Dr Russel Pears

Associate Professor

Phone: +64 9 921 9999 Ext 5344

Email: russel.pears@aut.ac.nz

Physical Address:
AUT Tower, Level 1,
2 – 14 Wakefield St,
Auckland 1010

Qualifications:

  • B.Sc. (Hons.) in Mathematics and Physics, University of Colombo, Sri Lanka
  • Postgraduate Diploma in Statistics, University of Sri Jayawardenapura, Sri Lanka
  • M.Sc. in Computer Science, University of Wales, College of Cardiff, United Kingdom
  • Ph.D. in Computer Science, University of Wales, College of Cardiff, United Kingdom

Biography:

Russel’s career in Computing spans 34 years. During this time he has held a number of academic positions in Universities both here and overseas. He has taught in various topics in Computer Science while practicing as a consultant in the IT industry in the areas of Database  Systems and Data Mining.  Russel has published in top tier Journals and Conferences in the Data Mining and Machine Learning literature

Teaching Areas:

  • Data Mining
  • Research Methods
Postgraduate Supervision
I have supervised 22 thesis/dissertation students to completion at the Masters level, and 7 at the Doctoral level.

Research Areas:

My research interests are currently in three areas: Mining High Speed Data Streams Pattern Mining and Time Series Prediction.


Publications:

a.  Recent Journal Publications

, , :
A graph based approach to inferring item weights for pattern mining. Expert Syst. Appl. 42(1): 451-461 () doi:10.1016/j.eswa.2014.07.030

, , , ,
Goal-oriented dynamic test generation. Information & Software Technology 66: 40-57 () doi:10.1016/j.infsof.2015.05.007

, :
Efficient negative association rule mining based on chance thresholds. Intell. Data Anal. 18(2): 243-260 ()  DOI: 10.3233/IDA-14063

, , :
Data stream mining for predicting software build outcomes using source code metrics. Information & Software Technology 56(2): 183-198 (doi:10.1016/j.infsof.2013.09.001

, , :
Detecting concept change in dynamic data streams - A sequential approach based on reservoir sampling. Machine Learning 97(3): 259-293 () 10.1007/s10994-013-5433-9 

, , :
Discovering diverse association rules from multidimensional schema. Expert Syst. Appl. 40(15): 5975-5996 (doi:10.1016/j.eswa.2013.05.031

, , :
Evolving integrated multi-model framework for on line multiple time series prediction. Evolving Systems 4(2): 99-117 () 10.1007/s12530-012-9069-y

, , , :
Weighted association rule mining via a graph based connectivity model. Inf. Sci. 218: 61-84 () doi:10.1016/j.ins.2012.07.001

, , :
A data mining approach to knowledge discovery from multidimensional cube structures. Knowl.-Based Syst. 40: 36-49 () doi:10.1016/j.knosys.2012.11.008

b.  Book Chapters

  • Widiputra H, Pears R, Kasabov N, “Kalman Filter to Estimate Dynamic and Important Patterns of Interaction between Multiple Variables” In Mark Columbus (ed.), Kalman Filtering, Nove Science, New York, 2010.
  • Pears R and Otema, R, “Boosting Prediction Accuracy of Imbalanced Data in Financial Credit Applications” In Rare Association Rule Mining and Knowledge Discovery: Technologies for Infrequent and Critical Event Detection, IGI Global Publishing, 2009.
  • Pears R, Houliston B, “Accelerating Multi Dimensional Queries in Data Warehouses” In Keng Siau and John Erickson (eds), Advanced Principles for Improving Database Design, System Modelling, and Software Development, IGI Global Publishing, USA., 2008.
  • Koh Yun Sing and Pears R, “A Multi Methodological Approach to Rare Association Rule Mining”, accepted for publication in Rare Association Rule Mining and Knowledge Discovery: Technologies for Infrequent and Critical Event Detection, IGI Global Publishing, 2008.
  • Kasabov N, Song Q, Jain, V, Benuskova, L, Gottgtroy, P, Jain, V, Verma, A, Havukkala, I, Rush, E, Pears, R, Tjahjana, A, Hu, Y, MacDonell, S,” Integrating local and personalised modelling with global ontology knowledge bases for biomedical and bioinformatics decision support”. In: Comp. Intel. In Biomed. & Bioinform., SCI 151, T.G. Smolinski et al. (eds), Springer-Verlag, Berlin Heidelberg, 2007


c.  Recent Refereed Conference Publications

, :
HI-Tree: Mining High Influence Patterns Using External and Internal Utility Values. DaWaK : 43-56 10.1007/978-3-319-22729-0_4


Last updated: 24-Nov-2016 8.26am

The information on this page was correct at time of publication. For a comprehensive overview of AUT qualifications, please refer to the Academic Calendar.