ANU Data Mining Group

2008:

• Data Mining and Analytics 2008
  John Roddick, Jiuyong Li, Peter Christen and Paul Kennedy (editors).
  Proceedings of the Seventh Australasian Data Mining Conference (AusDM 2008), Glenelg, Adelaide, November 2008.
  Conferences in Research and Practice in Information Technology (CRPIT), vol. 87.

• Towards Scalable Real-Time Entity Resolution using a Similarity-Aware Inverted Index Approach
  Peter Christen and Ross Gayler
  In proceedings of the Seventh Australasian Data Mining Conference (AusDM 2008), Glenelg, Adelaide, November 2008.
  To be published in Conferences in Research and Practice in Information Technology (CRPIT), vol. 87.
  Accepted paper (10 pages, pdf, 218 KB)

• Probabilistic Data Generation
  Agus Pudjijono
  Master of Computing (Honours) thesis, ANU Department of Computer Science, November 2008.
  Thesis (pdf.gz, 2.4 MB)

• Visualization of Temporal Changes in Cluster Structures using Self-Organizing Maps
  Denny, Graham Williams, and Peter Christen
  Accepted as regular paper for the IEEE International Conference on Data Mining (ICDM), Pisa, Italy, December 2008.
  Please contact Denny if you are interested in this paper.

• Automatic Record Linkage using Seeded Nearest Neighbour and Support Vector Machine Classification
  Peter Christen
  Proceedings of the ACM SIGKDD 2008 conference, Las Vegas, August 2008.
  Paper available online.
  

• Febrl - An Open Source Data Cleaning, Deduplication and Record Linkage System with a Graphical User Interface
  Peter Christen
  Proceedings of the demo session at the ACM SIGKDD 2008 conference, Las Vegas, August 2008.
  Paper available online.
  

• Automatic Training Example Selection for Scalable Unsupervised Record Linkage
  Peter Christen
  Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Osaka, Japan, May 2008.
  Paper available online.
  Submitted paper (12 pages, pdf, 146 KB)   Submitted paper (12 pages, ps.gz, 142 KB)

• Exploratory Hot Spot Profile Analysis using an Interactive Visual Drill-Down Self-Organizing Maps
  Denny, Graham J. Williams and Peter Christen.
  Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), Osaka, Japan, May 2008.
  Paper available online.

• Febrl - A Freely Available Record Linkage System with a Graphical User Interface
  Peter Christen
  Proceedings of the Australasian Workshop on Health Data and Knowledge Management (HDKM), Wollongong, January 2008.
  Paper (pdf, 748 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 80.

2007:

• Data Mining and Analytics 2007
  Peter Christen, Paul J. Kennedy, Jiuyong Li, Inna Kolyshkina and Graham J. Williams (editors).
  Proceedings of the Sixth Australasian Data Mining Conference (AusDM 2007), Gold Coast, Australia, December 2007.
  Conferences in Research and Practice in Information Technology (CRPIT), vol. 70.

• A Two-Step Classification Approach to Unsupervised Record Linkage
  Peter Christen
  In proceedings of the Sixth Australasian Data Mining Conference (AusDM 2007), Gold Coast, December 2007.
  Paper (pdf, 440 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 70.

• Exploratory Multilevel Hot Spot Analysis: Australian Taxation Office Case Study
  Denny, Graham J. Williams, and Peter Christen
  In proceedings of the Sixth Australasian Data Mining Conference (AusDM 2007), Gold Coast, December 2007.
  Paper (pdf, 759 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 70.

• Evaluation of a Graduate Level Data Mining Course with Industry Participants
  Peter Christen
  In proceedings of the Sixth Australasian Data Mining Conference (AusDM 2007), Gold Coast, December 2007.
  Paper (pdf, 436 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 70.

• Towards parameter-free blocking for scalable record linkage
  Peter Christen
  Technical Report TR-CS-07-03
  ANU Joint Computer Science Technical Report Series, August 2007.
  Report (pdf, 201 KB)   Report (ps.gz, 199 KB)

• Quality and Complexity Measures for Data Linkage and Deduplication
  Peter Christen and Karl Goiser
  Chapter in the book Quality Measures in Data Mining, vol. 43, Studies in Computational Intelligence.
  F. Guillet and H. Hamilton (eds), Springer, March 2007.
  Available online at SpringerLink.

2006:

• Privacy-Preserving Data Linkage and Geocoding: Current Approaches and Research Directions
  Peter Christen
  In proceedings of the Workshop on Privacy Aspects of Data Mining (PADM) held at the IEEE International Conference on Data Mining (ICDM), Hong Kong, December 2006.
  Final 5-page version: Paper (pdf, 53 KB)   Paper (ps.gz, 35 KB)
  Submitted 11-page version: Paper (pdf, 118 KB)   Paper (ps.gz, 74 KB)

• A Comparison of Personal Name Matching: Techniques and Practical Issues
  Peter Christen
  In proceedings of the Workshop on Mining Complex Data (MCD) held at the IEEE International Conference on Data Mining (ICDM), Hong Kong, December 2006.
  Final 5-page version: Paper (pdf, 57 KB)   Paper (ps.gz, 40 KB)
  Submitted 12-page version available as:
  Technical Report TR-CS-06-02
  ANU Joint Computer Science Technical Report Series, September 2006.
  Report (pdf, 248 KB)   Report (ps.gz, 236 KB)

• Dynamic Algorithm Selection Using Reinforcement Learning
  Warren Armstrong, Peter Christen, Eric McCreath and Alistair Rendell
  Proceedings of the Workshop on Integrating AI and Data Mining, Hobart, Australia, December 2006.
  Paper (pdf, 254 KB)

• Towards Automated Record Linkage
  Karl Goiser and Peter Christen
  In proceedings of the Fifth Australasian Data Mining Conference (AusDM2006), Sydney, November 2006.
  Paper (pdf, 513 KB) available online from Conferences in Research and Practice in Information Technology (CRPIT), vol. 61.

• Secure Health Data Linkage and Geocoding: Current Approaches and Research Directions
  Peter Christen and Tim Churches
  Proceedings of the National e-Health Privacy and Security Symposium (ehPASS), Brisbane, October 2006.
  Paper (pdf, 139 KB)   Paper (ps.gz, 127 KB)

• Automated Geocoding of Routinely Collected Health Data in New South Wales
  Richard Summerhayes, Paul Holder, John Beard, Peter Christen, Alan Willmore and Tim Churches
  The NSW Public Health Bulletin, volume 17, number 3-4, March-April 2006.
  Online version available here.

• A Probabilistic Geocoding System Utilising a Parcel Based Address File
  Peter Christen, Alan Willmore and Tim Churches
  In Advances in Data Mining: Theory, Methodology, Techniques, and Applications. Simeon Simoff and Graham Williams (editors). State-of-the-Art Lecture Notes in Artificial Intelligence, Volume 3755, Springer-Verlag, 2006.
  Available online at SpingerLink, LNCS 3755.
  Copyright for this publication is held by the Springer Verlag.
  

2005

• Automated Probabilistic Address Standardisation and Verification
  Peter Christen and Daniel Belacic
  Proceedings of the fourth Australasian Data Mining Conference (AusDM 2005), Sydney, December 2005.
  Paper (pdf, 146 KB)   Paper (ps.gz, 204 KB)

• Assessing Deduplication and Data Linkage Quality: What to Measure?
  Peter Christen and Karl Goiser
  Proceedings of the fourth Australasian Data Mining Conference (AusDM 2005), Sydney, December 2005.
  Paper (pdf, 178 KB)   Paper (ps.gz, 163 KB)

• Probabilistic Data Generation for Deduplication and Data Linkage
  Peter Christen
  Proceedings of the Sixth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'05), Brisbane, July 2005.
  Available online at SpingerLink, LNCS 3578.
  Copyright for this publication is held by the Springer Verlag.
  Paper (pdf, 124 KB)   Paper (ps.gz, 135 KB)

• Febrl - Freely extensible biomedical record linkage (Manual, release 0.3)
  Peter Christen and Tim Churches
  Available online from SourceForge.Net, April 2005.
  Manual (pdf, 960 KB)   Manual (pdf, 282 KB)

• A Probabilistic Deduplication, Record Linkage and Geocoding System
  Peter Christen and Tim Churches
  Proceedings of the ARC Health Data Mining workshop, University of South Australia, April 2005.
  Paper (pdf, 136 KB)   Paper (ps.gz, 134 KB)

2004

• A Probabilistic Geocoding System based on a National Address File
  Peter Christen, Tim Churches and Alan Willmore
  Accepted for the Australasian Data Mining Conference, Cairns, December 2004.
  Paper (pdf, 120 KB)   Paper (ps.gz, 128 KB)

• Some Methods for Blindfolded Record Linkage
  Tim Churches and Peter Christen
  Published online at BioMed Central Medical Informatics and Decision Making, June 2004.
  For abstract and downloadable PDF file see here.

• A Parallel Open Source Data Linkage System
  Peter Christen, Tim Churches and Markus Hegland
  Proceedings of the 8th PAKDD'04 (Pacific-Asia Conference on Knowledge Discovery and Data Mining), Sydney, May 2004.
  Springer Lecture Notes in Artificial Intelligence, (3056). Available online at Springer Online.
  Copyright for this publication is held by the Springer Verlag.
  Paper (pdf, 203 KB)   Paper (ps.gz, 82 KB)

• Blind Data Linkage using n-gram Similarity Comparisons
  Tim Churches and Peter Christen
  Proceedings of the 8th PAKDD'04 (Pacific-Asia Conference on Knowledge Discovery and Data Mining), Sydney, May 2004.
  Springer Lecture Notes in Artificial Intelligence, (3056). Available online at Springer Online.
  Copyright for this publication is held by the Springer Verlag.
  Paper (long version, pdf, 177 KB)   Paper (long version, ps.gz, 69 KB)

2003

• A Comparison of Fast Blocking Methods for Record Linkage
  Rohan Baxter, Peter Christen and Tim Churches
  Proceedings of the Workshop on Data Cleaning, Record Linkage and Object Consolidation at the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington DC, August 2003.
  Paper 3 pages (pdf, 87 KB)   Paper 6 pages (pdf, 138 KB)

• Parallelisation of Sparse Grids for Large Scale Data Analysis
  Jochen Garcke, Markus Hegland and Ole Nielsen
  in Computational Science - ICCS 2003, LNCS 2659, International Conference Melbourne, Australia and St. Petersburg, Russia, June 2003, Proceedings, Part III, pages 683-692, P.M.A. Sloot, D. Abramson, A. Bogdanov, J. Dongarra, A. Zomaya and Y. Gorbachev (Eds.), Springer.

• A Logical Formalisation of the Fellegi-Holt Method of Data Cleaning
  Agnes Boskovitz, Rajeev Gore and Markus Hegland
  Technical Report TR-ARP-02-03, Automated Reasoning Project, Australian National University, Canberra, May 2003.
  Paper (pdf, 132 KB)

• Parallel Algorithms for Predictive Modelling
  Markus Hegland
  Draft, April 2003.
  Paper (pdf, 327 KB)

• Approximation of a Thin Plate Spline Smoother Using Continuous Piecewise Polynomial Functions
  Stephen Roberts, Markus Hegland and Irfan Altas
  SIAM Journal on Numerical Analysis, vol. 41, no. 1, pages 208-234, 2003.
  Available online.

• Adaptive sparse grids
  Markus Hegland
  Proceedings of 10th Computational Techniques and Applications Conference CTAC-2001, ANZIAM Journal, vol. 44, C335--C353, editors: K. Burrage and Roger B. Sidje, April 2003.
  Available online.

• Data Mining - Challenges, Models, Methods and Algorithms
  Markus Hegland
  Draft, February 2003.
  Paper (pdf, 884 KB)  

2002

• Preparation of name and address data for record linkage using hidden Markov models
  Tim Churches, Peter Christen, Kim Lim and Justin X Zhu
  Published online at BioMed Central Medical Informatics and Decision Making, December 2002.
  For abstract and downloadable PDF file see here.

• Probabilistic Name and Address Cleaning and Standardisation
  Peter Christen, Tim Churches and Justin Xi Zhu
  Proceedings of the Australasian Data Mining Workshop, Canberra, December 2002.
  Paper (ps.gz, 74 KB)   Paper (pdf, 158 KB)

• How Fast is '-fast'? Performance Analysis of KDD Applications using Hardware Performance Counters on UltraSPARC-III
  Adam Czezowski and Peter Christen
  Proceedings of the Australasian Data Mining Workshop, Canberra, December 2002.
  Paper (ps.gz, 82 KB)   Paper (pdf, 174 KB)

• High-Performance Computing Techniques for Record Linkage
  Peter Christen, Justin Xi Zhu, Markus Hegland, Stephen Roberts, Ole M. Nielsen, Tim Churches and Kim Lim
  Proceedings of the Australian Health Outcomes Conference (AHOC-2002), Canberra, July 2002.
  Paper (ps.gz, 95 KB)   Paper (pdf, 233 KB)

• Additive Sparse Grid Fitting
  Markus Hegland
  Submitted to Fifth International Conference on Curves and Surfaces organized by AFA-SMAI, Saint-Malo, France, 27 June - 3 July, 2002.
  Paper (pdf, 136 KB)

• Graphical Models for High Dimensional Density Estimation
  Gordon T. Deane
  Honours Thesis in the Department of Mathematics at the Australian National University
  14 June 2002.
  Thesis (pdf, 1.1 MB)

• Algorithms for Association Rules
  Markus Hegland
  Course Notes, 2002.
  Paper (pdf, 95 KB)

• Symmetry and Fractal-like Structures in the Statistics of Sequence Comparison
  Hilary S Booth, Shev F MacNamara, Ole M. Nielsen and Susan R. Wilson
  Submitted to Journal of Computational Biology and Proceedings of RECOMB2003, Berlin, April 2003.
  Paper (ps.gz, 105 KB)   Paper (pdf, 98 KB)

• Parallel Computing Techniques for High-Performance Probabilistic Record Linkage
  Peter Christen, Markus Hegland, Stephen Roberts, Ole M. Nielsen, Tim Churches and Kim Lim
  Proceedings of the Symposium on Health Data Linkage, Sydney, March 2002.
  Paper (ps.gz, 91 KB)   Paper (pdf.gz, 107 KB)   Paper (pdf, 228 KB)

• Performance Analysis of KDD Applications using Hardware Event Counters
  Peter Christen and Adam Czezowski
  Technical Report TR-CS-02-01, ANU Joint Computer Science Technical Report Series, February 2002.
  Report (ps.gz, 131 KB)   Report (pdf.gz, 173 KB)

2001

• Adaptive Sparse Grids
  Markus Hegland
  Submitted to the CTAC-2001 Conference, Brisbane, 16-18 July 2001.
  Paper (ps.gz, 142 KB)

• DMtools - Open Source Software for Database Mining
  Peter Christen, Ole M. Nielsen and Markus Hegland
  Workshop on Database Support for KDD (at the PKDD'2001 Conference), Freiburg, Germany, September 2001. (Workshop proceedings online)
  Paper (ps.gz, 81 KB)
  

• Scalable Parallel Algorithms for Surface Fitting and Data Mining
  Peter Christen, Markus Hegland, Ole M. Nielsen, Stephen Roberts, Peter E. Strazdins and Irfan Altas
  Elsevier Journal of Parallel Computing, special issue on Aspects of Parallel Computing for Linear Systems and Associated Problems, Volume 27, Number 7, September 2001.

• Parallel Data Mining on a Beowulf Cluster
  Peter Christen, Ole M. Nielsen, Markus Hegland and Peter E. Strazdins
  Proceedings of the HPC Asia 2001 Conference, Gold Coast, Queensland, Australia, September 2001.
  Paper (ps.gz, 264 KB)   Paper (pdf.gz, 232 KB)

• Towards a Parallel Data Mining Toolbox
  Peter Christen, Markus Hegland, Ole M. Nielsen, Stephen Roberts, Peter E. Strazdins, Irfan Altas, Tatiana Semenova and Timothy Hancock
  Proceedings of the 15th International Parallel and Distributed Processing Symposium (IPDPS-2001), San Francisco, April 2001. Workshop Parallel and Distributed Data Mining.
  Copyright 2001 Institute of Electrical and Electronic Engineers (IEEE). Reprinted for the Proceedings of the IPDPS-2001.
  Paper (ps.gz, 140 KB)
  

• A Scalable Parallel FEM Surface Fitting Algorithm for Data Mining
  Peter Christen, Markus Hegland, Stephen Roberts, Ole M. Nielsen and Irfan Altas
  International Workshop on Mining Spatial and Temporal Data (at the PAKDD-2001 Conference), Hong Kong, April 2001.
  Paper (ps.gz, 229 KB)

• A Toolbox Approach to Flexible and Efficient Data Mining
  Ole M. Nielsen, Peter Christen, Markus Hegland, Tatiana Semenova and Timothy Hancock
  PAKDD-2001 Conference, Hong Kong, April 2001.
  Published in the Springer Lecture Notes in Computer Science, Artificial Intelligence series, LNAI2035.
  Copyright for this publication is held by the Springer Verlag.
  Paper (ps.gz, 157 KB)   Paper (pdf.gz, 166 KB)

• Data Mining with Python
  Ole M. Nielsen, Peter Christen, Markus Hegland and Tatiana Semenova
  9th International Python Conference, Long Beach, California, March 2001.
  Paper available upon request from: Ole Nielsen.

• A Scalable Parallel FEM Surface Fitting Algorithm for Data Mining
  Peter Christen, Markus Hegland, Stephen Roberts and Irfan Altas
  Technical Report TR-CS-01-01, ANU Joint Computer Science Technical Report Series, January 2001.
  Report (ps.gz, 254 KB)   Report (pdf.gz, 301 KB)

• Discovery and Classification of Variable Stars
  William Patrick Clarke
  A thesis submitted for the degree of Master of Science at the Australian National University, January 2001.
  Thesis (ps.gz, 4.3 MB)

2000

• High Dimensional Smoothing Based on Multilevel Analysis
  Markus Hegland, Ole M. Nielsen and Zuowei Shen
  Submitted, November 2000.
  Paper (ps.gz, 576 KB)

• Data Mining of Administrative Claims Data of Pathology Services
  Simon Hawkins, Graham Williams, Rohan Baxter, Peter Christen, Michael Fett, Markus Hegland, Fuchun Huang, Ole M. Nielsen, Tatiana Semenova and Andrew Smith
  Proceedings of the Thirty-Fourth Hawaii International Conference on System Sciences (HICSS-34), January 2001.
  Available upon request from: Rohan Baxter, CSIRO CMIS.

• Scalable Parallel Algorithms for Predictive Modelling
  Peter Christen, Markus Hegland, Ole M. Nielsen, Stephen Roberts and Irfan Altas
  Proceedings of the Data Mining 2000 Conference, Cambridge, UK, August 2000.
  Paper (ps.gz, 605 KB)

• Parallel Performance of Fast Wavelet Transforms
  Ole M. Nielsen and Markus Hegland
  International Journal of High Speed Computing, Vol. 11, No. 1 (2000) 55-74.
  Paper (ps.gz, 584 KB)   Paper (pdf.gz, 115 KB)

• Developing a Spline Smoothed Density
  Giles Hooker
  A thesis submitted for the degree of Bachelor of Science with Honours at the Australian National University, 2000.
  Thesis (ps.gz, 6.0 MB)

1999

• Additive Models in High Dimensions
  Markus Hegland and Vladimir Pestov
  Research Report 99-33, School of Mathematical and Computing Sciences, Victoria University of Wellington, December 1999.
  Available online at xxx.llnl.gov.
  Paper (pdf, 242 MB)

• Computational Challenges in Data Mining
  Markus Hegland
  Proceedings of the CTAC-99 Conference, Canberra, September 1999.
  Paper (ps.gz, 583 KB)

• Finite Element Thin Plate Splines in Density Estimation
  Markus Hegland, Giles Hooker and Stephen Roberts
  Proceedings of the CTAC-99 Conference, Canberra, September 1999.
  Paper (ps.gz, 360 KB)

• Identification and Classification of interesting variable stars in the MACHO database
  Bill Clarke and Markus Hegland
  Proceedings of the CTAC-99 Conference, Canberra, September 1999.

• High Dimensional Wavelet Smoothing
  Ole Møller Nielsen
  Proceedings of the CTAC-99 Conference, Canberra, September 1999.
  Paper (ps.gz, 1.5 MB)   Paper (pdf.gz, 1.5 MB)

• Parallelization of a Finite Element Surface Fitting Algorithm for Data Mining
  Peter Christen, Irfan Altas, Markus Hegland, Stephen Roberts, Kevin Burrage and Roger Sidje
  Proceedings of the CTAC-99 Conference, Canberra, September 1999.
  Paper (ps.gz, 552 KB)

• The Integrated Delivery of Large-Scale Data Mining: The ACSYS Data Mining Project
  Graham Williams, Irfan Altas, Sergey Barkin, Peter Christen, Markus Hegland, Alonso Marquez, Peter Milne, Rajehndra Nagappan and Stephen Roberts
  KDD-99 Workshop on Large-Scale Parallel KDD Systems, San Diego, August 1999,
  Springer Lecture Notes in Artificial Intelligence 1759.

• A Parallel Finite Element Surface Fitting Algorithm for Data Mining
  Peter Christen, Irfan Altas, Markus Hegland, Stephen Roberts, Kevin Burrage and Roger Sidje
  Proceedings of the ParCo-99 Conference, Delft, August 1999.

• A Parallel Solver for Generalised Additive Models
  Markus Hegland, Ian McIntosh and Berwin Turlach
  Computational Statistics and Data Analysis, 31(4), pages 377-396, 1999.
  Paper (ps.gz, 579 KB)

• Mining Taxation Data with the Parallel BMARS Algorithm
  Sergey Bakin, Markus Hegland and Graham Williams
  Parallel Algorithms and Applications, Vol. 15, Gordon and Breach Publishing, 2000.

1998

• Data-Mining Massive Time Series Astronomical Data Sets - a Case Study
  Michael K. Ng, Zhexue Huang and Markus Hegland
  Second Pacific-Asia Conference on Knowledge Discovery in Data Bases (PAKDD98) 1998.
  Paper (ps.gz, 226 KB)   Paper (pdf.gz, 480 KB)

• Finite Element Thin Plate Splines for Data Mining Applications
  Markus Hegland, Steve Roberts and Irfan Altas
  In 'Mathematical Methods for Curves & Surfaces II', M. Daehlen, T. Lyche and L.L. Schumaker, 1998, Vanderbilt University Press, Nashville, TN.
  Prepublished as SMS report MRR 057-97.
  Paper (ps.gz, 148 KB)   Paper (pdf.gz, 137 KB)
  

1997

• Cluster Analysis using Triangulation
  Markus Hegland and C. Eldershaw
  Computational Techniques and Applications: CTAC-97, B.J. Noye, M.D. Teubner and A.W. Gill, Eds., (World Scientific, Singapore).
  Paper (ps.gz, 132 KB)
  

• Can MARS be improved with B-splines?
  Sergey Bakin, Markus Hegland, Mike Osborne
  Computational Techniques and Applications: CTAC-97, B.J. Noye, M.D. Teubner and A.W. Gill, Eds., (World Scientific, Singapore).
  Paper (ps.gz, 188 KB)