Indian Journal of Science and Technology

The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off


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.
User