Skip to content

Information and Communication Technology Research

We conduct research into topics across the breadth of the ICT spectrum. Our four strategic research themes are Smart Services and Systems; Games and Creative Technologies; Transformative Information Systems; and Human Interface Technologies.

Strategic investments and initiatives, such as the HIT Lab, help us enhance and improve our research scope and output. Our innovative platforms and research topics attract high performing researchers from around the world as well government and industry collaborations, which provide ongoing benefit both to our students and our researchers.

Our research themes

  Study with us

Every industry both within Australia and around the world needs ICT graduates, who can combine technical skills with business know-how. Our research degrees offer advanced technical skills and work integrated learning across information technology and systems, and design technology. They contain a large proportion of professional development, meaning graduates gain skills and knowledge ideal for taking an ICT career to the next level, or leveraging existing qualifications for a move into the ICT industry.

Available Research Degree Projects

A research degree candidate may develop their own research project in collaboration with their supervisors or apply for one of our currently available projects below:

Applicants interested in a specific project should first contact the supervisor listed and then find out more about our Entry Requirements, Scholarships if relevant, and then Apply Now.

Closing Date

1st December 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

Facial Emotion Recognition is the process of identifying human emotion, most typically from human facial expressions. AI-based facial emotion detection can be applied in a variety of fields such as Driver Fatigue Monitoring, Marketing, and Entertainment. Driver Fatigue Monitoring employs facial emotion detection to determine whether a driver is in a state of fatigue so as to appropriately intervene in the behaviour of the driver to avoid possible accidents. Advertisers and market researchers try to use consumer emotional engagement with digital content, such as videos and ads, to create the best ads and optimizing media spend.

The popularity of deep learning approaches in the domain of emotion recognition may be mainly attributed to its success in related AI applications such as Computer Vision. Well-known deep learning algorithms include different architectures of Deep Neural Network (DNN) such as Convolutional Neural Network (CNN), Long Short-term Memory (LSTM), and Extreme Learning Machine (ELM). Deep Neural Networks have increasingly been employed to learn discriminative representations for automatic facial emotion recognition with some success, however, certain significant issues remain unresolved. Such issues include: Occlusion-robust and pose-invariant issues; Dataset bias and imbalanced distribution; Optimal DNN parameter set; Multimodal effect. In this project, you will develop new deep learning algorithms to overcome these and possibly other issues for faster, more reliable, and more accurate facial emotion detection.

Eligibility

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Shuxiang Xu for further information.

Closing Date

31st December 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

Given the important challenges associated with the processing of brain signals obtained from neuroimaging modalities, fuzzy sets, neural networks and evolutional systems have been proposed as a useful and effective framework for the modelling and understanding of brain activity patterns as well as to enable a direct communication pathway between the brain and external devices (brain computer/machine interfaces). However, most of the research so far has focused on lab-based applications in constrained scenarios, which cannot be extrapolated to realistic field contexts. Considering the decoding of brain activity, the computational Intelligence models, including fuzzy sets, neural networks, and evolutional computation, provide an excellent tool to overcome the challenge of learning from brain activity patterns that are very likely to be affected by non-stationary behaviours and high uncertainty. The application of computational Intelligence methods to learning and modeling​ has recently demonstrated its remarkable usefulness for coping with the effects of extremely noisy environments, as well as the variability and dynamicity of brain signals. Additionally, neurobiological studies have suggested that the behaviour of neural cells exhibits functional patterns that resemble the properties of intelligent computation to encode logical perception. This paves the way for developing new computational intelligence techniques based on intelligence abstractions that foster the capabilities for modeling and understanding brain function from a quantitative point of view.

Eligibility

Please refer to the Entry Requirements for a {Doctor of Philosophy/Master of Research} degree.

The following eligibility criteria also apply:

  • The project is open to domestic and international candidates
  • The PhD must be undertaken on a full-time basis
  • Applicants must already have been awarded a first class Honours degree or hold equivalent qualifications or relevant and substantial research experience in an appropriate sector

Selection Criteria

Knowledge and skills that will be ranked highly include:

  • Applicants must be able to demonstrate strong research and analytical skills
  • Data Mining and Predictive Analytics Skills
  • Foundational programming skills
  • Statistics

More Information

Please contact Zehong Cao for more information.

Closing Date

31st December 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

In this project, HDR students implement and develop of state-of-the-art machine learning and deep learning models, especially in deep reinforcement learning algorithms to easily train intelligent agents for various games. The research goal is to speed up the learning process of multiple agents and allow each agent receives higher rewards in a game scenario. These trained agents can be presented in the demo workshop and can be used for multiple purposes, including testing of game builds and controlling behaviour.

In this project, we used the OpenAI Gym and Unity platform, which have been developed for creating and interacting with simulation environments. Specifically, the Unity ML Agents Toolkit is an open-source Unity plugin that enables games and simulations to serve as environments for training intelligent agents. This project will use this toolkit to develop dynamic multi-agent interaction, and agents can be trained using reinforcement learning, imitation learning, neuro-evolution, or other machine learning methods through a simple-to-use Python API.

Additionally, this project is mutually beneficial for both students and AI researchers as it provides a central platform where advances in AI can be evaluated on rich environments and then made accessible to the industry and research developer communities.

The following eligibility criteria apply to this project:
  • See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree
  • The project is open to domestic and international candidates
  • Research must be undertaken on a full-time basis
  • Applicants must already have been awarded a first class Honours degree or hold equivalent qualifications or relevant and substantial research experience in an appropriate sector
  • Applicants must be able to demonstrate strong research and analytical skills
  • Candidate from a variety of disciplinary backgrounds are eligible to apply
Selection Criteria
  • Data Mining and Predictive Analytics Skills
  • Strong programming skills
  • Statistics experience
Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Zehong Cao for further information.

Closing Date

31st December 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

Deep Learning recently lends itself extremely well to the research in computer vision domain where hierarchical structures of computational neurons can learn predictive features to effectively make predictive decisions. For example, in health care, deep learning is becoming also popular among medical imaging researchers who are looking for great tools to process a large number of images produced by scanners.

The impact of this to the society is potential and attract more and more attention from health care experts who have been looking for better methods to reduce the error rates in diagnosis. However, the most common deep learning models used for image processing are CNN-based which is a complex black-box consisting of millions of parameters that confused the experts of why the decisions are made. As a result, there is an increasing scepticism from those who do not want to use deep learning because of the lack of explainability.

In this research, the student will improve the transparency of deep neural networks to provide insights of the decision-making process. The topics of interest are (but not limited to):

  • Medical imaging (eye disease detection, knee pain prevention, etc.)
  • Visual reasoning, image captioning
Eligibility
  • The project is open to Australian (domestic) and international candidates
  • The PhD must be undertaken on a full-time basis
  • Honours degree/Master degree or hold equivalent qualifications or relevant and substantial research experience in an appropriate sector
  • Applicants must meet English requirements, or be able to do so before commencement

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Dr Son Tran for further information.

Closing Date

14th May 2021

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

The Research Project

As learner interaction in an online educational environment leaves a lot of digital traces behind, vast data sets of students’ online activities are available, which is known as Big data. Data and analytics in education, teaching and learning has attained great interest, resulting high-quality research into models, methods, technologies, and impact of analytics in education area. Big data and learning analytics with Artificial Intelligence (AI) is greatly extending the power of computers to revolutionise education sector. Educational data mining techniques discover meaningful patterns in these large datasets to create probabilistic and predictive models such as student success algorithms, understand and optimise learning and the environment. Learning analytics and AI are not panaceas for addressing all the issues and decisions faced by higher education but become part of the solution to enhance and transforms the way to support learning process.

The aim of the project is to investigate the deployment of AI techniques and analytical model/algorithm for improving learning analytics and for discovering the meaningful patterns in the large datasets of students to improve educational processes.

Eligibility
  • Experience with programming
  • Critical thinking

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Dr Soonja Yeom for further information.

Closing Date

12th May 2021

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

The Research Project

Haptic technology is also widely used in education to enhance student's learning experiences with anatomy as it allows physical interaction with anatomical structures  (Kup-Sze, Hanqiu & Pheng-Ann 2003; Reid, Shapiro & Louw 2018; Yeom et al. 2013). It is evident that AR and haptic technologies encourage student learning of anatomy through exposure of the body visually by 3-D modelling, and physically with tactile feedback. There is a huge educational potential to apply AR and haptics in education of anatomy. However, it has not yet been widely researched or evaluated.

The purpose of the proposed research is to investigate the use of interactive 3D anatomical simulation, used in conjunction with haptic feedback, to determine if it improves students' learning. The research will compare the effectiveness of the combination of AR and Haptic technology to their use independently, as well as comparing it to existing learning methods, such as 2D images and interactive resources (CD/DVD).

The research will be undertaken into four stages:

  • Generation of interactive 3D anatomical models in a mobile device;
  • Applying haptic feedback when a user touches/interacts with the 3D models;
  • Integrating the simulation of AR with haptic feedback);
  • Comparison and Evaluation of effectiveness of AR/haptic education in anatomy against existing methods.
Eligibility

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Dr Soonja Yeom for further information.

Closing Date

31st May 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

Due to the advent of technologies such as 5G and IoT, the increase in network traffic has been exponential; consequently, presenting a larger set of opportunities for intrusion attacks on network traffic. Furthermore, the complexity and nature of these attacks can surely go undetected as they can easily be impersonated as normal behaviour (For example, DoS - Denial of Service attacks).

Due to high levels of work intensity and frequent turnovers, it is impractical for an organisation to leverage human intervention; especially, early-career engineers as the nature of this work requires higher understandings of hacking techniques.
In this project, we will conduct research that utilises Machine Learning to develop a model that can be applied to practice using payload detection in real-world Intrusion Detection (IDS) and Intrusion Prevention Systems (IPS). The targeted high detection rate of our model will significantly reduce the network payloads that need to be verified; consequently, overcoming human dependency.

Furthermore, we will devise a distributed methodology via Blockchain to detect not only network attacks but also intrusions based on abnormal behaviours that can be easily missed by an engineer. This methodology can be a novelty for Collaborative Intrusion Detection Systems (CIDS) to detect attacks such as Denial of Service (DoS) with high accuracy.

Eligibility
  • Strong research and analytical skills
  • Research and/or Development background in the areas of Blockchain, software architecture and distributed systems
  • Understanding of distributed application Development pertaining to Blockchain
  • Publication record or relevant industry experience

Applicants from the following disciplines are eligible to apply:

  • Computer Science
  • Software Engineering
  • Information Technology
  • Computer Engineering

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Muhammad Bilal Amin for further information.

Closing Date

31st May 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

Blockchain is a technology to store data securely and transparently using distributed and crypto techniques. It is a data storage of the future with security, immutability, and transparency built-in. With such an evolutionary feature set, blockchain has currently gained traction in its adoption ratio. However, the required momentum to take this technology to the future is still lagging due to the core limitation of its inability to interoperate between heterogeneous and multiple chains.

Considering this an opportunity, in this project, we will research to find the resolution to the blockchain interoperability challenge that enables arbitrary data sharing among heterogeneous and multiple blockchain networks.

The current block in the chain is highly specialized and designed to handle transaction-oriented records; consequently, limiting the possibility of flexibility and extensibility required to achieve an interoperable distributed data structure. Therefore, for general-purpose storage and sharing of arbitrary data, the block structure needs to be generalized with schema-based definitions to allow global data interpretation. Therefore, in this project, we will research on devising a markup-like meta-structure definition scheme to represent a generic data block structure within a blockchain network. Furthermore, a possible markup-translation algorithm that can facilitate arbitrary data exchange among multiple and heterogeneous blockchains.

Eligibility
  • Strong research and analytical skills
  • Research and/or Development background in the areas of Blockchain, software architecture and distributed systems
  • Understanding of distributed application Development pertaining to Blockchain
  • Publication record or relevant industry experience

Applicants from the following disciplines are eligible to apply:

  • Computer Science
  • Software Engineering
  • Information Technology
  • Computer Engineering

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Muhammad Bilal Amin for further information.

Closing Date

31st May 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filled earlier

The Research Project

In the past decade, blockchain has been one of the most revolutionary technologies that will have a far-reaching transformational effect across almost every industry in the coming years. A lot of organizations are examining its benefits for the sake of industries such as healthcare, law enforcement, asset management, forestry, agriculture, voting, and notarization. Given that every organization needs to share data, knowledge and assets; blockchains necessarily need to interoperate with each other.

Blockchain interoperability not only means the possibility to share and exchange, digital assets and arbitrary data but also to reference chain code across heterogeneous and multiple blockchain networks. However, the smart contract/chain code in a blockchain can be written in several different languages, thus, limiting the possibility of code reusability among blockchain networks.

In this project, we will conduct research to devise a chain code virtualization methodology for an interoperable blockchain ecosystem where the scale of execution of smart contracts is beyond a single block or a single chain deployment. Thus, enabling a new generation of distributed applications that can be built on the aggregation of smart contracts, written in different languages, like workflows and orchestrations

Eligibility
  • Strong research and analytical skills
  • Research and/or Development background in the areas of Blockchain, software architecture and distributed systems
  • Understanding of distributed application Development pertaining to Blockchain
  • Publication record or relevant industry experience

Applicants from the following disciplines are eligible to apply:

  • Computer Science
  • Software Engineering
  • Information Technology
  • Computer Engineering

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Muhammad Bilal Amin for further information.

Closing Date

1st October 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filler earlier

The Research Project

Trust is a term used in many fields, including computer science, and has many different meanings [1] [2]. In this project, trust is used to generate some expectation of success in a collaboration between two separate entities/agents. Most of trust models assume single and homogeneous trust relationship between agents [3}. However, most of these models cannot handle dynamic environments.

Contextual information plays important roles in trust evaluation. Especially as ground truth is not available in many complex environments, trust is closely related with contextual factors including social relationships among entities, spatial temporal information, features and types of services, etc. To overcome some limitations in existing trust mining approaches, in the research we will investigate how to utilize contextual information in trust mining and develop a robust mechanism which can allow more accurate and reasonable trust evaluations.

In this project, the student will propose a context-aware trust model, which can take contextual information into trust analysis. The proposed model will be applied in open dynamic environments, and to improve collaborations among agents with different capabilities and skills, i.e., heterogeneous. Simulation-based experiments will be conducted to evaluate the performance of the proposed model.

References:

  1. Marsh, S.P., Formalising trust as a computational concept. Ph.D. dissertation, University of Stirling, Apr. 1994.
  2. Sabater, J. and C. Sierra, REGRET: reputation in gregarious societies, in Proceedings of the fifth international conference on Autonomous agents. 2001, ACM: Montreal, Quebec, Canada. p. 194-195.
  3. Tang, J., H. Gao, and H. Liu, mTrust: discerning multi-faceted trust in a connected world, in Proceedings of the fifth ACM international conference on Web search and data mining. 2012, ACM: Seattle, Washington, USA. p. 93-102.
Eligibility
  • The project is open to Australian (domestic) and international candidates
  • The PhD must be undertaken on a full-time basis
  • Honours degree/Master degree or hold equivalent qualifications or relevant and substantial research experience in an appropriate sector
  • Applicants must meet English requirements, or be able to do so before commencement

Applicants from the following disciplines are eligible to apply:

  • Computer Science
  • Information and Computing Technologies

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Dr Quan Bai for further information.

Closing Date

1st December 2021*

Applicants should contact the primary supervisor, and submit their Expression of Interest (EOI) and Application as soon as possible.

*unless filler earlier

The Research Project

Knowledge graphs (KGs) are large networks of entities and their semantic relationships.  It has been widely applied in multiple areas, including information retrieval, situation awareness and recommender systems. A KG can be represented as a set of triples (h, t ,r) in which h (head) and t (tail) are entities (nodes), and r (relation) is  the relation (edge) between the two entities. KG embedding is to represent the entities and relations in a continuous vector space. This is a critical process to make KG semantic meaningful and machine understandable, and normally achieved by using machine learning methods. Negative sample generation is an important process for KG embedding. It provides sufficient training samples for the KG embedding, and fill the vector to a continuous space.

KG was first designed to formalize unstructured natural language data. With the development of KG techniques, researchers are now exploring the use of KG in other domains, especially IoT, Cyber Physical Systems (CPS) and Cybersecurity. However, traditional KG mining and KG embedding methods have been mainly focused on NLP data, and are not suitable for the latest applications. This project will investigate the limitations of existing KG embedding and mining methods, and design novel algorithms that can mine KG data more effectively and handle the dynamics from complex application domains.

  1. Yongqi Zhang, Quanming Yao, Yingxia Shao and Lei Chen, NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding, https://arxiv.org/pdf/1812.06410.pdf
  2. Yantao  Jia, Yuanzhuo  Wang, Xiaolong  Jin, Hailun  Lin, Xueqi  Cheng , Knowledge Graph Embedding: A Locally and Temporally Adaptive Translation-Based Approach, ACM Transactions on the Web (TWEB), 2017
Eligibility
  • The project is open to Australian (domestic) and international candidates
  • The PhD must be undertaken on a full-time basis
  • Honours degree/Master degree or hold equivalent qualifications or relevant and substantial research experience in an appropriate sector
  • Applicants must meet English requirements, or be able to do so before commencement

Applicants from the following disciplines are eligible to apply:

  • Computer science
  • ICT
  • Mathematical sciences
  • Electrical engineering

See the following web page for entry requirements: www.utas.edu.au/research/degrees/what-is-a-research-degree

Application Process

Applicants who require more information or are interested in this specific project should first contact the listed Supervisor. Information and guidance on the application process can be found on the Apply Now website.

Information about scholarships is available on the Scholarships webpage.

More Information

Please contact, Dr Quan Bai for further information.

  Partner with us

Information and Communication Technology seeks to broaden our impact by partnering with small-medium-large industry and government agencies. There are many ways to engage with us. We excel in industry collaborative research focussed on transformation of digital technologies in the business practices. We are eager to engage with local, regional, national, international collaborators to help facilitate with the digital revolution.

You will have access to our expertise across our ICT domains of research – artificial intelligence, machine learning, internet of things, game design and development, e-logistics and advanced human computer interface technologies – and especially our expertise in adapting ICT innovative solutions to solve complex problems.