Test Set Generation and Reduction With Artificial Neural Networks

Abstract

Reducing the number of test cases results directly in the saving of software testing resources. Based on the success of Neural Networks as classifiers in many fields we propose to use neural networks for automated input-output analysis of data-driven programs. Identifying input-output relationships, ranking input features and building equivalence classes of input attributes for a given code are three important outcomes of this research in addition to reducing the number of test cases. The proposed methodology is based on the three-phase algorithm for efficient network pruning developed by R. Setiono and his colleagues. A detailed study shows that the neural network pruning and ruleextraction can significantly reduce the number of test cases.

The application of artificial intelligence in software engineering

“…The authors concluded that in this ant colony optimization algorithm, a group of ants can effectively explore the graph and generate optimal test data to satisfy test coverage requirements. Furthermore, Saraph et al [160] discussed that analysis of inputs and outputs (I/O) to aid with testing. The authors proposed that using ANN for I/O analysis (by identifying important attributes and ranking them) can be effective.…”

Neural Network-Based Automated Priority Assigner

“…The proposed methodology has been used to test large scale software systems and automatic teller machine (ATM) Saraph et al [19] In order to reduce the number of test cases, neural networks has been used as classifiers in order to identify input output relations, ranking features, and forming equivalence classes of input domain An algorithm has been used for network pruning. Neural network pruning has been used in order to reduce the number.…”

Neural network based black box testing

“…al. [3] The work uses Neural Networks as classifiers in order to reduce the number of test cases. This has been done using the identification of input output relations, feature ranking and formation of equivalence classes of input domain.…”