Internet of Things and disruptive technology

Students outside.

Our research group is driven by ideas of disruptive technologies and the advancement of the Internet of Things. We aim to translate research and practice into meaningful multi-disciplinary projects that make a difference to our daily lives.

Our group seeks to demonstrate applications in the areas of:

  • agriculture
  • healthcare
  • manufacturing
  • mining
  • smart cities
  • environmental monitoring.

We work closely with local government authorities and key industry partners through the Australian Smart Communities Association (ASCA), Creative Science Foundation (CSF), IoT Alliance Australia (IoTAA) and the Smarter Bendigo Alliance.

Technology Innovation Lab

Our research group hosts the Technology Innovation Lab which is currently equipped with three infrastructure platforms:

Internet of Things (IoT) Infrastructure Platform

This platform supports our Internet of Things (IoT) research strength which explores new and innovative wireless technologies, protocols and applications in this new and emerging field. IoT networks have many application areas and the data they collect will help manage our hospitals, homes, farms and cities of the future in more interesting, informed and efficient ways.

We have established an extensive long-range IoT network spanning the City of Greater Bendigo based around the LoRaWAN IoT standard. Our network continues to grow and is enabling new protocol developments and innovative large-scale application case studies in a unique living lab environment.

Social Robotics Platform

This platform supports our research strength in human robot interaction (HCI) with IoT. Robots will form part of our everyday futures. They may help democratise and extend our expertise and services into remote and rural areas, caring for our elderly, looking after our health, servicing our farms and helping educate our next generation. We have established several open-source robot platforms which are currently helping us engage with projects in telehealth, healthcare, well-being and education.

Rapid Prototyping Platform

This platform facilitates the creation of new IoT, robotic tools and technology designs. We innovate using open source hardware, software, design and manufacturing.

Meet our team

Group members

Research projects

Adaptive stress management system for healthcare professionals


Our research proposes a stress management framework that aims to help professionals in the health care sector manage their occupational stress. Our system employs chatbots and robots to conduct conversations with individuals in order to derive a measure of stress using a Sense of Coherence model.

The outputs of this model drive a Peer Support model which selects and administers an intervention with the aim of reducing measured stress. Our preliminary results showthat our conversation and sense of coherence models are capable of measuring stress and can be used by our peer support model to successfully select appropriate support actions.

Robust and secure federated learning in edge computing for smart healthcare systems


Our research proposes a smart federated learning (FL) model, which can be embedded in Internet of Medical Things (IoMT) devices to help analyse the patients’ health data. This early analysis and preserving privacy will enable more effective medical treatment.

Clever weather


Our research aims to predict and map micro-climates and heat islands within a city landscape for the purposes of city policy and planning. We have established a dense, real-time, low-energy framework of sensors throughout the City of Greater Bendigo over the community LoRa network we set up as a precursor to the project. Machine learning methods are used to derive inference models from the data and build correlations with data from other sources. The project also serves the purpose of educating the community around the idea of IoT and to highlight other possible use cases of the technology.

Indoor Air Quality and Impacts on Productivity


This project aims to implement a sensor network across a suite of teaching and learning environments to monitor gasses and airborne particulates. The data is collated and analysed in relation to quantifiable survey values on attention span and productivity of students. The outcome is an informed contribution to implementing better learning environments and adding to the body of knowledge on learning ability and environmental factors.

Energy Harvesting / Sustainable Devices

Deep Reinforcement Learning in Self-sustainable and Secure IoT

This project aims to develop novel reinforcement learning (RL) and deep RL (DRL) algorithms for wireless energy self-sufficient and secure IoT to maximise network throughput and simultaneously to guarantee data communications secrecy and energy constraint satisfaction.