Logo

CIRG - Research  -  Data Mining 



[Bullet] Home
About
News
[Bullet]

- NN
- DM
- SI
- EC
- MAS
- AIS
- IA
- Bioinf
- Games
- Opt
- FA
- Industry

Publications
People
Resources
Links
Contact Us

OVERVIEW

The data and text mining focus area has the objective of developing new techniques for knowledge discovery and to improve existing techniques. The focus area is also active in applying data mining techniques to solve real-world problems in consultation to South African industries.

Some of the questions being addressed are how to mine knowledge from data with continuous classes, how to cope with extremely large databases, more efficient data clustering methods and how to extract knowledge in environments where data changes over time. Tools are currently under development which address these questions.

ACTIVE MEMBERS

I Eyo

PhD Started in 2011

P Raharja

PhD Started in 2009

M Riekert

M.Sc Started in 2008
Hons-B.Sc Completed in 2007

A Graaff

PhD Started in 2005
M.Sc Completed in 2003

W van Heerden

M.Sc Started in 2002

ALUMNI MEMBERS

List alumni of this research focus area. [ Show ]

GROUP PUBLICATIONS

List publications of this research focus area. [ Show ]

MEMBER PROFILE



 Name:

 Willem van Heerden

Portrait photo

 E-mail:

 wvheerden@cs.up.ac.za

 Group(s):

 Data mining
Neural Networks

 

 Degree specific information: M.Sc

 Title:

 Exploratory Data Analysis and Data Mining with Self-Organising Feature Maps

 Abstract:

The Self-Organising Feature Maps (SOM) is an unsupervised machine learning approach that offers extremely useful data clustering and visualisation abilities. The approach has been successfully employed to a wide variety of problems. Exploratory Data Analysis (EDA) and Data Mining (DM) are both fields that attempt to algorithmically extract insightful knowledge from a data set, with a greater or lesser level of human assistance. This thesis aims to provide a complete survey of EDA and DM approaches that specifically utilise a SOM implementation. A new, hybrid approach to DM rule extraction, using a SOM in conjunction with other DM algorithms is presented. The hybrid approach is compared experimentally to existing approaches. Empirical results are presented to illustrate the relative merits of each EDA and DM approach.

 Supervisor / Co-Supervisor:

 AP Engelbrecht

 Thesis:

 Not available for download yet.




You are visitor #154526
Contact webmaster
Back to top

QualNet Network Simulator University Program Valid XHTML 1.0! Valid CSS!


Computational Intelligence Research Group
University of Pretoria
Copyright © 2017