Research interests:

Data mining, Record linkage, Privacy-preserving record linkage, and Health informatics.

Bio:

I'm a PhD student in the Research School of Computer Science at the Australian National University (ANU). I'm currently working on privacy-preserving record linkage techniques (PPRL). PPRL is the problem of identifying matching records from different databases that correspond to the same real-world entities without compromising privacy of the entities represented by those records. A viable solution for PPRL that is well-applicable to real-world conditions needs to address the major aspect of scalability of linking large databases while achieving high linkage quality and providing sufficient privacy guarantees. The main goal of my research study is to develop scalable techniques for efficient private indexing, approximate private matching, and effective private classification in PPRL. My supervisors are Peter Christen, Vassilios S. Verykios, and Lexing Xie.

Education:

• BSc. (Hons) Information and Communication Technology with first class from University of Colombo School of Computing (2009)

Work Experience:

• Tutor - Research School of Computer Science, Australian National University, Canberra, Australia, Feb 2013 - Jun 2013.
• Research Assistant - Research School of Computer Science, Australian National University, Canberra, Australia, Feb 2012 - May 2012.
• Instructor - School of Computing, University of Colombo, Sri Lanka, Nov 2009 - Nov 2010.
• Trainee Software Engineer - Aeturnum (Pvt) Ltd, Sri Lanka, Feb 2008 - Aug 2008.

Publications:

• A taxonomy of privacy-preserving record linkage techniques. Dinusha Vatsalan, Peter Christen, and Vassilios S. Verykios. In Information Systems (Elsevier), volume 38, issue 6, September 2013, Pages 946-969. Article available online at http://dx.doi.org/10.1016/j.is.2012.11.005.
• Sorted Nearest Neighborhood Clustering for Efficient Private Blocking. Dinusha Vatsalan and Peter Christen. Proceedings of the Seventeenth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'13), Gold Coast, Australia, April 2013. Paper available online from Springer Link.
• An Iterative Two-Party Protocol for Scalable Privacy-Preserving Record Linkage. Dinusha Vatsalan and Peter Christen. Proceedings of the Tenth Australasian Data Mining Conference (AusDM'12), Sydney, December 2012. Paper, (pdf, 682 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 134.
• An Efficient Two-Party Protocol for Approximate Matching in Private Record Linkage. Dinusha Vatsalan, Peter Christen and Vassilios Verykios. Proceedings of the Ninth Australasian Data Mining Conference (AusDM'11), Ballarat, December 2011. Paper (pdf, 880 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 121.
• Mobile technologies for enhancing eHealth solutions in developing countries. Dinusha Vatsalan, Shiromi Arunatileka, Keith Chapman, Gihan Senaviratne, Saatviga Sudahar, Dulindra Wijetileka, Yvonne Wickramasinghe. Proceedings of the Second International Conference on eHealth, Telemedicine and Social Medicine (eTelemed 2010), Sint Maarten, Netherlands Antilles. Paper (pdf, 571 KB) available online from IEEE Xplore.

Awards & Scholarships:

• Endeavour Postgraduate Research Award - Awarded by the Australian Government, DEEWR, 2011.
• Recognition of Women in Data Mining Citation - Awarded by AusDM 2011 Conference, 2011.
• NBQSA Silver Award - National Best Quality Software Awards, ViduSuwa Project, eHealth Track, 2010.
• Manthan Award South Asia - South Asia’s Best e-Content Award, ViduSuwa Project, eHealth Track, 2009.