Mr Thilina Ranbaduge

Thilina Nuwanga Ranbaduge
Postdoctoral Fellow
Research Area:
CSIT (108), N319

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) for multiple parties. 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. The main objectives of my research study is to develop scalable techniques for efficient and effective indexing mechanisms in PPRL for multiple parties. Currently I am supervised by Peter Christen,Vassilios S. Verykios, Dinusha Vatsalan.

A live demo of our Multi-party PPRL work can be accessed from here.
 

Education:

  • PhD in Computer Science, Australian National University, Australia (2014 - Current)
  • PG Dip in Computer Science, University of Moratuwa, Sri Lanka (2013)
  • BSc. (Hons) Information Technology with first class from University of Moratuwa, SriLanka (2009).

Work Experience:

  • Lecture (Probationary) University of Moratuwa, SriLanka (2012 - 2013)
  • Lecture (On contract) University of Moratuwa, SriLanka (2011 - 2012)
  • Software Engineer (2009 - 2011)

Awards & Scholarships:

  • Data Linkage and Anonymisation Programme participant -  Funded by the Isaac Newton Institute for Mathematical Sciences, Cambridge, UK, 2016.
  • ANU PhD Scholarship (International) (2014)
  • ANU HDR Merit Scholarship (2014)
  • DEAN LIST Awards in BSc Hons for (2007,2008,2009)

Publications:

  • Scalable Block Scheduling for Efficient Multi-Database Record Linkage, Thilina Ranbaduge, Vatsalan Dinusha, Peter Christen, 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona, Spain.
  • Evaluation of Advanced Techniques for Multi-Party Privacy-Preserving Record Linkage on Real-World Health Databases, Thilina Ranbaduge, Dinusha Vatsalan, Sean Randall, Peter Christen, The International Population Data Linkage Conference 2016.
  • Hashing-Based Distributed Multi-party Blocking for Privacy-Preserving Record Linkage , Thilina Ranbaduge, Dinusha Vatsalan, Peter Christen, Vassilios Verykios, 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 16), Auckland New Zealand (2016).
  • MERLIN - A Tool for Multi-party Privacy-preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 15th IEEE International Conference on Data Mining (ICDM 2015), Atlanta City USA.
  • Clustering-based Scalable Indexing for Multi-party Privacy-preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 15), Vietnam(2015)
  • Tree based Scalable Indexing for Multi-party Privacy Preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 12th Australian Data Mining and Analytics Conference (AusDM 14), Brisbane (2014)
  • Use of Data Mining Methodologies in Evaluating Educational Data, Thilina Ranbaduge, International Journal of Scientific and Research Publications 3 (11), 25-39 (2013)
  • Evaluating Outliers in Student Performances Through Online Activities in Distance Learning Environments,Thilina Ranbaduge, Thilak Chaminda, IEEE PCS Japan Chapter Technical Meeting and 4th ACM Chapter on E-learning and Technical Communication Conference, University of Aizu, Japan (2012)
  • Forecasting Website Accesses using Data Mining Techniques , Thilina Ranbaduge, Thilak Chaminda, Chandana Napagoda, 4th Information Technology Research Unit Research Symposium - 2012, University of Moratuwa, SriLanka, (2012)

Posters:

  • Multi-Party Privacy-Preserving Record Linkage (MP-PPRL), Thilina Ranbaduge, Vatsalan Dinusha, Peter Christen, Data linkage: techniques, challenges and applications workshop, Isaac Newton Institute for Mathematical Sciences, University of Cambridge, UK, 2016.

 

Data mining, Record linkage, Privacy-preserving record linkage, and Educational Data Mining.

Scalable Block Scheduling for Efficient Multi-Database Record Linkage, Thilina Ranbaduge, Vatsalan Dinusha, Peter Christen, 16th IEEE International Conference on Data Mining (ICDM 2016), Barcelona Spain.

Evaluation of Advanced Techniques for Multi-Party Privacy-Preserving Record Linkage on Real-World Health Databases, Thilina Ranbaduge, Dinusha Vatsalan, Sean Randall, Peter Christen, The International Population Data Linkage Conference 2016.

Hashing-Based Distributed Multi-party Blocking for Privacy-Preserving Record Linkage , Thilina Ranbaduge, Dinusha Vatsalan, Peter Christen, Vassilios Verykios, 20th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 16), Auckland New Zealand (2016).

MERLIN - A Tool for Multi-party Privacy-preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 15th IEEE International Conference on Data Mining (ICDM 2015), Atlanta City USA.

Clustering-based Scalable Indexing for Multi-party Privacy-preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 15), Vietnam(2015)

Tree based Scalable Indexing for Multi-party Privacy Preserving Record Linkage, Thilina Ranbaduge,Peter Christen,Dinusha Vatsalan, 12th Australian Data Mining and Analytics Conference (AusDM 14), Brisbane (2014)

Use of Data Mining Methodologies in Evaluating Educational Data, Thilina Ranbaduge, International Journal of Scientific and Research Publications 3 (11), 25-39 (2013)

Evaluating Outliers in Student Performances Through Online Activities in Distance Learning Environments,Thilina Ranbaduge, Thilak Chaminda, IEEE PCS Japan Chapter Technical Meeting and 4th ACM Chapter on E-learning and Technical Communication Conference, University of Aizu, Japan (2012)

Forecasting Website Accesses using Data Mining Techniques , Thilina Ranbaduge, Thilak Chaminda, Chandana Napagoda, 4th Information Technology Research Unit Research Symposium - 2012, University of Moratuwa, SriLanka, (2012)

Updated:  8 September 2015/Responsible Officer:  Dean, CECS/Page Contact:  CECS Marketing