KEDRI - Centre for Data Mining and Decision Support Systems

KEDRI
AUT

KEDRI
AUT Main Nav
Centre Banner
Main Content

Centre for Data Mining and Decision Support Systems

This page is a summary of what our centre does and who we are. It covers:

We develop software and hardware systems to enable comprehensive data analysis, knowledge discovery and decision support across a range of domain areas.

Research projects

  • NeuCom (www.theneucom.com) - a self-programmable, learning and reasoning computer environment (Fig. 1). NeuCom is currently being used by 35 universities from all over the world for teaching and research.
  • On-line prediction and resource optimisation of mobile phone calls traffic (with Telecom/Lucent/MediLab, U Auckland and U Canterbury) (Fig. 1).
  • On-line prediction and optimisation of resources for milk delivery and production (with Fonterra) (Fig. 1).
  • Wind prediction for the wind energy resources
  • Multiple time-series modelling for financial applications
Snapshot of the data mining and decision support environment NeuCom and two of its applications with Telecom and Fonterra.
Figure 1. A snapshot of the data mining and decision support environment NeuCom (www.theneucom.com) and two of its applications with Telecom and Fonterra.

NeuCom - Neuro-Computing Decision Support Environment

Project Team

  • Dr. Peter Hwang
  • Prof. N. Kasabov
  • Mr. Dougal Greer
  • Dr. Qun Song
  • Dr. Zeke Chan
  • Dr. Shaoning Pang
  • Ms. Liang Goh
NeuCom is a complete software package for generic data processing that emphasis on the evolving connectionist system modelling techniques. It contains a set of tools for data visualisation, normalisation, analysis, feature extraction, clustering and modelling with cross validation and genetic algorithm with an consistent and easy to use interface. It is designed to help the user to extract knowledge from any given dataset and, if the user desire, developed prediction or classification models with it. This software is currently being used in several research projects at KEDRI. It is also used as a teaching environment at AUT.

It is self-programmable, learning and reasoning computer environment based on connectionist (Neurocomputing) modules. NeuCom learns from data, thus evolving new connectionist modules. The modules can adapt to new incoming data in an on-line incremental, life-long learning mode, and can extract meaningful rules that would help people discover new knowledge in their respective fields. NeuCom is based on the theory of Evolving Connectionist Systems (ECOS) as published in ("Evolving connectionist systems: methods and applications in bioinformatics, brain study and intelligent machines", N.Kasabov, Springer Verlag, London, 2002.

NeuCom includes both software and hardware modules. It can be run on both conventional computers (emulated) or on specialised neurocomputer hardware for special applications. Different computing devices can be connected to Neucom. A small version of NeuCom can run on palmtop computers.

Our researchers

  • Dr. Russel Pears, Centre Director
  • Prof. Nikola Kasabov
  • Harya Widiputra
  • Marin Karaivanov
  • Gary Chen
  • Kshitij Dhoble

Last updated: 02 Dec 2011 10:16am

Auckland University of Technology, New Zealand | Copyright © | Privacy | Site map