Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition an ....Ensembles of Collaborative Neural Networks. Artificial neural networks have been used successfully for data mining and control. A neural network ensemble(NNE) is a collection of networks that exhibits properties of self-organization, plasticity, and adaptive behaviour. The aim of this research is to develop an efficient and theoretically sound algorithm for NNE learning. The outcomes of the project will include insights into self-organization of complex NNE and automatic problem decomposition and an efficient algorithm for constructing and training NNE. Practical outcomes will include research training for early career researchers and new modelling tools for data mining, robotics and multi-agent systems. The project contributes to the national priority area of smart information use.Read moreRead less
Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected ....Kernel and Margin Based Machine Learning Algorithms. Certain machine learning algorithms, such as support vector machines, utilizing
the ideas of large margins and kernels have attracted much attention lately
because of their impressive performance on real world problems such as optical
character recognition. We plan to refine and extend such algorithms to a wide
range of different machine learning problems such as gene sequence analysis,
image processing and text classification. Expected outcomes include the
development of software that allows the solution of hitherto unsolved machine
learning problems, and the ability to solve problems larger than those solvable
by the current generation of machine learning tools.Read moreRead less
Internet web page mining. This project aims to study the behaviour of internet search engines designed using a best first search strategy, and to improve on the existing designs. The outcome of the project will be a much better design of internet search engine which can be used to search for specific topics. The benefit to the Australian partner will be the gaining of skills in internet search engine design, originating from the Italian partner's group. The benefit to the Italian partner will be ....Internet web page mining. This project aims to study the behaviour of internet search engines designed using a best first search strategy, and to improve on the existing designs. The outcome of the project will be a much better design of internet search engine which can be used to search for specific topics. The benefit to the Australian partner will be the gaining of skills in internet search engine design, originating from the Italian partner's group. The benefit to the Italian partner will be the gaining of skills in research techniques, e.g., utilising a support vector machine as a classification tool, data mining techniques developed originally by the Australian partner's group, and in further developments of these techniques with specific applications to the internet web page mining problem.Read moreRead less
Predictive Assessment Tool for Beach Conditions Using Video Imaging and Neural Network Analysis. Beaches are vital part of Australian lifestyle and economic development. Monitoring of variable beach conditions is vital for beach safety and for management of storm erosion. The aim of this project is to develop an assessment tool which will permit a rating system of beach conditions both from an environmental as well as a leisure aspect. This tool will be developed into a software analysis system ....Predictive Assessment Tool for Beach Conditions Using Video Imaging and Neural Network Analysis. Beaches are vital part of Australian lifestyle and economic development. Monitoring of variable beach conditions is vital for beach safety and for management of storm erosion. The aim of this project is to develop an assessment tool which will permit a rating system of beach conditions both from an environmental as well as a leisure aspect. This tool will be developed into a software analysis system which will include components of artificial intelligence to enable the system to use feedback loops to create a better prediction of the beach morphology relative to the breaking wave characteristics.Read moreRead less
Concept-based retrieval and interpretation for large data sets. Access to on-line information is growing at an exponential rate, fuelled by advances in computing and
communications technologies. Current information retrieval methods are becoming ineffective due to
their reliance on simple term-based methods, resulting in a massive number of matches, of which only
a small proportion are relevant. We address this problem by developing new matching algorithms which
understand the underlying ....Concept-based retrieval and interpretation for large data sets. Access to on-line information is growing at an exponential rate, fuelled by advances in computing and
communications technologies. Current information retrieval methods are becoming ineffective due to
their reliance on simple term-based methods, resulting in a massive number of matches, of which only
a small proportion are relevant. We address this problem by developing new matching algorithms which
understand the underlying meaning of documents in database repositories - by building semantic
structures semi-automatically - and thus provide more relevant information to queries.
This project will be of great benefit to a multitude of end-users in medicine, history, law and many other disciplines.
Read moreRead less
Intelligent and objective measurement of wool fibre diameter. More than a half million tones of wool produced in Australia per year are visually evaluated by human woolclassers. This fibre-classing process is subjective and heavily dependent on the experience of the classers. In this project, we will objectively measure wool fibre diameter by extracting features used by human woolclassers and by combining image processing and artificial intelligence. The fractal dimension calculated by fracta ....Intelligent and objective measurement of wool fibre diameter. More than a half million tones of wool produced in Australia per year are visually evaluated by human woolclassers. This fibre-classing process is subjective and heavily dependent on the experience of the classers. In this project, we will objectively measure wool fibre diameter by extracting features used by human woolclassers and by combining image processing and artificial intelligence. The fractal dimension calculated by fractal based texture analysis will be correlated to fibre diameter. This approach will provide an insight into an on farm and/or in shed objective measurement of wool fibre diameter.Read moreRead less
Investigations into Distributed Information Processing of the World Wide Web: Addressing Major Bottlenecks in Search Engine Design. The Internet is a global medium used increasingly for commercial purposes. Nationally provided commercial services and products, as well as general types of information are made available globally via the Internet. Web search engines are the only method by which a common user can find a relevant service or information on the Internet. The sheer size and the dynamics ....Investigations into Distributed Information Processing of the World Wide Web: Addressing Major Bottlenecks in Search Engine Design. The Internet is a global medium used increasingly for commercial purposes. Nationally provided commercial services and products, as well as general types of information are made available globally via the Internet. Web search engines are the only method by which a common user can find a relevant service or information on the Internet. The sheer size and the dynamics of the Internet pose a significant challenge to search engines. This project proposes to address some major bottlenecks in search engine design (viz. the page rank computation). This may help future search engines to maintain a good level of Web penetration and, consequently will help to ensure a suitable coverage of nationally available services and information to the world.
Read moreRead less
Automatic Human Age Estimation Based on Visual Information. Age verification is important for many security applications including passport control for border security, and protecting children from adult websites, venues, or products. Accurate, reliable and practical age estimation or verification technologies would be of enormous benefit for 'Safeguarding Australia'. The ability of a machine to estimate a person's age and provide an age-appropriate interface also has benefits for the young and ....Automatic Human Age Estimation Based on Visual Information. Age verification is important for many security applications including passport control for border security, and protecting children from adult websites, venues, or products. Accurate, reliable and practical age estimation or verification technologies would be of enormous benefit for 'Safeguarding Australia'. The ability of a machine to estimate a person's age and provide an age-appropriate interface also has benefits for the young and old in our society. The outcome of this project, practical technologies for automatic human age estimation based on visual information, will dramatically change the current (non-technology based) methods of age verification and create new opportunities for customised human-machine interfaces. Read moreRead less
Online Structural Health Monitoring (SHM) System Using Active Diagnostic Sensor Network. It is imperative to remain technological leading for Australian research community. But current lack of reliable technique in structural health monitoring in Australia is considerably impeding her competition with other developed countries in areas of forefront technology. Outcomes of the project will lead to an online structural health monitoring system incorporated with active diagnostic sensor network, re ....Online Structural Health Monitoring (SHM) System Using Active Diagnostic Sensor Network. It is imperative to remain technological leading for Australian research community. But current lack of reliable technique in structural health monitoring in Australia is considerably impeding her competition with other developed countries in areas of forefront technology. Outcomes of the project will lead to an online structural health monitoring system incorporated with active diagnostic sensor network, related software and hardware, novel signal processing technique, and artificial intelligence algorithm-based damage identification scheme. Its successful applications in various industries, e.g. aerospace, maritime and civil, are expected to bring significant improvement in operation safety and great benefit in reducing maintenance cost.Read moreRead less
New Techniques for Artificial Neural Network Modelling in Hydrology. In recent years, artificial neural networks (ANNs) have demonstrated the potential to provide improved predictions when compared with the more traditional hydrological modelling techniques in a number of areas. These include the prediction of rainfall, streamflow and water quality parameters. However, one of the major difficulties associated with the application of ANNs is the lack of an established methodology for their design ....New Techniques for Artificial Neural Network Modelling in Hydrology. In recent years, artificial neural networks (ANNs) have demonstrated the potential to provide improved predictions when compared with the more traditional hydrological modelling techniques in a number of areas. These include the prediction of rainfall, streamflow and water quality parameters. However, one of the major difficulties associated with the application of ANNs is the lack of an established methodology for their design and implementation. This research will develop new methods for constructing ANN models and test them on a number of case studies so that the full potential and genuine utility of ANNs for solving hydrological problems can be assessed.Read moreRead less