Applied informatics

Digital water management models

Our research teams specialise in web mining, data management, health informatics and e-health service-oriented computing. These are increasingly important in the management of issues in the environment, health services, sport performance, tourism, law and other sectors.

Victorian Institute of Sport
Relationships Australia
Westgate General Practice Network
Tasmania Department of Health and Human Services
Australia e-Health Research Center
South East Queensland Healthy Waterways Partnership
Royal Brisbane and Women’s Hospital
ANZ Bank
Nanjing University of Finance and Economics
IBM
World Health Organisation
Chinese Academy of Sciences
Beijing Jiaotong University (China)
University of Queensland
German Sports University (Cologne)
Autonomous University of Barcelona
Australian Institute of Sport

We are also part of other research networks and collaborations committed to developing technologies that have benefits to most industry sectors.

Please contact us if you would like to collaborate on research on applied informatics and deliver real benefits to industry, the community and your organisation.

Postgraduate research opportunities

We welcome applications from prospective research students wanting to undertake a PhD or Masters by Research in the area of applied informatics.

For further information about becoming a research student or guidance about possible project areas and supervisors, please contact Professor Yanchun Zhang.

New research projects available for 2013 applicants

Title: Real Time and Self Adaptive Stream Data Processing

This project will develop an original algorithmic and model solution for online stream data processing. Beyond the stream compression technique, it will develop novel optimal strategies on multiple continuous queries, efficient trends detection methods and integration.
Principal supervisor: Professor Yanchun Zhang

Title: Using Data Mining Methods to Remove Uncertainties in Sensor Data Streams

This project will develop a flexible framework that comprises several novel algorithms for removing uncertainties through mining multiple sensor data streams. In addition to improving single stream data quality, we will maximize precision for querying multiple sensor streams. Static/mobile real world sensor stream applications will be employed to evaluate the proposed framework. This project will develop key techniques for removing uncertainties in sensor data streams and thus improve the monitoring quality of sensor networks.
Principal supervisor: Professor Yanchun Zhang

Title: Accurate and Online Abnormality Detection in Multiple Correlated Time Series

This project develops effective, efficient and accurate methods for mining the anomalies of correlated multiple time series in online and real-time manner. The study includes the detection/prediction of anomalies by analysing differences, changes, and trends in correlated multiple time. The predicted anomalies often indicate the critical and actionable information in several application domains.
Principal supervisor: Dr. Jing He