Indian Journal of Science and Technology
Year: 2016, Volume: 9, Issue: 44, Pages: 1-6
V. Chandraprakash, M. R. Narasingarao, M. Sindhu Saraswathi, N. Dorothy William, T. Lavanya Kumari and K. Venkata Sujith
Department of Computer Science and Engineering, K. L. University, Green Fields, Vaddeswaram, Guntur - 522502, Andhra Pradesh, India; [email protected], [email protected], [email protected], [email protected], [email protected], [email protected]
Objective: To find out whether a trained neural network can predict the Average percentage of Faults Detected (APFD) value for the given prioritized test suite without having the knowledge of computing APFD formula. Methods: To generate a test suite, A fault matrix containing faults and test cases is considered and for each possible permutation of test cases. The APFD value is computed for each of such test suite. The test suites with their respective APFD values are given to the neural network during training. During testing, a prioritized test suite is fed to the neural network. The APFD value predicted by the neural network is noted down. Findings: The neural network has learnt to predict APFD value of the given prioritized test suite. The predicted APFD value is compared with computed APFD value using the Root Mean Square Deviation. The deviation is found to be very low, showing that the values are very nearer. Applications/Improvements: Number of hidden layers can be increased in order to reduce the deviation further.
Keywords: Artificial Neural Network, Average Percentage of Faults Detected, Test Case Prioritization
Subscribe now for latest articles and news.