Identification of diagnostic rules with the application of an evolutionary algorithm

The paper deals with a way of identification of associative and diagnostic rules, which determine relationships between features of observed processes. Rules are identified by means of a method based on the application of an evolutionary algorithm. Special ways of coding, genetic operations and individual assessments were elaborated. The approach described in the paper is a part of a method of diagnostic inference with the use of contexts. Identified associative rules are transformed into diagnostic rules within given contexts.