Discovery Early Career Researcher Award - Grant ID: DE230100761
Funder
Australian Research Council
Funding Amount
$430,504.00
Summary
Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a ....Identifying biases in news using models of narrative framing. This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a tool to highlight biases with recommendations for diverse sets of news articles. By raising awareness to biased news reporting, the project will benefit Australians through more balanced public discourse on global challenges, such as climate change and health pandemics.Read moreRead less
Application Of A Machine Learning Approach For Effective Stock Management Of Farmed Abalone
Funder
Fisheries Research and Development Corporation
Funding Amount
$115,649.00
Summary
Determining the number and size distribution of abalone present at various stages of production is critical information for effective stock management. Currently the Australian abalone aquaculture industry spends in the order of $25,000 per annum, per farm, gathering this information by hand. However, the resulting data is of mediocre quality, is limited in its scope, and collecting the data causes stress to the animals (as it is removed from the water) which can compromise growth and survival. ....Determining the number and size distribution of abalone present at various stages of production is critical information for effective stock management. Currently the Australian abalone aquaculture industry spends in the order of $25,000 per annum, per farm, gathering this information by hand. However, the resulting data is of mediocre quality, is limited in its scope, and collecting the data causes stress to the animals (as it is removed from the water) which can compromise growth and survival. Automated counting and measuring of abalone will increase farm efficiency and productivity in the short term and, in the longer term, will provide an advanced platform for further R & D improvements including accurate data collection during experimental trials (e.g. feeds, temperature). Artificial intelligence and machine learning has now matured to a point that accurately counting and measuring abalone is possible using this approach, however specific application to the abalone industry is yet to be achieved. This project would involve the development, training and validation of a machine learning model to identify, segment and measure quantitative abalone traits in production systems and, render the product data to be accessible and applicable for farmers. Objectives: 1. To develop and implement artificial intelligence as a method for accurately measuring and counting abalone at nursery, weaning and grow out. Read moreRead less
Semantic change detection through large-scale learning. This project aims to develop technologies which understand the content of images before higher-level analysis is performed. This approach is intended to allow more accurate and reliable decisions to be made using automated image analysis than has previously been possible. The project will particularly investigate the detection of change in the contents of an image.
Effective Fuzzy Systems for Complex Structured Data Using Fuzzy Signatures. We are developing systematic, heuristic and mathematical techniques to produce effective fuzzy systems for complex structured data. Many or most real world problems have data which has interdependent sub-components depending on the context (eg only female patients need be tested for pregnancy), and often has missing components. Our techniques use fuzzy signatures to extend simple fuzzy systems to deal with data with such ....Effective Fuzzy Systems for Complex Structured Data Using Fuzzy Signatures. We are developing systematic, heuristic and mathematical techniques to produce effective fuzzy systems for complex structured data. Many or most real world problems have data which has interdependent sub-components depending on the context (eg only female patients need be tested for pregnancy), and often has missing components. Our techniques use fuzzy signatures to extend simple fuzzy systems to deal with data with such complex (sub-)structure. This produces effective fuzzy systems with wide applicability to real problems, in telecommunications, and petroleum reservoir data.Read moreRead less
Developing Minimum Message Length and Support Vector Machine methods to predict user behaviour. Predicting and modelling customer behaviour enables considerable savings in the telecommunications industry and elsewhere. The resulting predictive models facilitate identifying novice users, identifying fraud, responding to users' needs, guiding and advising users, and forwarding useful information.
We consider two cutting-edge data mining approaches, Minimum Message Length (developed and led by ....Developing Minimum Message Length and Support Vector Machine methods to predict user behaviour. Predicting and modelling customer behaviour enables considerable savings in the telecommunications industry and elsewhere. The resulting predictive models facilitate identifying novice users, identifying fraud, responding to users' needs, guiding and advising users, and forwarding useful information.
We consider two cutting-edge data mining approaches, Minimum Message Length (developed and led by Monash) and Support Vector Machines, in order to create efficient tailor-made software.
Our software will respond to specific groups of users, and their changes over time, rather than just the average user. Moreover, it will integrate the functionalities of existing individual data mining software.Read moreRead less
Resource-bounded adaptive inference of accurate conditional probability estimates from data. This project will develop machine learning techniques with a valuable new capability: the ability to produce estimates of complex conditional probabilities to varying levels of expected accuracy depending upon the constraints of available computational resources. This will provide significant competitive advantage to developers of many types of online application by allowing them to maximise utilisation ....Resource-bounded adaptive inference of accurate conditional probability estimates from data. This project will develop machine learning techniques with a valuable new capability: the ability to produce estimates of complex conditional probabilities to varying levels of expected accuracy depending upon the constraints of available computational resources. This will provide significant competitive advantage to developers of many types of online application by allowing them to maximise utilisation of available computational resources when making inferences from data, together with the flexibility to trade-off accuracy and computing resources during system design. Australia will also benefit by strengthening its machine learning expertise, which is central to many complex and intelligent systems and the booming data mining industry.Read moreRead less
ARDC: Food Security Data Challenges: Increasing Food Security Through Liberation Of Fishing And Aquaculture Data
Funder
Fisheries Research and Development Corporation
Funding Amount
$1,001,708.12
Summary
The development of digital and data systems (DSS) across fisheries & aquaculture, as well as the agriculture sector more broadly is disparate. How data is collected, how it is stored, and how it can subsequently be used is greatly influenced by factors such as sector digital maturity, or available funding to develop (or upgrade) DSS.
This project seeks to develop a national fisheries and aquaculture data ingestion and storage system (Activity 1), ensuring that information derived from f ....The development of digital and data systems (DSS) across fisheries & aquaculture, as well as the agriculture sector more broadly is disparate. How data is collected, how it is stored, and how it can subsequently be used is greatly influenced by factors such as sector digital maturity, or available funding to develop (or upgrade) DSS.
This project seeks to develop a national fisheries and aquaculture data ingestion and storage system (Activity 1), ensuring that information derived from fisheries and aquaculture activities is findable, accessible, interoperable and reusable (FAIR). The ingestion and storage system will be bolstered by a complementary data catalogue (detailing the data sets available on the platform) (Activity 2) and analytical tools (able to gain insights without moving data outside the storage platform) (Activity 6). The platform will be underpinned by metadata (Activity 3) and a robust governance framework (Activity 4). Use of the system will be tested through 3 case studies, supporting capacity and capability improvement of the sector (Activity 5).
The production of and use of data cuts across industry and government, and covers activities throughout the fisheries supply chain (from pre-fishing quota management, to post-fishing processing and subsequent traceability). Consequently there is no one organisation across fishing and aquaculture that is best placed to co-ordinate and trial this technology. FRDC is capable to the leadership required to ensure a fit for purpose product for end users, additionally the leverage of Australia Research Data Commons investment will contribute to the development of a nationally coherent eResearch infrastructure
This project received investment from the Australian Research Data Commons (ARDC). The ARDC is funded by the National Collaborative Research Infrastructure Strategy (NCRIS). Objectives: 1. Develop a new cloud-based fisheries data storage platform to enable ingestion, management, and sharing of datasets 2. Develop a CKAN-based data catalogue, a searchable fisheries data source allowing users to browse, combine, share, and access exchangeable data assets 3. Create best practice metadata standards that will be identified, documented, and then operationalised through the data catalogue and storage platform 4. Develop and operationalise a fisheries-focused data governance framework 5. Enhance capacity and capacity to use the platform through demonstration of 3 unique case studies 6. Develop use-case relevant suite of reporting and analysis tools to allow researchers to gain insights without moving data outside the storage platform Read moreRead less
Supporting adaptive, interactive documents. The project will improve comprehensibility of technical material, reduce paper usage, encourage collaborative science, improve the reliability of published science (by allowing post-publication annotation and correction), and improve the accessibility of technical material for readers who are blind or have poor vision. The project also holds considerable potential for supporting Australian companies in the publishing and document processing industries.
Multi-Ontologies meet UML: Improving the Software Engineering of Multi-Agent Systems. Multi-agent systems are a new style of software well suited for open, dynamic, distributed, global, heterogeneous environments such as the Internet. Systematic methods are needed to allow multi-agent systems to reason effectively with high level knowledge. This research draws on software engineering practice to develop a theory and methodology for multi-ontologies for expressing knowledge within multi-agent sys ....Multi-Ontologies meet UML: Improving the Software Engineering of Multi-Agent Systems. Multi-agent systems are a new style of software well suited for open, dynamic, distributed, global, heterogeneous environments such as the Internet. Systematic methods are needed to allow multi-agent systems to reason effectively with high level knowledge. This research draws on software engineering practice to develop a theory and methodology for multi-ontologies for expressing knowledge within multi-agent systems that facilitate adaptation and change.
Read moreRead less