A5015087475- Marine Biology and Ecology Research
- Marine and coastal plant biology
- Robotic Path Planning Algorithms
- Statistical Methods and Bayesian Inference
- Bayesian Modeling and Causal Inference
- Transportation Planning and Optimization
- Sports Analytics and Performance
- Sports Performance and Training
- Marine and fisheries research
- Markov Chains and Monte Carlo Methods
- Bayesian Methods and Mixture Models
- Aviation Industry Analysis and Trends
- Air Traffic Management and Optimization
- Risk and Safety Analysis
- Robotics and Sensor-Based Localization
- Coral and Marine Ecosystems Studies
- Occupational Health and Safety Research
- Data Analysis with R
- Multi-Criteria Decision Making
- Software System Performance and Reliability
- Traffic and Road Safety
- Business Process Modeling and Analysis
- Advanced Queuing Theory Analysis
- Advanced Clustering Algorithms Research
- AI-based Problem Solving and Planning
Queensland University of Technology
2016-2025
ARC Centre of Excellence for Mathematical and Statistical Frontiers
2019-2022
Australian Research Council
2016-2021
The University of Melbourne
2017-2019
Edith Cowan University
2017
Western Australian Marine Science Institution
2017
Philips (China)
2013
Network Technologies (United States)
2008
Alcatel Lucent (Germany)
2006
Nokia (United States)
2006
This paper presents Multi-Step A∗ (MSA∗), a search algorithm based on for multi-objective 4-D vehicle motion planning (three spatial and one time dimensions). The research is principally motivated by the need offline online autonomous unmanned aerial vehicles (UAVs). For UAVs operating in large dynamic uncertain environments, plan consists of sequence connected linear tracks (or trajectory segments). track angle velocity are important parameters that often restricted assumptions grid...
Better mitigation of anthropogenic stressors on marine ecosystems is urgently needed to address increasing biodiversity losses worldwide. We explore opportunities for stressor using whole-of-systems modelling ecological resilience, accounting complex interactions between stressors, their timing and duration, background environmental conditions biological processes. then search windows, times when minimally impact defined here as risk, recovery resistance. show 28 globally distributed...
This study investigated the relationship between ground reaction force-time profile of a countermovement jump (CMJ) and fatigue, specifically focusing on predicting onset neuromuscular versus metabolic fatigue using CMJ.Ten recreational athletes performed 5 CMJs at time points prior to, immediately following, 0.5, 1, 3, 6, 24 48 h after training, which comprised repeated sprint sessions low, moderate, or high workloads. Features concentric portion CMJ signature measurement were analysed...
The return-to-sport (RTS) process is multifaceted and complex, as multiple variables may interact influence the time to RTS. These include intrinsic factors related player, such anthropometrics playing position, or extrinsic factors, competitive pressure. Providing an individualised estimation of return play often challenging, clinical decision support tools are not common in sports medicine. This study uses epidemiological data demonstrate a Bayesian Network (BN). We applied BN that...
To evaluate statistical models developed for predicting medal-winning performances international swimming events and generate updated performance predictions the Paris 2024 Olympic Games.The of 2 was evaluated. The first model employed linear regression forecasting to examine trends among medal winners, finalists, semifinalists over an 8-year period. A machine-learning algorithm used time each individual event Games. second a Bayesian framework comprised autoregressive term (the previous...
Abstract Coastal development is contributing to ongoing declines of ecosystems globally. Consequently, understanding the risks posed these systems, and how they respond successive disturbances, paramount for their improved management. We study cumulative impacts maintenance dredging on seagrass as a canonical example. Maintenance causes disturbances lasting weeks months, often repeated at yearly intervals. present risk‐based modelling framework time varying complex systems centred around...
Challenges in Big Data analysis arise due to the way data are recorded, maintained, processed and stored. We demonstrate that a hierarchical, multivariate, statistical machine learning algorithm, namely Boosted Regression Tree (BRT) can address challenges drive decision making. The challenge of this study is lack interoperability since data, collection GIS shapefiles, remotely sensed imagery, aggregated interpolated spatio-temporal information, stored monolithic hardware components. For...
Various methods have been developed to combine inference across multiple sets of results for unsupervised clustering, within the ensemble clustering literature. The approach reporting from one 'best' model out several candidate models generally ignores uncertainty that arises selection, and in inferences are sensitive particular parameters chosen. Bayesian averaging (BMA) is a popular combining offers some attractive benefits this setting, including probabilistic interpretation combined...
Abstract Background Seagrass, a vital primary producer habitat, is crucial for maintaining high biodiversity and offers numerous ecosystem services globally. The increasing severity frequency of marine heatwaves, exacerbated by climate change, pose significant risks to seagrass meadows. Aims This study acknowledges the uncertainty variability heatwave scenarios aims aid managers policymakers in understanding simulated responses different durations, frequencies recurrence gaps heatwaves....
A system for automated mission planning is presented with a view to operate unmanned aerial vehicles (UAVs) in the National Airspace System (NAS). This paper describes methods modelling decision variables, enroute flight under visual rules (VFR). For demonstration purposes, task of delivering medical package remote location was chosen. Decision variables include fuel consumption, time, wind and weather conditions, terrain elevation, airspace classification trajectories other aircraft. The...
Although the influence of psychosocial hazards on mental health has been widely recognized, complex pattern in prediction still needs to be identified. Bayesian networks serve as an important, and yet untapped, method achieve this aim. As such, a network (BN) was developed assess based survey data from 186 site-based construction practitioners informed by literature expert knowledge. Results indicated that 66% target population suffered poor (i.e., mild, moderate, severe states). Poor...
In general, it is not feasible to collect enough empirical data capture the entire range of processes that define a complex system, either intrinsically or when viewing system from different geographical temporal perspective. this context, an alternative approach consider model transferability, which act translating built for one environment another less well-known situation. Model transferability and adaptability may be extremely beneficial-approaches aid in reuse adaption models,...
Summary Dynamic Bayesian networks (DBNs) provide a versatile method for predictive, whole-of-systems modelling to support decision makers in managing natural systems subject anthropogenic disturbances. However, DBNs typically assume homogeneous Markov chain which we show can limit the dynamics that be modelled especially complex ecosystems are susceptible regime change (i.e. state transition probabilities). Such changes occur as result of exogenous inputs and/or because past system states;...
Abstract The world's coral reefs are under threat as climate change causes increases in frequency and severity of acute thermal stress. This is compounded by chronic pressures including rises sea surface temperature, overfishing decline water quality. Monitoring to understand the recovery dynamics corals paramount enable effective management reefs. While detailed mechanistic models provide insight into reef patterns, colony scale monitoring not viable for over a large geographical extent,...
Seagrass ecosystems, vital as primary producer habitats for maintaining high biodiversity and delivering numerous ecosystem services, face increasing threats from climate change, particularly marine heatwaves. This study introduces a pioneering methodology that integrates Dynamic Bayesian Networks of resilience with projections, aiming to enhance our understanding seagrass responses extreme events. We developed cutting-edge metrics measuring shoot density biomass in terms population site...