Projects by Tags

Real-time EH&S Intervention to Improve Site Safety

This project integrates AI-based visual models with augmented reality (AR) to address fall-from-height (FFH) risks in high-rise construction. In collaboration with Lendlease, we explore how these technologies can improve the speed, accuracy, and scalability of hazard detection compared to manual inspections. We developed proof-of-concept prototypes that combine AI-driven computer vision with AR to enable real-time analysis, automated reporting, and immersive inspection and training.

ProDAIS: GenAI-Facilitated Collaborative Learning System for Productive Group Discussion in Information Technology Education

This study explored how Generative AI can support productive group discussions by acting as a low-interference regulatory partner rather than a content generator. Using a Design-Based Research approach, we developed and evaluated ProDAIS, a lightweight AI facilitator grounded in SSRL and APT frameworks, with results showing high usability, low cognitive load, and effective support for participation balance and time management.

Implementation and comparison of large language models for ICU notes transcription and summarisation

This project focuses on the comparison and potential implementation of Large Language Models (LLMs) aiming to assist the clinical handovers process in an Intensive Care Unit (ICU) environment. This process is commonly identified as “the transfer of professional responsibility and accountability for some or all aspects of care for a patient and generally occurs between the shifts of supervising nursing staff.

A Context-Aware Computing Framework for Performance Improvement in Distributed Vision-Based Augmented Reality

This project aims to address the limitations identified in the current state of the art by designing and evaluating a context-aware computing framework for distributed vision-based AR systems.

Intelligent Control and Manufacturing in the Agentic Era

This project proposes a simulation-based research framework that investigates how VLA-inspired decision-making can support adaptive robotic behaviours in tasks such as storage, retrieval, sorting, and replenishment. By focusing on system integration, realistic task modelling, and evaluation under dynamic operational conditions, this research aims to contribute toward more practical and scalable intelligent manufacturing systems in the agentic era.

Exploring Free-Sketch Stylus-Based Text Input for Mixed Reality Interfaces

This research examines text input methods in virtual and mixed reality, highlighting limitations in speed, accuracy, and usability across keyboards, speech, and gesture-based approaches, and identifies stylus-based input as a promising alternative. It proposes a system that converts 3D stylus trajectories into text using machine learning, aiming to provide a more natural, efficient, and adaptable input method for immersive environments.

Towards Intelligent Immersive Healthcare: A Systematic Literature Review

This systematic literature review examines how Augmented Reality (AR) and Artificial Intelligence (AI) are being integrated to support medical clinical trials, with a focus on where AI augments AR (e.g., real-time sensing, decision support, adaptive guidance) across trial workflows. It synthesises current integration patterns, application areas, and research gaps to inform the design of more intelligent, immersive trial tools.

Behavioural Skills Training System for Emergency Services Workers

The project tests flexible virtual personas that vary in tone, emotion, and resistance to create adaptive role play. It aims to improve the quality, accessibility, and scalability of simulation training, especially for regional and remote learners. Educators can supervise sessions in real time or review interactions through secure recordings and analytics, strengthening feedback loops.

AI-facilitated Brain Tumour Segmentation in Immersive Environments

This project develops an AI-driven system to automate brain tumour segmentation from complex 3D MRI scans, reducing the need for time-consuming and error-prone manual annotation by medical experts. It combines deep learning models with immersive visualisation (e.g., AR/VR), allowing clinicians to interact with and refine tumour predictions directly in 3D space.

AI-facilitated AR Handover System for ICU Nurses

This project addresses the challenges in the nurse handover process in critical care settings by designing an integrated solution that leverages immersive and AI technologies. We propose an integrated approach consisting of the following innovative concepts: in-situ augmented reality (AR) overlays, an AI-assisted conversational agent, and a cross-reality collaborative model.

Real-time EH&S Intervention to Improve Site Safety

This project integrates AI-based visual models with augmented reality (AR) to address fall-from-height (FFH) risks in high-rise construction. In collaboration with Lendlease, we explore how these technologies can improve the speed, accuracy, and scalability of hazard detection compared to manual inspections. We developed proof-of-concept prototypes that combine AI-driven computer vision with AR to enable real-time analysis, automated reporting, and immersive inspection and training.

Fusion of Infrastructure-Based 3D Scene Reconstructions and Mobile Visual-Inertial Odometry for Drift-Resilient Indoor Augmented Reality

This project uses a comparative experimental design to evaluate a baseline smartphone-only AR navigation system against a hybrid system supported by sparse infrastructure cameras. Through a phased approach, first extending the Monash campus app into an AR prototype, then integrating stereo camera-based 3D reconstructions, the study investigates whether periodic infrastructure “checkpoints” can reduce drift and improve robustness in indoor AR navigation under controlled lab conditions.

A Context-Aware Computing Framework for Performance Improvement in Distributed Vision-Based Augmented Reality

This project aims to address the limitations identified in the current state of the art by designing and evaluating a context-aware computing framework for distributed vision-based AR systems.

Towards Intelligent Immersive Healthcare: A Systematic Literature Review

This systematic literature review examines how Augmented Reality (AR) and Artificial Intelligence (AI) are being integrated to support medical clinical trials, with a focus on where AI augments AR (e.g., real-time sensing, decision support, adaptive guidance) across trial workflows. It synthesises current integration patterns, application areas, and research gaps to inform the design of more intelligent, immersive trial tools.

SafePhARm: Safe and Efficient Pharmacy Practice Through Augmented Reality

SafePhARm project explores the use of Augmented Reality (AR) to provide context-aware information directly within pharmacists’ field of view. It aims to identify workflow inefficiencies, co-design AR interfaces with pharmacists, and develop a proof-of-concept prototype. The system will be evaluated in a controlled environment to assess its impact on task efficiency, usability, and cognitive load, ultimately generating design guidelines and evidence for AR-enabled digital health solutions.

AI-facilitated AR Handover System for ICU Nurses

This project addresses the challenges in the nurse handover process in critical care settings by designing an integrated solution that leverages immersive and AI technologies. We propose an integrated approach consisting of the following innovative concepts: in-situ augmented reality (AR) overlays, an AI-assisted conversational agent, and a cross-reality collaborative model.

ProDAIS: GenAI-Facilitated Collaborative Learning System for Productive Group Discussion in Information Technology Education

This study explored how Generative AI can support productive group discussions by acting as a low-interference regulatory partner rather than a content generator. Using a Design-Based Research approach, we developed and evaluated ProDAIS, a lightweight AI facilitator grounded in SSRL and APT frameworks, with results showing high usability, low cognitive load, and effective support for participation balance and time management.

SafePhARm: Safe and Efficient Pharmacy Practice Through Augmented Reality

SafePhARm project explores the use of Augmented Reality (AR) to provide context-aware information directly within pharmacists’ field of view. It aims to identify workflow inefficiencies, co-design AR interfaces with pharmacists, and develop a proof-of-concept prototype. The system will be evaluated in a controlled environment to assess its impact on task efficiency, usability, and cognitive load, ultimately generating design guidelines and evidence for AR-enabled digital health solutions.

Behavioural Skills Training System for Emergency Services Workers

The project tests flexible virtual personas that vary in tone, emotion, and resistance to create adaptive role play. It aims to improve the quality, accessibility, and scalability of simulation training, especially for regional and remote learners. Educators can supervise sessions in real time or review interactions through secure recordings and analytics, strengthening feedback loops.

AI-facilitated AR Handover System for ICU Nurses

This project addresses the challenges in the nurse handover process in critical care settings by designing an integrated solution that leverages immersive and AI technologies. We propose an integrated approach consisting of the following innovative concepts: in-situ augmented reality (AR) overlays, an AI-assisted conversational agent, and a cross-reality collaborative model.

Real-time EH&S Intervention to Improve Site Safety

This project integrates AI-based visual models with augmented reality (AR) to address fall-from-height (FFH) risks in high-rise construction. In collaboration with Lendlease, we explore how these technologies can improve the speed, accuracy, and scalability of hazard detection compared to manual inspections. We developed proof-of-concept prototypes that combine AI-driven computer vision with AR to enable real-time analysis, automated reporting, and immersive inspection and training.

A Context-Aware Computing Framework for Performance Improvement in Distributed Vision-Based Augmented Reality

This project aims to address the limitations identified in the current state of the art by designing and evaluating a context-aware computing framework for distributed vision-based AR systems.

Impacts of Adaptive Contextual Immersive Environments in ProxSituated Data Analytics

This research explores how context-dependent memory influences users’ ability to interpret and recall insights in prox-situated data analytics. This work examines how physical and spatial context, such as environment, viewpoint, and interaction modality, affects understanding and memory retention during analysis. The goal is to inform the design of immersive and situated analytics systems that better support cognition and decision-making.

Implementation and comparison of large language models for ICU notes transcription and summarisation

This project focuses on the comparison and potential implementation of Large Language Models (LLMs) aiming to assist the clinical handovers process in an Intensive Care Unit (ICU) environment. This process is commonly identified as “the transfer of professional responsibility and accountability for some or all aspects of care for a patient and generally occurs between the shifts of supervising nursing staff.

SafePhARm: Safe and Efficient Pharmacy Practice Through Augmented Reality

SafePhARm project explores the use of Augmented Reality (AR) to provide context-aware information directly within pharmacists’ field of view. It aims to identify workflow inefficiencies, co-design AR interfaces with pharmacists, and develop a proof-of-concept prototype. The system will be evaluated in a controlled environment to assess its impact on task efficiency, usability, and cognitive load, ultimately generating design guidelines and evidence for AR-enabled digital health solutions.

AI-facilitated Brain Tumour Segmentation in Immersive Environments

This project develops an AI-driven system to automate brain tumour segmentation from complex 3D MRI scans, reducing the need for time-consuming and error-prone manual annotation by medical experts. It combines deep learning models with immersive visualisation (e.g., AR/VR), allowing clinicians to interact with and refine tumour predictions directly in 3D space.

AI-facilitated AR Handover System for ICU Nurses

This project addresses the challenges in the nurse handover process in critical care settings by designing an integrated solution that leverages immersive and AI technologies. We propose an integrated approach consisting of the following innovative concepts: in-situ augmented reality (AR) overlays, an AI-assisted conversational agent, and a cross-reality collaborative model.

Impacts of Adaptive Contextual Immersive Environments in ProxSituated Data Analytics

This research explores how context-dependent memory influences users’ ability to interpret and recall insights in prox-situated data analytics. This work examines how physical and spatial context, such as environment, viewpoint, and interaction modality, affects understanding and memory retention during analysis. The goal is to inform the design of immersive and situated analytics systems that better support cognition and decision-making.

Fusion of Infrastructure-Based 3D Scene Reconstructions and Mobile Visual-Inertial Odometry for Drift-Resilient Indoor Augmented Reality

This project uses a comparative experimental design to evaluate a baseline smartphone-only AR navigation system against a hybrid system supported by sparse infrastructure cameras. Through a phased approach, first extending the Monash campus app into an AR prototype, then integrating stereo camera-based 3D reconstructions, the study investigates whether periodic infrastructure “checkpoints” can reduce drift and improve robustness in indoor AR navigation under controlled lab conditions.

Fusion of Infrastructure-Based 3D Scene Reconstructions and Mobile Visual-Inertial Odometry for Drift-Resilient Indoor Augmented Reality

This project uses a comparative experimental design to evaluate a baseline smartphone-only AR navigation system against a hybrid system supported by sparse infrastructure cameras. Through a phased approach, first extending the Monash campus app into an AR prototype, then integrating stereo camera-based 3D reconstructions, the study investigates whether periodic infrastructure “checkpoints” can reduce drift and improve robustness in indoor AR navigation under controlled lab conditions.

Implementation and comparison of large language models for ICU notes transcription and summarisation

This project focuses on the comparison and potential implementation of Large Language Models (LLMs) aiming to assist the clinical handovers process in an Intensive Care Unit (ICU) environment. This process is commonly identified as “the transfer of professional responsibility and accountability for some or all aspects of care for a patient and generally occurs between the shifts of supervising nursing staff.

ProDAIS: GenAI-Facilitated Collaborative Learning System for Productive Group Discussion in Information Technology Education

This study explored how Generative AI can support productive group discussions by acting as a low-interference regulatory partner rather than a content generator. Using a Design-Based Research approach, we developed and evaluated ProDAIS, a lightweight AI facilitator grounded in SSRL and APT frameworks, with results showing high usability, low cognitive load, and effective support for participation balance and time management.

Towards Intelligent Immersive Healthcare: A Systematic Literature Review

This systematic literature review examines how Augmented Reality (AR) and Artificial Intelligence (AI) are being integrated to support medical clinical trials, with a focus on where AI augments AR (e.g., real-time sensing, decision support, adaptive guidance) across trial workflows. It synthesises current integration patterns, application areas, and research gaps to inform the design of more intelligent, immersive trial tools.

Intelligent Control and Manufacturing in the Agentic Era

This project proposes a simulation-based research framework that investigates how VLA-inspired decision-making can support adaptive robotic behaviours in tasks such as storage, retrieval, sorting, and replenishment. By focusing on system integration, realistic task modelling, and evaluation under dynamic operational conditions, this research aims to contribute toward more practical and scalable intelligent manufacturing systems in the agentic era.

Behavioural Skills Training System for Emergency Services Workers

The project tests flexible virtual personas that vary in tone, emotion, and resistance to create adaptive role play. It aims to improve the quality, accessibility, and scalability of simulation training, especially for regional and remote learners. Educators can supervise sessions in real time or review interactions through secure recordings and analytics, strengthening feedback loops.

Impacts of Adaptive Contextual Immersive Environments in ProxSituated Data Analytics

This research explores how context-dependent memory influences users’ ability to interpret and recall insights in prox-situated data analytics. This work examines how physical and spatial context, such as environment, viewpoint, and interaction modality, affects understanding and memory retention during analysis. The goal is to inform the design of immersive and situated analytics systems that better support cognition and decision-making.

Intelligent Control and Manufacturing in the Agentic Era

This project proposes a simulation-based research framework that investigates how VLA-inspired decision-making can support adaptive robotic behaviours in tasks such as storage, retrieval, sorting, and replenishment. By focusing on system integration, realistic task modelling, and evaluation under dynamic operational conditions, this research aims to contribute toward more practical and scalable intelligent manufacturing systems in the agentic era.

Exploring Free-Sketch Stylus-Based Text Input for Mixed Reality Interfaces

This research examines text input methods in virtual and mixed reality, highlighting limitations in speed, accuracy, and usability across keyboards, speech, and gesture-based approaches, and identifies stylus-based input as a promising alternative. It proposes a system that converts 3D stylus trajectories into text using machine learning, aiming to provide a more natural, efficient, and adaptable input method for immersive environments.

Exploring Free-Sketch Stylus-Based Text Input for Mixed Reality Interfaces

This research examines text input methods in virtual and mixed reality, highlighting limitations in speed, accuracy, and usability across keyboards, speech, and gesture-based approaches, and identifies stylus-based input as a promising alternative. It proposes a system that converts 3D stylus trajectories into text using machine learning, aiming to provide a more natural, efficient, and adaptable input method for immersive environments.

Towards Intelligent Immersive Healthcare: A Systematic Literature Review

This systematic literature review examines how Augmented Reality (AR) and Artificial Intelligence (AI) are being integrated to support medical clinical trials, with a focus on where AI augments AR (e.g., real-time sensing, decision support, adaptive guidance) across trial workflows. It synthesises current integration patterns, application areas, and research gaps to inform the design of more intelligent, immersive trial tools.

Behavioural Skills Training System for Emergency Services Workers

The project tests flexible virtual personas that vary in tone, emotion, and resistance to create adaptive role play. It aims to improve the quality, accessibility, and scalability of simulation training, especially for regional and remote learners. Educators can supervise sessions in real time or review interactions through secure recordings and analytics, strengthening feedback loops.

AI-facilitated Brain Tumour Segmentation in Immersive Environments

This project develops an AI-driven system to automate brain tumour segmentation from complex 3D MRI scans, reducing the need for time-consuming and error-prone manual annotation by medical experts. It combines deep learning models with immersive visualisation (e.g., AR/VR), allowing clinicians to interact with and refine tumour predictions directly in 3D space.