Novel schemes for automated software testing using neural network

Abstract

The main goal of software testing is to design new test case sets so that it can depict the faults in the software product. As soon as these test cases have been designed, Test Oracle provides a method in which the software has to behave for a particular test case given. Prioritization of such test cases with the execution of their components specifying inputs, their operation, and their outcome will determine whether the application and their properties are working correctly. The prioritization methods are as follows: initial ordering, random ordering, and finally, reverse ordering based on fault detection abilities. For developing software applications, a test suite that was less commonly known as the suite for checking the validity of software was employed. The test suite contained a detailed set of instructions and goals for each test case collection based on the system and its configuration used during testing. newlineAutomating the generation of a test case and test oracle was researched extensively. From among the automated test oracle, the Artificial Neural Network (ANN) was used extensively but with a high computational complexity. This work proposed a weight-optimized ANN using Stochastic Diffusion Search (SDS) algorithm. The SDS applies to the search problems and their optimization wherein the component functions were independently evaluated with swarm agents maintaining a hypothesis on the optima. ANN refers to an adaptive system that is complex and can convert its internal structure on the basis of the information that is passed through it. This can be achieved by means of adjusting the connection and its weight. In the proposed ANN had a simple numerical procedure with sufficient information, and the SDS showed this in a dynamic training approach aside from optimization and the synthesis of the ANN. newline