Cognitive Modelling of Computer Games Pidgins. This project develops a pidgin language for use in computer games and models the way human users exploit such languages. It has implications also for computer assisted collaborative work and other educational or entertainment interactive environments like computer games. By developing mini-languages for games environments we can dramatically simplify the speech recognition problem and make recognition robust across different speech cultures and ba ....Cognitive Modelling of Computer Games Pidgins. This project develops a pidgin language for use in computer games and models the way human users exploit such languages. It has implications also for computer assisted collaborative work and other educational or entertainment interactive environments like computer games. By developing mini-languages for games environments we can dramatically simplify the speech recognition problem and make recognition robust across different speech cultures and backgrounds. We use protocol analysis and markup techniques for modelling dialogues between human player and reactive agents in computer games.Read moreRead less
Generalised quantum models of complexity with application to cognitive systems. Non-separable systems surround us. Our transportation, taxation, schooling, environmental and social policies are all interrelated, and it is increasingly recognised that we cannot consider them in isolation. Such systems are generally deemed complex, and it is often impossible to separate them from one another. Despite this, many of our most advanced modelling techniques are grounded in principles of separability a ....Generalised quantum models of complexity with application to cognitive systems. Non-separable systems surround us. Our transportation, taxation, schooling, environmental and social policies are all interrelated, and it is increasingly recognised that we cannot consider them in isolation. Such systems are generally deemed complex, and it is often impossible to separate them from one another. Despite this, many of our most advanced modelling techniques are grounded in principles of separability and non-contextuality. This project will develop a new set of models of non-separable systems and complexity that will in turn lead to new frontier technologies and theories.Read moreRead less
CyberMate: using digital social media and Internet data to support mental health interventions in young Australians. This project will develop CyberMate, which is a novel automated psychological intervention based on data collected from social networks, personal diaries, natural language processing and machine learning techniques. The Internet-based intervention will be the first of its kind, helping young people affected by depression and other mental health issues.
Accessible Data Exploration and Analysis for Blind People. This project aims to develop new assistive technologies that will enable blind people to explore and analyse data more readily. The project expects to generate new knowledge in the fields of assistive technology, multimodal interfaces, dialogue systems and natural language understanding and generation. The expected outcome of the project is an innovative conversational agent that uses a mix of speech and tactile graphics to communicate ....Accessible Data Exploration and Analysis for Blind People. This project aims to develop new assistive technologies that will enable blind people to explore and analyse data more readily. The project expects to generate new knowledge in the fields of assistive technology, multimodal interfaces, dialogue systems and natural language understanding and generation. The expected outcome of the project is an innovative conversational agent that uses a mix of speech and tactile graphics to communicate with a blind user and proactively assists with data analysis tasks. This should provide significant benefits, as it will overcome barriers to data analysis and exploration by blind people that currently restrict access to government, health and personal data, and limit employment opportunities.Read moreRead less
Discovery Early Career Researcher Award - Grant ID: DE120100508
Funder
Australian Research Council
Funding Amount
$375,000.00
Summary
A framework for building dynamic knowledge bases in the biomedical domain. This project will provide clinicians and researchers with a semantics and time-aware technique, which will help them work together to build and maintain the knowledge required to support a better management and understanding of the mechanisms (for example, gene mutations) that affect diseases in any biomedical domain.
Enabling Situated Immersive Science Collaboration with Remote Sensing Data . This project aims to help scientists communicate and collaborate in immersive environments. Fieldwork is more valuable to scientists than looking at abstract remote data, but expense, danger, or inaccessible locations often stand in the way. This project will address this issue by researching and designing immersive environments that combine remote data with visualisations and new interaction tools for science teams to ....Enabling Situated Immersive Science Collaboration with Remote Sensing Data . This project aims to help scientists communicate and collaborate in immersive environments. Fieldwork is more valuable to scientists than looking at abstract remote data, but expense, danger, or inaccessible locations often stand in the way. This project will address this issue by researching and designing immersive environments that combine remote data with visualisations and new interaction tools for science teams to make sense of spatial and temporal aspects of data. Outcomes will include new presentation and interaction methods, an evaluation with geoscientists, and a framework for designing interactive systems that enable situated interactions. Benefits will include helping Australian scientists overcome distance in their research. Read moreRead less
Remote presence for guidance on physical tasks. This project aims to transform remote collaboration on physical tasks. Current systems for remote collaboration on physical tasks are not as effective as working face-to-face. This could be overcome by sharing non-verbal cues, designing systems to account for cultural issues, and using a new model of communication. This project will develop theories and interaction methods for remote guidance based on natural non-verbal communication cues and cultu ....Remote presence for guidance on physical tasks. This project aims to transform remote collaboration on physical tasks. Current systems for remote collaboration on physical tasks are not as effective as working face-to-face. This could be overcome by sharing non-verbal cues, designing systems to account for cultural issues, and using a new model of communication. This project will develop theories and interaction methods for remote guidance based on natural non-verbal communication cues and cultural issues. This project is expected to benefit industries with widely distributed multi-cultural workforces such as mining, defence and medicine.Read moreRead less
Smart Information Use for PET-CT Quantitative Molecular Imaging. This project aims to use advanced computing algorithms to tackle
challenging problems associated with a new medical technology called
PET-CT which combines two imaging modalities in one device. While this technology is very new and has great potential in cancer and brain disorders, it also poses major challenges for information processing and transmission. We will address these challenges by developing advanced algorithms that op ....Smart Information Use for PET-CT Quantitative Molecular Imaging. This project aims to use advanced computing algorithms to tackle
challenging problems associated with a new medical technology called
PET-CT which combines two imaging modalities in one device. While this technology is very new and has great potential in cancer and brain disorders, it also poses major challenges for information processing and transmission. We will address these challenges by developing advanced algorithms that optimally extract information from PET and CT using mathematical models that correct for the various sources of inaccuracy. Our research will put Australian biomedical researchers and healthcare professionals at the forefront of advanced medical imaging technology.Read moreRead less
An Innovative Multimedia Framework for Multidimensional PET-CT Image Navigation and Communication. The recent development of a combined positron emission tomography and computerized tomography (PET-CT) device ushers in a completely new era in molecular imaging that will revolutionize the approach to imaging in the clinical environment. In this project, we address a number of the critical challenges associated with the introduction of PET-CT, and provide a range of innovative multimedia technolo ....An Innovative Multimedia Framework for Multidimensional PET-CT Image Navigation and Communication. The recent development of a combined positron emission tomography and computerized tomography (PET-CT) device ushers in a completely new era in molecular imaging that will revolutionize the approach to imaging in the clinical environment. In this project, we address a number of the critical challenges associated with the introduction of PET-CT, and provide a range of innovative multimedia technologies to visualize, manipulate and deliver these multi-dimensional data. Our research will greatly enhance the clinical and research benefits of PET-CT and facilitate new discoveries which will have a significant scientific and social impact in Australia and the world at large.Read moreRead less
Varying similarity metrics in indexing and retrieving high dimensional data. Many applications require varying distance metrics by putting a weight on different dimensions. Taking an example in visual information retrieval, due to the subjective nature of similarity measurements, the distance metrics can vary between different users. The main problem with k nearest neighbour (k-nn) searches using weighted metrics in a high dimensional space is whether the searches can be done efficiently, since ....Varying similarity metrics in indexing and retrieving high dimensional data. Many applications require varying distance metrics by putting a weight on different dimensions. Taking an example in visual information retrieval, due to the subjective nature of similarity measurements, the distance metrics can vary between different users. The main problem with k nearest neighbour (k-nn) searches using weighted metrics in a high dimensional space is whether the searches can be done efficiently, since in an arbitrary distance metric the intersection between the k-nn sphere and the bounding envelopes of nodes in an index tree cannot be easily calculated. This project aims to seek a novel solution. It will create a great impact on and have many applications in high dimensional visual information retrieval, instance-based learning, complex analysis, non-parametric density estimation, etc.Read moreRead less