An implementation of genetic algorithms for rule based machine learning

Abstract

Genetic algorithms have given rise to two new fields of research where (global) optimisation is of crucial importance: ‘Genetic Programming’ and ‘Genetic 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 more complex application of GBML is presented. The goal of this application is the automatic development of a rule set for an industrial production process. To this end, the case study on generating a rule set for predicting the spinnability in the fibre-to-yarn production process will be presented. A largely modified LCS, called Fuzzy Efficiency based Classifier System (FECS), originally designed by one of the authors, is used to solve this problem successfully.