No abstract

Now-a-days software has a great impact on different aspects of human life. Software systems are responsible for safety of major critical tasks. To prevent catastrophic malfunctions, promising quality testing techniques should be used during software development. Software testing is an effective technique to catch defects, but it significantly increases the development cost. Therefore, automated testing is a major issue in software engineering. Search-Based Software Testing (SBST), specifically genetic algorithm, is the most popular technique in automated testing for achieving appropriate degree of software quality. In this paper TLBO, a swarm intelligence technique, is proposed for automatic test data generation as well as for evaluation of test results. The algorithm is implemented in EvoSuite, which is a reference tool for search-based software testing. Empirical studies have been carried out on the SF110 dataset which contains 110 java projects from the online code repository SourceForge and the results show that the TLBO provides competitive results in comparison with major genetic based methods.