Conceptual Clustering and its Application to Concept Drift and Novelty Detection
N. Fanizzi, C. d'Amato, and F. Esposito. Proceedings of the 5th European Semantic Web Conference, Berlin, Heidelberg, Springer Verlag, (June 2008)
Abstract
We present a method based on clustering techniques to detect concept drift or novelty in a knowledge based expressed in Description Logics. The method exploits an effective and language-independent semi-distance measure defined for the space of individuals, that is based on a finite number of dimensions corresponding to a committee of discriminating features (represented by concept descriptions). A maximally discriminating group of features can be obtained with the randomized optimization methods described in the paper. An experimentation with some ontologies proves the feasibility of our method and its effectiveness in terms of clustering validity indices. Then, with a supervised learning phase, each cluster can be assigned with a refined or newly constructed intensional definition expressed in the adopted language. We propose a method for exploiting the clustering results for concept drift and novelty detection
%0 Conference Paper
%1 fanizzi2008conceptual
%A Fanizzi, Nicola
%A d'Amato, Claudia
%A Esposito, Floriana
%B Proceedings of the 5th European Semantic Web Conference
%C Berlin, Heidelberg
%D 2008
%E Hauswirth, Manfred
%E Koubarakis, Manolis
%E Bechhofer, Sean
%I Springer Verlag
%K clustering drift conceptual similarity semantic concept setection novelty learning
%T Conceptual Clustering and its Application to Concept Drift and Novelty Detection
%U http://data.semanticweb.org/conference/eswc/2008/papers/273
%X We present a method based on clustering techniques to detect concept drift or novelty in a knowledge based expressed in Description Logics. The method exploits an effective and language-independent semi-distance measure defined for the space of individuals, that is based on a finite number of dimensions corresponding to a committee of discriminating features (represented by concept descriptions). A maximally discriminating group of features can be obtained with the randomized optimization methods described in the paper. An experimentation with some ontologies proves the feasibility of our method and its effectiveness in terms of clustering validity indices. Then, with a supervised learning phase, each cluster can be assigned with a refined or newly constructed intensional definition expressed in the adopted language. We propose a method for exploiting the clustering results for concept drift and novelty detection
@inproceedings{fanizzi2008conceptual,
abstract = {We present a method based on clustering techniques to detect concept drift or novelty in a knowledge based expressed in Description Logics. The method exploits an effective and language-independent semi-distance measure defined for the space of individuals, that is based on a finite number of dimensions corresponding to a committee of discriminating features (represented by concept descriptions). A maximally discriminating group of features can be obtained with the randomized optimization methods described in the paper. An experimentation with some ontologies proves the feasibility of our method and its effectiveness in terms of clustering validity indices. Then, with a supervised learning phase, each cluster can be assigned with a refined or newly constructed intensional definition expressed in the adopted language. We propose a method for exploiting the clustering results for concept drift and novelty detection},
added-at = {2008-05-28T14:50:02.000+0200},
address = {Berlin, Heidelberg},
author = {Fanizzi, Nicola and d'Amato, Claudia and Esposito, Floriana},
biburl = {https://www.bibsonomy.org/bibtex/22f250404994a287160f00ef1e8a631ac/eswc2008},
booktitle = {Proceedings of the 5th European Semantic Web Conference},
editor = {Hauswirth, Manfred and Koubarakis, Manolis and Bechhofer, Sean},
interhash = {a0e5e87741613d3742f1c60b84d9d924},
intrahash = {2f250404994a287160f00ef1e8a631ac},
keywords = {clustering drift conceptual similarity semantic concept setection novelty learning},
month = {June},
publisher = {Springer Verlag},
series = {LNCS},
timestamp = {2008-05-28T14:50:03.000+0200},
title = {Conceptual Clustering and its Application to Concept Drift and Novelty Detection},
url = {http://data.semanticweb.org/conference/eswc/2008/papers/273},
year = 2008
}