Student research opportunities
Research in population informatics
Project Code: CECS_1122
This project is available at the following levels:
CS single semester, Honours, Masters, PhD
Keywords:
Population databases, Big Data, data science, data mining, data matching, record linkage, entity resolution, data integration, privacy preserving record linkage, health informatics, Honours project, PhD project, MPhil project
Supervisors:
Professor Peter ChristenDr Dinusha Vatsalan
Assoc Professor Qing Wang
Outline:
Social genomes are the digital footprints of our society. They are the basis of population informatics, an emerging research area that is concerned with the integration and analysis of large population databases that contain records about people as collected by many organisations.
Population informatics is revolutionising how researchers conduct studies, how governments plan services and expenditures, and how businesses advertise and interact with their customers. Population databases provide tremendous opportunities for the discovery of novel and valuable information.
A core requirement of population informatics is the linking of large dynamic databases that contain details about people from diverse sources. However, the scale and dynamic nature of databases that contain personal information, as well as privacy concerns, often prevent their linking.
Goals of this project
Various topics / research projects are possible within this research area. They include:
- Analysing the requirements of research studies based on population databases and developing a taxonomy of such requirements.
- Develop models of how to best represent the social genome.
- Develop rule- or statistical models to link dynamic population databases that contain temporal information.
- Develop privacy-preserving record linkage techniques for dynamic and temporal population data.
Requirements/Prerequisites
Projects in this research area are available as one semester projects, as one-year Honours projects, or as multi-year MPhil or PhD projects.
Students interested in undertaking such projects as a MPhil or PhD student should hold the equivalent of an Australian Bachelors degree with Honours H2A level or above (ideally level H1) in computer science, and preferably have done their Honours research in the areas of data mining or machine learning, and have a very good understanding of algorithms as well as good programming skills.
Further details about requirements for MPhil and PhD students are given in one of the links below.
Student Gain
A student working in a project in population informatics will learn about various data mining, record linkage and privacy techniques, and be able to develop novel techniques that potentially are of high interest to researchers in many domains, government agencies, and a variety of private sector organisations.
Background Literature
See the link provided to Peter's publications page below.
Links
Peter Christen's publicationsIEEE Computer paper: Social Genome: Putting Big Data to Work for Population Informatics
More information for MPhil and PhD students
