Neural Network-based Framework for Data Stream Mining

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We address the problem of mining data streams using Artificial Neural Networks (ANN). Usual data stream clustering models (eg. k-means) are too de- pendent on assumptions regarding cluster statistical properties (ie. number of clus- ters, cluster shape), while unsupervised ANN algorithms (Adaptive Resonant The- ory — ART networks and Self-Organizing Maps — SOM) are recognized widely by their ability to discover hidden patterns, generalization capabilities and robust- ness to noise. However, use of ANNs with the data stream model is still poorly ex- plored. We propose a methodology and modular framework to cluster data streams and extract other relevant knowledge. Empirical results with both synthetic and real data provide evidence of the validity of the approach.
Original languageUnknown
Title of host publicationFrontiers in Artificial Intelligence and Applications
Pages294-305
ISBN (Electronic)978-1-61499-096-3
DOIs
Publication statusPublished - 1 Jan 2012
EventECAI - European Conference on Artificial Inteligence -
Duration: 1 Jan 2012 → …

Conference

ConferenceECAI - European Conference on Artificial Inteligence
Period1/01/12 → …

Cite this