/system changes need to occur to fulfill the requirements (goals) of the mission.

A scholarship/stipend may be available.

For more information contact: lina.yao@unsw.edu.au

Context and Activity Recognition for Personalised Behaviour Recommendation

Supervisory Team: Lina Yao, Boualem Benatallah and Quan Z. Sheng

Project Summary: The overall goal of this project is to develop novel machine learning and deep learning techniques that can accurately monitor and analyse human activities. These techniques will monitor and analyse daily living on a real-time basis and provide users with relevant personalised recommendations, improving their lifestyle through relevant recommendations.

A scholarship/stipend may be available.

For more information contact: lina.yao@unsw.edu.au or b.benatallah@unsw.edu.au

Context-Aware Intent Prediction for Human-Machine Cooperation Improvement

Supervisory Team: Lina Yao

Project Summary: This project is supported by Office of Naval Research Global (US Department of Navy). The aim of this project is to develop a software package for resilient context-aware human intent prediction for human-machine cooperation.

A scholarship/stipend may be available.

For more information contact: lina.yao@unsw.edu.au

Multi-Faceted Adaptive Trust Management in Federated/Distributed Data and AI Systems

Supervisory Team: Lina Yao and Xiwei Xu

Project Summary: The research is supported by our collaborative research project with Data61. The aim is to develop an integrated end-to-end framework for fostering trust in Federated/Distributed AI systems.

A scholarship/stipend may be available.

For more information contact: lina.yao@unsw.edu.au or xiwei.xu@unsw.edu.au

Efficient Big Data Analytics Framework for Blockchain Data and Events

Supervisory Team: Helen Paik

Project Summary: Micro-transactions stored in blockchain create transparent and traceable data and events, providing burgeoning industry disruptors an instrument for trust-less collaborations. However, the blockchain data and its’ models are highly diverse. To fully utilise its potential, a new technique to efficiently retrieve and analyse the data at scale is necessary.

This project addresses a significant gap in current research, producing a new data-oriented system architecture and data analytics framework optimised for online/offline data analysis across blockchain and associated systems. The outcome will strongly underpin blockchain data analytics at scale, fostering wider and effective adoption of blockchain applications.

A scholarship/stipend may be available.

For more information contact: h.paik@unsw.edu.au

Knowledge Engineering for Business Analytics

Supervisory Team: Fethi Rabhi and Boualem Benatallah

Project Summary: All modern organisations use some form of analytics tools. Configuring, using and maintaining these tools can be very costly for an organisation. Analytics tools require expertise from a range of specialties, including business insight, state-of-the-art modelling approaches and tools such as AI and machine learning as well as efficient data management practices. A knowledge engineering approach can deliver flexible and custom data analytics applications that align with organisational objectives and existing IT infrastructures. This model uses existing resources and knowledge within the organisation. The project uses semantic-web based knowledge modelling techniques to build a comprehensive view related to an organisation’s analytics objectives while leveraging open knowledge and open data to expand its scope and reduce costs.

We aim to help organisations utilise and reuse public and organizational knowledge efficiently when conducting data analytics. Our work also involves the rapid development and deployment of analytics applications that suit emerging analytics needs, plugging new data and software on-demand using new approaches such as APIs and cloud services. The proposed techniques have already been piloted in the areas of house price prediction in collaboration with the NSW Government and portfolio management in collaboration with Ignition Wealth.

A scholarship/stipend may be available.

For more information contact: f.rabhi@unsw.edu.au or b.benatallah@unsw.edu.au

Theoretical Computer Science
Blockchain, Smart Contracts and Cryptocurrency

Supervisory team: Ron van deMeyden 

Project Summary: The technology of cryptocurrency and its concepts can be broadly applicable to range of applications include financial services, legal automation, health informatics and international trade. These underlying ideas and the emerging infrastructure for these applications is known as ‘Distributed Ledger Technology’. 

A scholarship/stipend may be available. 

For more information contact: meyden@cse.unsw.edu.au  

Trustworthy Systems
seL4

Supervisory team: Gernot HeiserJune Andronick 

Project Summary: seL4, the secure embedded L4 microkernel, is a key element of our research program. We developed seL4 to provide a reliable, secure, fast and verified foundation for building trustworthy systems. seL4 enforces security within componentised system architectures by ensuring isolation between trusted and untrusted system components, and by carefully controlling software access to hardware devices in the system. 

A scholarship/stipend may be available. 

Form more information contact: gernot@unsw.edu.au or June.Andronick@data61.csiro.au