A Neural Network Approach for Software Defects Fix Effort Estimation

H. Zeng and D. Rine (USA)

Keywords

Defects fix effort, software process metric, neural networks, Self Organizing Map (SOM)

Abstract

Software defects fix effort is an important software development process metric that plays a critical role in software quality assurance. Generally parametric effort estimation techniques using historical Lines of Code (LOC) and Function Points (FP) data are used to estimate effort of defects fix. However, these techniques are neither efficient nor effective for a new different kind of project's fixing defects when code will be written within the context of a different project or organization. In this paper, we present our strategic solution for estimating software defect fix effort by using a non-parametric technique applying a dissimilarity matrix and self organizing neural network for software defects clustering and effort prediction.

Important Links:



Go Back


IASTED
Rotating Call For Paper Image