Publications

Recent publications

 

Journal papers

 

1. Lutu, P. E. N. & Engelbrecht A.P. (2012) Base model combination algorithm for resolving tied predictions for k-nearest neighbour aggregate models, to appear in INFORMS JOC.

 

2. Lutu, P. E. N. & Engelbrecht A.P. (2012) Positive-Versus-Negative Classification for Model Aggregation in Predictive Data Mining, to appear in INFORMS JOC.

 

3.  Lutu, P. E. N. & Engelbrecht, A. P. (2012) Using OVA modeling to improve classification performance for large datasets. Expert Systems With Applications,  39 (4) 4358-4376.

 

4. Motjolopane, R. & Lutu, P.E.N. (2012)  Improving data quality in the banking supervisory data of Southern Africa central banks. Electronic Journal of Information Systems in Developing Countries (EJIDC), 50. (also appears in the Proceedings of the International Development Informatics Association Conference, IDIA 2010, Cape Town, November 2010 )

 

5. Lutu, P.E.N. & Engelbrecht, A.P. (2010) A decision-rule based method for feature selection in predictive data mining.  Expert systems with applications, 37, 602-609.

 

6. Lutu, P.E.N &  Engelbrecht, A.P.,  (2006) A comparative study of sample selection methods for classification.   SACJ: Joint  Special Issue ARIMA & SACJ -  Advances in End-User Data Mining Techniques, 36, 69-85

 

 

Conference papers

 

1. Lutu, P.E.N. (2012) Generation of an empirical theory for positive-versus-negative ensemble classification. Proceedings of the Silver 2012 Workshop, collocated with the ECML-PKDD 2012 conference, Bristol, United Kingdom, 24-28 September, 2012.

2. Lutu, P.E.N. (2012) Replication of base models to improve the performance of positive-versus-negative classification ensembles for predictive data mining, presentation at the 41st Operations Research Society of South Africa – ORSSA 2012 Annual Conference, Johannesburg, 17-19 September, 2012.

3. Lutu, P.E.N. (2011) Empirical comparison of four classifier fusion strategies for positive-versus-negative ensembles. Proceedings of the South African Institute of Computer Science and Information Technology  Conference, SAICSIT 2011, October 3-5 2011, Cape Town, South Africa. ACM International Conference proceedings.

 

4. Lutu, P.E.N. (2011) Using confusion matrices and confusion graphs to design ensemble classification models from large datasets, in A. Cuzzocrea and U. Dayal (eds.) Proceedings of the 13th International Conference on Data warehousing and Knowledge Discovery, DaWak 2011, Toulouse, France, August / September 2011, Lecture Notes in Computer Science, LNCS 6862, 301-315.

 

5. Lutu, P.E.N. &  Meyer, B. (2008) An exploratory study of the adoption and usage of business intelligence in public sector organisations in  South Africa.  Proceedings of the  IFIP WG 9.4 Workshop, Pretoria,  September 2008.

 

6. Adigun, E.A &  Lutu,P.E.N. (2006)  Mobile and wireless technology, making a world of difference.  Proceedings of the Conference on Community Informatics for Developing Countries: Understanding and Organising for a Participatory Future Information Society  (CIDC2006) 31 August -2 september 2006, Cape Town, South Africa.  

 

7. Lutu,P.E.N. (2002) An integrated approach for scaling up  classification and prediction algorithms for data mining. proceedings of the South African Institute of Computer Science and Information Technology  Conference, SAICSIT 2002. ACM  International Conference Proceedings.

8. Lutu, P.E.N. (2001) Optimal multi-splitting of numeric ranges for  decision tree induction. International Conference on Operations Research (ICORD 2001), May 2001.

 

Chapters in books

 

1.  Lutu, P.E.N. (2006) Database sampling for data mining in: Encyclopedia for Data Warehousing and Data Mining, Wang, J. Editor, 2006.