12,000

We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK

93%

93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Algorithms for Real-Time Clustering and Generat...
View graph of relations

« Back

Algorithms for Real-Time Clustering and Generation of Rules from Data

Research output: Contribution in Book/Report/ProceedingsChapter

Published

Publication date2007
Host publicationAdvances in Fuzzy Clustering and Its Applications
EditorsJ V de Oliveira, W Pedrycz
Place of publicationChichester
PublisherJohn Willey and Sons
Pages353-370
Number of pages18
ISBN (Print)978-0-470-02760-8
Original languageEnglish

Abstract

The problem of real-time clustering has gained considerable attention in recent years in conjunction with the advances in the areas of multiple model representation of complex systems, summarization of information, and novelty detection for diagnostics and prognostics. This chapter deals with two main approaches for real-time clustering – the first algorithm is density based and is derived from the Mountain/Subtractive clustering method while the second one is distance based and has its roots in the k-nearest neighbors (k-NN) and self-organizing maps (SOM) clustering methods. Applications of these algorithms for extraction of rules from data, for control of complex systems with multiple operating modes, fault detection, and prognostics are presented in the chapter. (c) John Willey and Sons