An automatic test data generation from UML state diagram using genetic algorithm.
Chartchai Doungsa-ard, Keshav Prasad Dahal, Mohammad Alamgir Hossain, Taratip Suwannasart · 2007
Abstract — Software testing is a part of software development process. However, this part is the first one to miss by software developers if there is a limited time to complete the project. Software developers often finish their software construction closed to the delivery time, they usually don’t have enough time to create effective test cases for testing their programs. Creating test cases manually is a huge work for software developers in the rush hours. A tool which automatically generates test cases and test data can help the software developers to create test cases from software designs/models in early stage of the software development (before coding). Heuristic techniques can be applied for creating quality test data. In this paper, a GA-based test data generation technique has been proposed to generate test data from UML state diagram, so that test data can be generated before coding. The paper details the GA implementation to generate sequences of triggers for UML state diagram as test cases. The proposed algorithm has been demonstrated manually for an example of a vending machine. Index Terms — test data generation, gray-box testing, artificial intelligence, genetic algorithm I.