Network measures for information extraction in evolutionary algorithms

DOI

10.1080/18756891.2013.823004How to use a DOI?

Keywords

Knowledge extraction, network theory, optimization, evolutionary algorithms, computational intelligence

Abstract

Problem domain information extraction is a critical issue in many real-world optimization problems. Increasing the repertoire of techniques available in evolutionary algorithms with this purpose is fundamental for extending the applicability of these algorithms. In this paper we introduce a unifying information mining approach for evolutionary algorithms. Our proposal is based on a division of the stages where structural modelling of the variables interactions is applied. Particular topological characteristics induced from different stages of the modelling process are identified. Network theory is used to harvest problem structural information from the learned probabilistic graphical models (PGMs). We show how different statistical measures, previously studied for networks from different domains, can be applied to mine the graphical component of PGMs. We provide evidence that the computed measures can be employed for studying problem difficulty, classifying different problem instances and predicting the algorithm behavior.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Roberto Santana
AU  - Rubén Armañanzas
AU  - Concha Bielza
AU  - Pedro Larrañaga
PY  - 2013
DA  - 2013/11/01
TI  - Network measures for information extraction in evolutionary algorithms
JO  - International Journal of Computational Intelligence Systems
SP  - 1163
EP  - 1188
VL  - 6
IS  - 6
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2013.823004
DO  - 10.1080/18756891.2013.823004
ID  - Santana2013
ER  -