AUTOMATED FAULT TAXONOMY AND REWORK EVALUATOR USING DATA SCIENCE AND DEEP LEARNING TECHNIQUES

  • P. Patchaiammal, G. Sundar, Dr. R. Thirumalaiselvi
Keywords: Software Development Life Cycle (SDLC), RNN (Recurrent Neural Network), Tkinter, GFT (Genetic Fault Taxonomy), Deep Learning, CNN (Convolutional Neural Network), SQLite Database.

Abstract

In software development rework plays a major role to delay the software delivery and also increase the risk of failure.  The quality of software is also impacted by rework. This research work provides in depth details of rework occurrence in both online and offline software development. In this work first automated genetic fault taxonomy is designed using python. Also, it provides rework evaluator tool to analyze the rework occurrence of software development with and without usage of fault taxonomy. The result recommends that using fault taxonomy along with software development phase reduce the rework percentage in software development.

Published
2021-07-28
How to Cite
Dr. R. Thirumalaiselvi, P. P. G. S. (2021). AUTOMATED FAULT TAXONOMY AND REWORK EVALUATOR USING DATA SCIENCE AND DEEP LEARNING TECHNIQUES. Design Engineering, 5344- 5363. Retrieved from http://thedesignengineering.com/index.php/DE/article/view/2986
Issue
Vol 2021: Issue 07
Section
Articles