Query and Decision Support under Uncertainty for a Secure and Sustainable Environment
The Query and Decision under Uncertainty for a Secure and Sustainable Environment (QUSE) project performs research and development of generic, robust, expressive and efficient models, algorithms/prototypes to interpret and query (incomplete) data under uncertainty applied to two domains: digital forensics and environmental management.
What will this research achieve?
Many problems that face modern decision makers involve utilizing evidence from multiple temporal-spatial sources to make decisions or plans about the state of our natural and man-made environments, particularly under uncertainty. The QUSE project focuses on two such domains: digital forensics and environmental management.
Inspired by such uses, the QUSE project performs research and development of generic, robust, expressive and efficient models and algorithms to interpret and query data under uncertainty and include situations of incomplete data using such frameworks as (Dynamical) Bayesian Networks.
What are the key features?
There are three sub-projects involving partners from governmental and industrial agencies. The first one focuses on summarization and querying of digital forensic data with the aim of detecting digital crime. This is a joint project with the DSTO. The second involves work with the ACT Planning and Land Authority (ACTPLA) on exploring intelligent land planning and decision support related to relational spatial data used in town planning. The third is with the Australian Department of Agriculture, Fisheries and Forestry, Bureau of Rural Sciences, where the aim is to develop tools for querying and decision support for Australian Environmental GIS Spatial Mapping Data and focused on land use management.
See also:
All these problems, though quite practical, require the development of more optimal and efficient ways of estimation particular types of Dynamical Bayesian Networks models and how to use such models to summarize, infer and query about the underlying large datasets. These are basic research issues whose solutions would significantly improve current decision support tools.
In the following 3-5 years, we will explore such basic issues and their uses in these areas.
The QUSE solution is built upon background IP such as:
- Dynamical Bayesian Network Code (NICTA)
- Set of correspondence algorithms to automatically co-register spatial and spatial-temporal features (NICTA)
- MCAS-S software code (BRS)
Progress update
- Building and learning domain-driven model from temporal-spatial data/database
Research team
Staffs
- Nianjun Liu (Project leader)
- Warren Jin (Researcher)
- Li Cheng (Researcher)
- Marcus Hutter (Associate Professor)
- Terry Caelli (Canberra Lab director)
Students
- Nathan Brewer
- Ke Jia
- Yifan Lu
- Bin Jiang
- Ke Zhang
Duration:
October 2006 - October 2010
Participants
- Defence Science and Technology Organisation (DSTO)
- ACT Planning and Land Authority (ACTPLA)
- Australian Bureau of Rural Science (BRS)
Task: Structural Pattern Analysis and Recognition for Knowledge Discovery in Relational Temporal-Spatial Data/Database
Topic of Joint Project with DSTO
Summarize and Query Relations from Digital Forensic Data Digital forensics undertakes the post-mortem reconstruction of the causal sequence of events arising from an intrusion perpetrated by one or more external agents, or as a result of unauthorised activities generated by authorised users, in one or more digital systems. The field of digital forensics covers a broad set of applications, uses a variety of evidence and is supported by a number of techniques. Application areas include forensic accounting, law enforcement, commodity flow analysis and threat analysis. Forensic investigations often focus on unusual and interesting events that may not have arisen previously. A major objective of a digital investigation is to extract these interesting pieces of evidence and to identify the causal relationship between this evidence. This project aims at extending Dynamical Bayesian Network model developed for digital forensics by investigating a number of possible topics.
Task: Structural Pattern Analysis and Recognition for Knowledge Discovery in Relational Temporal-Spatial Data/Database
Topic of Joint Project with ACTPLA
Intelligent Land Planning and Decision Support on Relational Spatial Data Multi-criteria approaches to the analysis of complex issues in environment decision systems have found wide application across business, government and communities around the world. Such approaches may be readily applied in the context of land planning, which is a prerequisite to the development of a city, town or suburb. Generally, planners collect a range of information about an area, including information about natural resources, topography, demographics, political issues, economic characteristics and proximity to neighbouring settlements and services, and combine this information to make planning decisions. Computer aided Multi-criteria decision support tools allow for measurement and analysis of alternatives or options, involving a variety of both qualitative and quantitative dimensions. The project involves collaboration with the ACT Planning and Land Authority (ACTPLA) to present a sample demonstration of an Intelligent Land Planning tool using Bayesian Networks. Specifically, it will aim to develop a tool for the selection of optimal sites for community services within existing areas of settlement in the ACT, including recreational facilities, schools, childcare centres, aged care facilities and community centres. The factors of interest include existing settlement patterns, demographics (current and anticipated), future development, available land resources, existing services and community need.
Bayesian Network is designed to apply when there is uncertainty about evidence and how it should be combined in decision making. The proposed approach is to use a supervised strategy whereby experts provide known thematic layers of the land cover GIS spatial database as known successful decisions. The Bayesian Networks then trained to optimize the predications of such decision with the aim of applying the optimal decision model to new situations or scenarios.
Task: Structural Pattern Analysis and Recognition for Knowledge Discovery in Relational Temporal-Spatial Data/Database
Topic of Joint Project with BRS
Tools of Query and Decision Support on Australian Environmental GIS Spatial Mapping Data Analysis of spatial information in natural resources management is crucial to support a decision making process. However, with the advent of various technologies to acquire the data, analysis of multiple spatial data becomes a very challenging area. Those technologies will produce different accuracy and different resolution in the data. In spite of multi representation of spatial data, evidences of an area can be from different time and different observer’s view that makes combining those evidences is quite complicated. Combining spatial data or evidences is not just simply combining evidences from different technologies, but it is also combining multi criteria evidences.
Australian Bureau of Rural Science (BRS) has developed a system known as multi criteria analysis shell for spatial decision support (MCAS-S). The project is to incorporate an option for use of (Dynamical) Bayesian network approaches to model multiple types of evidences for intelligent environmental query and decision supports.
