This project develops core techniques to learn image-centric knowledge graphs by connecting large collections of image/video and their descriptions to existing knowledge bases with encyclopedic, lexical, and commonsense knowledge.
The aim of the project is to develop novel techniques to construct advanced types of Knowledge Graphs.
The aim of the project is to develop novel methods and a complete eco-system of tools to facilitate average users to curate the Knowledge Graph.
The aim of the project is to design novel technical solutions to refine a Knowledge Graph, including its entities, relations, and its associated Concept Graph effectively and efficiently.
The aim of the project is to design novel technical solutions to enable flexible querying and efficient processing of various types of queries issued on a large and complex knowledge graph.
The aim of the project is to create a data driven ontology, called Concept Graph, about concepts and their instances.
This project focuses on merging two or more big datasets by using the structure of the entire database of information at once, using modern graph theory and algebraic tools.
This project involves developing mathematical and computational algorithms to extract meaningful mobility patterns from massive, open, geolocated data sets such mobile phone data, geolocated social media .
This project will develop new methods that in particular exploit open data sources, and will perform a comprehensive comparison of methods using historical disease data.
This project will look at ways in which mining open data for information on disease transmission can best be used to infer epidemiological parameters.
This project uses sentiment analysis techniques to develop real time political polling tools from open social media data.
This project explores how social network structures affect the nature of influence, and develops predictive models for information flow through these structures.
This project will develop new methods for detecting anomalous events using open data sources.
This project will delve into the concept of “analyst curation tasks” to encapsulate customizable data curation micro-apps accessible through a user-friendly abstraction.
This research will delve into effective methods for incrementally constructing and collectively curating a contextualized Knowledge Graph.
This project will focus on aspects of developing natural language mechanisms for interrogating the integrated knowledge hub, such as automated vocabulary learning or automated translation of event processing specifications to an executable language.
This project focuses on adaptation of user queries to be executed on different systems, and the automated adaptation (transformation) of queries to database systems with differing data models.
This project will examine the suitability of established meta-data schemas and versioning models, identify query patterns and examine the implementation of meta-data services using conventional and NoSQL databases in Big Data tool chains
This project aims to develop innovative tools to extract significant topics for real-time prediction of population-level societal events.
This project aims to model the relationship between Dengue virus outbreaks in different Australian cities and/or in cities of a neighbouring country.