Document stream clustering: experimenting an incremental algorithm and AR-based tools for highlighting dynamic trends
Artificial Intelligence
2008-11-04 v1
Abstract
We address here two major challenges presented by dynamic data mining: 1) the stability challenge: we have implemented a rigorous incremental density-based clustering algorithm, independent from any initial conditions and ordering of the data-vectors stream, 2) the cognitive challenge: we have implemented a stringent selection process of association rules between clusters at time t-1 and time t for directly generating the main conclusions about the dynamics of a data-stream. We illustrate these points with an application to a two years and 2600 documents scientific information database.
Cite
@article{arxiv.0811.0340,
title = {Document stream clustering: experimenting an incremental algorithm and AR-based tools for highlighting dynamic trends},
author = {Alain Lelu and Martine Cadot and Pascal Cuxac},
journal= {arXiv preprint arXiv:0811.0340},
year = {2008}
}