Our Research

AI/IoT-powered Dashboard for environmental management at Tram Chim National Park

A multi-disciplinary team led by Prof Hoa Dam from the Decision Systems Lab in School of Computing and IT has recently completed a project on developing AI/IoT solutions to support environmental management in Tram Chim National Park in Vietnam. Tram Chim National Park is one of five largest national parks in Vietnam. It has significant biodiversity, providing habitat for over 230 bird species and 130 fish species, including the iconic and endangered Sarus Crane. Environmental management and research at Tram Chim National Park were hampered by insufficient and irregular survey data, due to extreme weather conditions, complex, large environments, and the lack of digital resources.

To address those issues, the project brought together experts across multiple disciplines in Artificial Intelligence, Software Engineering, Environmental Engineering, Conservation Biology, Computer Vision and Telecommunication, including Prof Hoa Dam (SCIT), Prof Faisal Hai (CMEA), Dr Kimberly Maute (SMAH), Prof Son Lam Phung (SECTE) and A/Prof Chung Le Tran (SECTE) from UOW and researchers from Ho Chi Minh City University of Technology, Vietnam.

An IoT station deployed in Tram Chim National Park

An IoT station deployed in Tram Chim National Park

The team developed and deployed a diverse range of IoT devices to allow continuous survey of large areas in Tram Chim National Park. AI technologies were developed to process, analyse and classify large volumes of data into metrics that give real-time insights into the national park's ecosystem health. The system continuously collects and displays in real time a range of water telemetry (temperature, turbidity, water level, pH level, conductivity and diluted oxygen level), and soil and air telemetry (soil temperature, humidity, conductivity, air CO2 level, humidity, temperature, PM10 and PM2.5 level) across different areas in the national park.

Painted picture of five long beck grey birds in green grass with yellow tags sicky up from the grass over the birds' heads.

Bird detection and classification


Blue line graphs on light blue background and white background column on right right. An example of AI4TramChim dashboard viewed on a mobile device

An example of AI4TramChim dashboard viewed on a mobile device

The system is also able to detect birds, classify bird species and count birds in real time through live video streams. It also detect smoke and fire and send alerts to users in real time. In addition, it can predict fire risk level (low, moderate, high or extreme) through images of grasses and soil/air telemetry (air temperature, humidity, soil temperature, humidity, conductivity) collected in real time. The system also supports storage and exporting historical data to facilitate adaptive environmental management and research. The system also offers a digital AI-powered dashboard that is readily accessible to different stakeholders of the Park (e.g. rangers, governance officers and researchers) through various computing devices (e.g. PCs, mobile phones or tablets) to support the decision making and adaptive management at Tram Chim National Park. 

People in a river boat wearing orange life jackets.

A delegation led by Australian Ambassador to Vietnam visited the project site in 2022

People standing at an exhibition stall watching a screen.

Deputy PM of Vietnam and Australian Ambassador to Vietnam visited the project demo at AI4VN Expo

The project was funded under the competitive grant of the Department of Foreign Affairs and Trade’s Aus4Innovation program. Project partners include technology giant Microsoft.

Advanced Systems Integration Pty Ltd

  • The Problem: Truck despatch systems for open-pit mines help decide which truck should service which excavator (shovel, dragline etc.) but these tend to work in batch mode. They are thus not responsive to on-the-fly changes (roadway blockages, landslips, truck breakdowns etc.).
  • The Solution: An agent-based market-oriented solution where individual truck agents bid for work (the excavator agents are auctioneers) and subsequently internally trade jobs to maintain near-optimal performance.

Bluescope Steel

  • The Problem: Long-term planning, medium-term planning and scheduling and short-term scheduling was happening in disparate silos, leading to locally optimal but globally suboptimal solutions. The conjoint problem was very large, involving upwards of 2.5 million decision variables.
  • The Solution: A novel problem decomposition scheme called hypertree decomposition was developed which permitted decomposed sub-problems to be solved separately while still permitting these solutions to be composed into a global solution.
  • The Problem: Real-time scheduling was being done in separate silos for the blast furnace, stockyard (for iron slabs) and the hot strip mill.
  • The Solution: A novel distributed constraint optimization technique called SBDO was developed and tested at Bluescope Steel.

Bluescope Steel


  • The Problem: BHP Building Products’ manufacturing facility in Chullora used sub-optimal production scheduling strategies.
  • The Solution: A novel system called ISSUS was developed that used constraint programming technology at the back end for optimization, and offered, at the front end, an interactive Gantt chart that permitted operators to interrupt and alter system-generated production schedules while exploring the implications of relaxing applicable constraints (and generating what-if scenarios).

IBM Research 

  • The Problem: IBM and its clients routinely used the notion of “process variant” but had no concrete means of deciding whether a given process design or instance was a valid variant of another. This had significant implications for process compliance management.
  • The Solution: A bespoke framework (GOVM) was developed that used a machinery for extracting/identifying goals from process designs and instances to make a principled determination of whether a design or instance was a valid variant of another.
  • The Problem: Service teams were being over-staffed – an easy way to deal with the prospect of paying penalties associated with SLA violations if leaner teams were used.
  • The Solution: Build a business case by using agent-based simulation of the service delivery setting. Build an optimal service despatcher using distributed constraint optimization (DCOP) technology. Use the agent-based simulation coupled with the optimized service despatcher to establish the savings that accrue.

IBM Research

Infosys Labs

  • The Problem: Business processes are often described, modelled and executed at a level of granularity that precludes strategy-level analysis. Critical business processes would thus not figure in strategic planning and deliberations, despite having significant strategic impact.
  • The Solution: A novel notion of goal orchestration was developed. Using a client dataset with 65,000 data points (relating to IT incident management processes), it was shown that a variation of standard process mining techniques could be used to mine goal orchestrations.

Infosys Labs

NSW State Emergency Services

  • The Problem: A vast operational infrastructure that remains dormant in normal times but “wakes up” during emergencies. A vast pool of volunteer staff. This infrastructure was not adequately modelled nor adequately understood.
  • The Solution: A very large-scale enterprise process architecture built using the i* notation. A novel form-based technique for model elicitation was also developed. These outcomes were put into routine used by SES managers and eventually informed the design of a system called RFAOnline.

NSW State Emergency Services

Xerox Research (Conduent Labs)

  • The Problem: Leveraging past execution histories to predict cloud process performance under various cloud load scenarios.
  • The Solution: Build a tool that permits us to query past execution histories as if they constituted a causal theory correlating the process context (cloud load), process design and process instance-level data with process performance.

Conduent Labs


  • Pattaraporn Sangaroonsilp, Hoa Khanh Dam, Aditya Ghose, On Privacy Weaknesses and Vulnerabilities in Software Systems, Proceedings of the 45th International Conference on Software Engineering (ICSE), To Appear, 2023.
  • Pattaraporn Sangaroonsilp, Hoa Khanh Dam, Morakot Choetkiertikul, Chaiyong Ragkhitwetsagul, Aditya Ghose, A Taxonomy for Mining and Classifying Privacy Requirements in Issue Reports, Information and Software Technology journal, To Appear, 2023.
  • Swasti Khurana , Novarun Deb , Sajib Mistry , Member, IEEE, Aditya Ghose , Aneesh Krishna, Hoa Khanh Dam, Egalitarian Transient Service Composition in Crowdsourced IoT Environment, IEEE Transactions on Services Computing, DOI: 10.1109/TSC.2023.3264581.
  • Saad Hashmi, Hoa Khanh Dam, Anton Uzunov, Mohan Baruwal Chhetri, Aditya Ghose, Alan Colman, Goal-Driven Adversarial Search for Distributed Self-Adaptive Systems, Proceedings of IEEE International Conference on Software Services Engineering, To Appear, 2023.
  • Abdulaziz Alhefdhi, Hoa Khanh Dam, Yusuf Sulistyo Nugroho, Hideaki Hata, Takashi Ishio and Aditya Ghose, A Framework for Conditional Statement Technical Debt Identification and Description, Automated Software Engineer journal, Springer, Volume 60, pages 1-36, 2022.
  • Ahmad Alelaimat, Aditya Ghose and Hoa Khanh Dam, XPlaM: A Toolkit for Automating the Acquisition of BDI Agent-based Digital Twins of Organizations, Computers in Industry journal, Volume 145, pages 1 - 13, 2023.


  • Saad Hashmi, Hoa Khanh Dam, Peter Smet and Mohan Baruwal Chhetri, Towards Antifragility in Contested Environments: Using Adversarial Search to Learn, Predict, and Counter Open-Ended Threats, Proceedings of International Conference on Autonomic Computing and Self-Organizing Systems, To Appear, 2022, IEEE.
  • Aditya Ghose, Hoa Khanh Dam, Shunichiro Tomura, Dean Philp and Angela Consoli, Goal-oriented coordination with cumulative goals, Proceedings of 24th International Conference on Principles and Practice of Multi-Agent Systems, Lecture Notes in Computer Science, vol 13753, pages 260 - 280, Springer, 2022.
  • Helena Ibro, Geeta Mahala, Simon Pulawski, Steven Harvey, Alexis Andrew Miller, Aditya Ghose, Hoa Khanh Dam , DITURIA: A Framework for Decision Coordination Among Multiple Agents, Proceedings of 24th International Conference on Principles and Practice of Multi-Agent Systems, Lecture Notes in Computer Science, vol 13753, pages 492-508, Springer, 2022
  • Anton V. Uzunov, Bao Vo, Hoa Khanh Dam, Charles Harold, Mohan Baruwal Chhetri, Alan Colman, Saad Sajid Hashmi, Adaptivity and Antifragility, in Autonomous Intelligent Agents for Cyber Defense, A. Kott, Ed. Springer Nature, To Appear, 2022.
  • Jirayus Jiarpakdee, Chakkrit Tantithamthavorn, Hoa Khanh Dam and John Grundy, An Empirical Study of Model-Agnostic Techniques for Defect Prediction Models, IEEE Transactions on Software Engineering, Volume: 48, Issue: 1, pages 166 – 185, 2022


  • Hoa Khanh Dam, Truyen Tran, Trang Pham, Shien Wee Ng, John Grundy, and Aditya Ghose, Automatic feature learning for predicting vulnerable software components, IEEE Transactions on Software Engineering, Volumne 47, Issue 1, pages 67-85, 2021.
  • Morakot Choetkiertikul, Hoa Khanh Dam, Truyen Tran, Trang Pham, Chaiyong Ragkhitwetsagul and Aditya Ghose, Automatically recommending components for issue reports using deep learning. Empirical Software Engineering, Volumne 26, Issue 14,  pages 1 - 39, 2021, Springer.  
  • Asjad Khan, Aditya Ghose, Hoa Khanh Dam, Hung Le, Truyen Tran and Kien Do, DeepProcess: Supporting business process execution using a MANN-based recommender system, Proceedings of the 19th International Conference on Service Oriented Computing (ICSOC 2021), Lecture Notes in Computer Science, vol 13121, pages 19 – 43, Springer.
  • Asjad Khan, Aditya Ghose, Hoa Khanh Dam, Cross-Silo Process Mining with Federated Learning, Proceedings of the 19th International Conference on Service Oriented Computing (ICSOC 2021), Lecture Notes in Computer Science, vol 13121, pages 612 – 626, Springer.
  • Asjad Khan, Aditya Ghose and Hoa Khanh Dam, Decision Support for Knowledge Intensive Processes using RL based Recommendations, Business Process Management Forum, Lecture Notes in Business Information Processing, Volume 427 (2021), Springer.
  • Davoud Mougouei, Aditya Ghose, Hoa Khanh Dam, Mahdi Fahmideh and David Powers, A Fuzzy-Based Requirement Selection Method for Considering Value Dependencies in Software Release Planning, IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 2021, pp. 1-6.
  • Simon Pulawski, Hoa Khanh Dam and Aditya Ghose, BDI-Dojo: developing robust BDI agents inevolving adversarial environments, SPS Special Session on Cyber Resilience and Antifragility in Complex Distributed Systems, To Appear.


  • Geeta Mahala, Renuka Sindhgatta, Hoa Khanh Dam and Aditya Ghose, Designing Optimal Robotic Process Automation Architectures, Lecture Notes in Computer Science, Proceedings of the 18th International Conference on Service-Oriented Computing (ICSOC 2020), Lecture Notes in Computer Science, Springer.  
  • Aditya Ghose, Geeta Mahala, Simon Pulawski, Hoa Khanh Dam, The Future of Robotic Process Automation (RPA). In: Hacid H. et al. (eds) Service-Oriented Computing – ICSOC 2020 Workshops. ICSOC 2020. Lecture Notes in Computer Science, vol 12632. Springer.
  • Ahmad Alelaimat, Aditya Ghose, Hoa Khanh Dam, Abductive Design of BDI Agent-Based Digital Twins of Organizations. In: Uchiya T., Bai Q., Marsá Maestre I. (eds) PRIMA 2020: Principles and Practice of Multi-Agent Systems. PRIMA 2020. Lecture Notes in Computer Science, vol 12568.
  • Kinzang Chhogyal, Angela Consoli, Aditya Ghose, Hoa Khanh Dam, G2I: A principled approach to leveraging the goal-to-information nexus in BDI agents. Proceedings of the 24th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems. pages 2675-2684, Procedia Computer Science 176, Elsevier 2020.
  • Wisam Haitham Abbood Al-Zubaidi, Patanamon Thongtanunam, Hoa Khanh Dam, Chakkrit Tantithamthavorn and Aditya Ghose, Workload-Aware Reviewer Recommendation using a Multi-Objective Search-based Approach , Proceedings of the 13th International Conference on Predictive Models and Data Analytics in Software Engineering, pp. 21–30, ACM.

Browse our previous years' papers

  • Aus4Innovation (with Faisal Hai, Son Lam Phung, Kimberly Maute, Le Chung Tran) - AI/IoT-powered Dashboard for Environmental Management at Tram Chim National Park, $250,000
  • Aus4Innovation (with Pascal Perez, Le Chung Tran, Son Lam Phung, Johan Barthelemy, Rohan Wickramasuriya, Thao Duong, Christian Ritz, Montse Ros, Jiangtao Xi, Farzad Safaei) - Smart Eye – Airborne and AI-Driven Assessment Solution of Sugarcane, $300,000
  • Australian Research Council Collaborative Grant (SPIRT) for a collaborative project entitled “Robust reactive constraint-based scheduling”to be conducted with BHP-IT (jointly held with Joseph Davis and Li-Yen Shue), $198,000 ($148,00 in cash and $50,000 in kind).
  • Australian Research Council Discovery Grant for a project entitled “Ontology based agent oriented development methodologies” (with G. Low, B. Henderson-Sellers and G. Beydoun), $350,000.
  • Australian Research Council Discovery Grant for a project entitled “Intelligent information assimilation” (with A. Nayak, N. Foo and M. Pagnucco), $184,000.
  • Australian Research Council IREX grant for a project entitled “Integrating non-monotonic reasoning and constraint programming”(with Norman Foo, University of New South Wales, Maurice Pagnucco, Macquarie University, Bill Havens, Simon Fraser University and Randy Goebel, University of Alberta), $42,000.
  • Australian Research Council Large Grant for a project entitled “Formal methods in software requirements engineering” (with J. Davis), $153,000.
  • Australian Research Council Linkage Project Grant (APAI only) for a project entitled “Agent-oriented conceptual modelling” in collaboration with NSW State Emergency Services (joint with R. Clarke and P. Hyland), $82,000.
  • Australian Research Council Linkage Project Grant for a project entitled “Integrated constraint-based planning and scheduling” in collaboration with BHP Steel, $240,000 ($160,000 cash and $80,000 in-kind).
  • Australian Research Council Linkage Project Grant for a project entitled “Optimizing steel industry supply chains through constraint- and market-oriented programming” in collaboration with BHP Steel, $197,300 ($137,300 in cash and $60,000 in-kind).
  • Australian Research Council Small Grant for a project entitled “Agent-based requirements engineering”, $6,000.
  • Australian Research Council Small Grant for a project entitled “Constraint retraction: Semantics and applications”, $6,762.
  • Australian Research Council Small Grant for a project entitled “Formal specification languages for intelligent agents”, $10,000.
  • Australian Research Council Small Grant for a project entitled “Reverse engineering legacy information systems using flexible plan specifications”, $5,000.
  • Canadian Natural Sciences and Engineering Research Council grant on “Development of a Canadian/Australian research collaboration in constraint programming and non-monotonic reasoning” (joint with W. S. Havens, R. G. Goebel, N. Foo, M. Pagnucco, M. Horsch), $15,000 (approx.).
  • Cooperative Research Center for Smart Services grant for a project entitled “Strategic alignment of services”, $500,000 (approx.).
  • Illawarra Shoalhaven Local Health District grant for “Oncology Informatics”, $750,000.
  • Japanese Research Institute for Advanced Information Technology (AITEC) grant (formerly known as ICOT – the institute that led the Japanese Fifth Generation project) for a project entitled “Anytime hypothetical reasoning”, 1.5 million yen.
  • Next Generation Technologies Fund (with Bao Quoc Vo and Ryszard Kowalczyk) - Autonomic Cyber Resilience and Antifragility, $1,157,100
  • Next Generation Technologies Fund, Self-integrating architectures to enable agile C2 information systems, $344,534
  • Next Generation Technologies Fund, Rapid Situation Awareness using Network Knowledge and AI Reasoning, $704,000
  • NSW Small Business Innovation & Research Grant (with Wize Dynamics, Katarina Mikac and Kimberly Maute) - AI for identifying koalas, Koala Count Challenge, $96,448
  • Research Contract with Pillar Administration, $17,000.
  • Samsung grant for “Predicting hazardous software components using deep learning” (joint with H. Dam, T. Tran and J. Grundy), $100,000.
  • South Western Sydney Local Health District grant for “Data mining in radiation oncology”, $114,000
  • UGPN Colalboration Fund (with Davoud Mougouei, Munindar Singh, Aditya Ghose, Simon Evans, Inga Prokopenko, Jaime Simão Sichman, Cath Taylor and Zhanna Balkhiiarova) - Understanding the emotional impact of Covid-19 coverage in popular media, $USD 40,000
  • UGPN Collaboration Fund (with Munindar Singh, Nigel Gilbert and Aditya Ghose) - Artificial Intelligence for Sustainable Project Management, USD $40,000.
  • University of Wollongong ARC “near miss” grant, $10,000.
  • University of Wollongong Industry Links Grant with BHP Steel for a project entitled “Robust applications of constraint programming in operations planning”, $14,000.
  • University of Wollongong Industry Links Grant with CSIRO Mathematical and Information Sciences for a project entitled “Cooperative problem solving in multi-agent systems”, $18,000.
  • University of Wollongong New Partnerships Grant, $15,000.
  • University of Wollongong Research Infrastructure Block Grant to the Decision Systems Lab for 1998-99 (jointly held with J. Davis and L.-Y. Shue), $20,421.
  • University of Wollongong Research Infrastructure Block Grant to the Decision Systems Lab for 1999-2000 (jointly held with J. Davis and L.-Y. Shue), $18,685.
  • University of Wollongong, Faculty of Commerce Internal Grant for a project on intelligent scheduling, $4,500.
  • University of Wollongong, Faculty of Commerce Internal Grant for a project on requirements engineering, $2,000.
  • University of Wollongong, Faculty of Commerce Internal Grant, $7, 000.
  • University of Wollongong, University Research Council New Staff Grant, $2,000.