Predicate Expression Cost Functions to Guide Evolutionary Search for Test Data

Several researchers are using evolutionary search methods to search for test data with which to test a program. The fitness or cost function depends on the test goal but almost invariably an important component of the cost function is an estimate of the cost of satisfying a predicate expression as might occur in branches, exception conditions, etc. This paper reviews the commonly used cost functions and points out some deficiencies. Alternative cost functions are proposed to overcome these deficiencies. The evidence from an experiment is that they are more reliable.

• Type: Conference
• Year: 2003
• Where: GECCO
• Authors: Leonardo Bottaci
• Keywords: Alternative Cost Functions, Cost Functions, Evolutionary Search Methods, GECCO 2003