T. Ramasundaram

Work place: Department of Computer Science, Periyar University, Salem,Tamilnadu, India

E-mail: rofram01@yahoo.in


Research Interests: Software Construction, Software Development Process, Software Engineering


T.Ramasundaram is currently a Ph.D. candidate in the Department of Computer Science, Periyar University, Salem, Tamilnadu, India. He received his B.Sc., M.Sc., and M.Phil. degrees in Computer Science from the same university, in 2003, 2005, and 2009 respectively. His current research interest is Software Engineering.

Author Articles
Hybridization of Buffalo and Truncative Cyclic Gene Deep Neural Network-based Test Suite Optimization for Software Testing

By T. Ramasundaram V. Sangeetha

DOI: https://doi.org/10.5815/ijmecs.2022.04.04, Pub. Date: 8 Aug. 2022

Software testing is the significant part of the software development process to guarantee software quality with testing a program for discovering the software bugs. But, the software testing has a long execution time by using huge number of test suites in the software development process. In order to overcome the issue, a novel technique called Hybridized Buffalo and Truncation Cyclic Gene Optimization-based Densely Connected Deep Neural Network (HBTCGO-DCDNN) introduced to improve the software testing accuracy with minimal time consumption. At first, the numbers of test cases are given to the input layer of the deep neural network layer. In the first hidden layer, the test suite generation process is carried out by applying the improved buffalo optimization technique with different objective functions namely time and cost. The improved buffalo optimization selects optimal test cases and generates the test suites. After the generation, the redundant test cases from the test suite are eliminated in the reduction process in the second hidden layer. The Truncative Cyclic Uniformed Gene Optimization technique is applied for the test suite reduction process based on thefault coverage rate. Finally, the reduced test suites are obtained at the output layer of the deep neural network The experimental evaluation of the HBTCGO-DCDNN and existing methods are discussed using the test suite generation time, test suite reduction rate as well as fault coverage rate. The comparative results of proposed HBTCGO-DCDNN technique provide lesser the generation time by 48% and higher test suit reduction rate by 19% as well as fault coverage rate 18% than the other well-known methods.

[...] Read more.
Other Articles