Pattern-Based Video Coding Techniques for Real-Time Low Bit-Rate and Low Complexity Encoding Applications. This project will benefit the National Research Priority on Frontier Technology with applications in video surveillance, smart home design, and patient monitoring. It will enable Australia to lead the world in setting up coding standards and thus impact directly on the manufacturing initiatives of the multimedia communication and entertainment industries. Telecommunication industries will b ....Pattern-Based Video Coding Techniques for Real-Time Low Bit-Rate and Low Complexity Encoding Applications. This project will benefit the National Research Priority on Frontier Technology with applications in video surveillance, smart home design, and patient monitoring. It will enable Australia to lead the world in setting up coding standards and thus impact directly on the manufacturing initiatives of the multimedia communication and entertainment industries. Telecommunication industries will be the immediate beneficiary by enabling quality live video transmissions at low bit rates in a cost-effective manner. This project will improve the ability of large organisations to operate virtually across huge distances in Australia with the aid of reliable multimedia communications using distributed devices of limited power and processing capacity.Read moreRead less
Visual Tracking: Geometric Fitting and Filtering. One of the most elementary things that people and sighted animals do is to follow moving objects with their eyes. Movement is a cue to the importance and relevance of objects in a scene. Visually tracking objects allows the determination of important characteristics - distance to the object, shape of the object, likely behaviour of the object etc. Though systems have been built that can perform visual tracking: accuracy and reliability must be i ....Visual Tracking: Geometric Fitting and Filtering. One of the most elementary things that people and sighted animals do is to follow moving objects with their eyes. Movement is a cue to the importance and relevance of objects in a scene. Visually tracking objects allows the determination of important characteristics - distance to the object, shape of the object, likely behaviour of the object etc. Though systems have been built that can perform visual tracking: accuracy and reliability must be improved though a better understanding of the underlying processes. Applications include visual inspection (industrial automation), surveillance (civil and military), robot vision for scene understanding and navigation, multimedia production (automatic human motion capture for example), and human computer interfaces.
Read moreRead less
A probabilistic framework for nonlinear dimensionality reduction algorithms. The Twin Measures Framework is a novel platform for analysing existing dimensionality reduction methods and the invention of new ones. This research will radically improve image analysis, with beneficial applications from pharmaceutical drug design through to border protection.
Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces an ....Partially Observable MDPs, Monte Carlo Methods, and Sustainable Fisheries. Partially Observable Markov Decision Processes (POMDPs) provide a general mathematical framework for sequential decision making under uncertainty. However, solving POMDPs effectively under realistic assumptions remains a challenging problem. This project aims to develop new efficient Monte Carlo algorithms to significantly advance the application of POMDPs to real-world decision problems involving complex action spaces and system dynamics. Both theoretical and algorithmic approaches will be applied to sustainable fishery management --- an important problem for Australia and an ideal context for POMDPs. The project will advance research in artificial intelligence, dynamical systems, and fishery operations, and benefit the national economy.Read moreRead less
Geometric parameters in Learning Theory. We aim to investigate the behaviour of geometric parameters which appear naturally in Statistical Learning Theory. Those parameters are used to control the sample complexity, which is the size of a random sample needed to produce an accurate prediction. They are also of independent interest in the local theory of Banach spaces. We shall use geometric methods originating in the local theory of Banach spaces to investigate the parameters and the way they in ....Geometric parameters in Learning Theory. We aim to investigate the behaviour of geometric parameters which appear naturally in Statistical Learning Theory. Those parameters are used to control the sample complexity, which is the size of a random sample needed to produce an accurate prediction. They are also of independent interest in the local theory of Banach spaces. We shall use geometric methods originating in the local theory of Banach spaces to investigate the parameters and the way they influence sample complexity. All the problems we focus on are not only important from the Machine Learning point of view, but are intriguing in their theoretical implications.Read moreRead less
Dynamic Deep Learning for Electricity Demand Forecasting. This project aims at developing a deep learning technology for high resolution electricity demand forecasting and residential demand response modelling. Electricity consumption data are dynamic and highly uncertain. The deep learning technology expects to provide accurate demand forecasting, and thus enabling optimal use of existing
grid assets and guiding future investments. The expected outcome can support data-driven decision-making in ....Dynamic Deep Learning for Electricity Demand Forecasting. This project aims at developing a deep learning technology for high resolution electricity demand forecasting and residential demand response modelling. Electricity consumption data are dynamic and highly uncertain. The deep learning technology expects to provide accurate demand forecasting, and thus enabling optimal use of existing
grid assets and guiding future investments. The expected outcome can support data-driven decision-making in Australia's electricity distribution network planning and operation by considering future challenges such as integrating battery storage and electric vehicles into the grid, and thus providing reliable energy. The project expects to train next generation expert workforce for Australia's future power grid.Read moreRead less
Approximate reasoning with qualitative spatial constraints involving landmarks. Applications like emergency management of bushfires, floods, or earthquake require spatial information systems to integrate multiple kinds of information and make intelligent responses in a very limited time. This project will make breakthroughs in developing efficient methods to reason about complex spatial situations.
Parameterized Analysis of Bio-inspired Computing - From Theory to High Performing Algorithms. This project will establish the field of parameterised analysis of bio-inspired computing which includes prominent approaches such as evolutionary algorithms and ant colony optimisation. It will rigorously analyse features of instances of combinatorial optimisation problems and their impact on the runtime behaviour of bio-inspired computing methods. Furthermore, the project will design new bio-inspired ....Parameterized Analysis of Bio-inspired Computing - From Theory to High Performing Algorithms. This project will establish the field of parameterised analysis of bio-inspired computing which includes prominent approaches such as evolutionary algorithms and ant colony optimisation. It will rigorously analyse features of instances of combinatorial optimisation problems and their impact on the runtime behaviour of bio-inspired computing methods. Furthermore, the project will design new bio-inspired computing algorithms that make use of instance features and hardness characteristics. The results will advance the theoretical knowledge of bio-inspired computing, bridge the gap between theory and practice, and provide more powerful algorithms for complex optimisation problems occurring for example in the field of supply chain management for the mining industry.Read moreRead less
Exploring Emerging Collective Behaviours in Large-Scale Data-Driven Networked Systems. Understanding emerging collective behaviours in large-scale data-driven networked systems and developing methodology and approach for pattern identification and intervention are very important for high impact applications such as smart energy supply using smart meters. This project will propose a new theory for the developments, which will enhance Australia's leading position in this research and provide a cut ....Exploring Emerging Collective Behaviours in Large-Scale Data-Driven Networked Systems. Understanding emerging collective behaviours in large-scale data-driven networked systems and developing methodology and approach for pattern identification and intervention are very important for high impact applications such as smart energy supply using smart meters. This project will propose a new theory for the developments, which will enhance Australia's leading position in this research and provide a cutting-edge technology for industrial applications and training of the next generation of leading researchers.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE150101351
Funder
Australian Research Council
Funding Amount
$315,000.00
Summary
Playing and Solving General Games. Constructing rational agents for general dynamic decision problems is a long-standing open Artificial Intelligence challenge. An important milestone is to construct artificial agents that can learn and play new games well (universal playing agents). Specialised artificial intelligence systems are increasingly successful in domains such as Chess, Go, and Poker. The project aims to develop the theoretical and practical foundations of universal playing agents thro ....Playing and Solving General Games. Constructing rational agents for general dynamic decision problems is a long-standing open Artificial Intelligence challenge. An important milestone is to construct artificial agents that can learn and play new games well (universal playing agents). Specialised artificial intelligence systems are increasingly successful in domains such as Chess, Go, and Poker. The project aims to develop the theoretical and practical foundations of universal playing agents through a mathematical study of algorithms and heuristics for specific games. This project aims to significantly bridge the gap from efficient specialised players to high performance rational agents.Read moreRead less