Software testing by using the black-box method and the equivalence partition technique to predict the accuracy of the neural network base

Authors

  • Zulkifli Computer Science Department, BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480
  • Gaol FL Computer Science Department, BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480
  • Warnars HLHS Computer Science Department, BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480
  • Soewito B Computer Science Department, BINUS Graduate Program – Doctor of Computer Science, Bina Nusantara University Jakarta, Indonesia 11480

Keywords:

Neural Network, Black-Box, Equivalence Partitions

Abstract

A neural network algorithm is an artificial nervous system or artificial neural network, it is a physical cellular system that can acquire, store and use the knowledge gained from experience for activation using bipolar sigmoid where the output value ranges from -1 to 1. Because there is a yet of a neural network algorithm model to predict the level of accuracy in terms of software testing, the equivalent partitions black-box technique is used. The black-box software testing method is a testing approach where the data comes from defined functional requirements regardless of the final program structure, and the technique used is equivalent partitions. The design of the accurate prediction of this research is by determining the college application as the software to be tested, then testing it using the black-box method with the equivalence partitions technique. This test was chosen because it will find software errors in several categories. From black-box testing, a dataset is obtained to measure the accuracy of real output and predictive output. The last step is to calculate the error, RSME from the real output, and the predicted output. Furthermore, the final results of the research on the neural network algorithm that is applied to determine the prediction of the accuracy level of black-box software testing with the equivalent partitioning technique is the average accuracy above 80%.

References

Albert Endres, Cs. (2003). Hanbook software and System Engineering, Empirical Observations, Laws and Theories.

B. B. Agarwal, C. (2010). Software Engineering & Testing. Boston.

Beizer, B. (1990). Software Testing Techniques, Published by Van Nostrand Reinhold, New York.

Myers, G. (1979). The Art of Software Testing, Wiley; 2nd edition (June 21, 2004).

Berard, C. (1994). Issues in the Testing of Object-Oriented Software.

Fournier, Cs. (2009). Essential Software Testing: A Use-Case Approach.

Mark Last, Cs. (2002). Effective Black-Box Testing with Genetic Algorithms.

Hetzel, W. C. (1988). The Complete Guide to Software Testing, 2nd ed.

Jacek. M. Zuranda. (1992). Introduction to artificial neural systems.

Albert Endres, Cs. (2003). Hanbook software and System Engineering, Empirical Observations, Laws and Theories.

Simon, H. (1999:p20). Neural networks – A comprehensive Foundation.

Patrick J, C. (2000). Black-Box Test Reduction Using Input-Output Analysis. ACM.

Downloads

Published

2024-02-26

How to Cite

Zulkifli, Gaol, F. L., Warnars, H. L. H. S., & Soewito, B. (2024). Software testing by using the black-box method and the equivalence partition technique to predict the accuracy of the neural network base. COMPUSOFT: An International Journal of Advanced Computer Technology, 9(10), 3856–3859. Retrieved from https://ijact.in/index.php/j/article/view/592

Issue

Section

Original Research Article

Similar Articles

1 2 3 4 5 6 7 8 9 10 > >> 

You may also start an advanced similarity search for this article.