An implementation of genetic algorithms for rule based machine learning

Citation
S. Sette et L. Boullart, An implementation of genetic algorithms for rule based machine learning, ENG APP ART, 13(4), 2000, pp. 381-390
Citations number
14
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
ISSN journal
09521976 → ACNP
Volume
13
Issue
4
Year of publication
2000
Pages
381 - 390
Database
ISI
SICI code
0952-1976(200008)13:4<381:AIOGAF>2.0.ZU;2-T
Abstract
Genetic algorithms have given rise to two new fields of research where (glo bal) optimisation is of crucial importance: 'Genetic Programming' and 'Gene tic based Machine Learning' (GBML). In this paper the second domain (GBML) will be introduced. An overview of one of the first GBML implementations by Holland, also known as the Learning Classifier Systems (LCS) will be given . After describing and solving a well-known basic (educational) problem a m ore complex application of GBML is presented. The goal of this application is the automatic development of a rule set for an industrial production pro cess. To this end, the case study on generating a rule set for predicting t he spinnability in the fibre-to-yarn production process will be presented. A largely modified LCS, called Fuzzy Efficiency based Classifier System (FE CS), originally designed by one of the authors, is used to solve this probl em successfully. (C) 2000 Elsevier Science Ltd. All rights reserved.