A survey of software reliability growth models using non-parametric methods

Saley, M. K.; Sreedharan, Sasikumaran

doi:10.1109/iccic.2014.7238416

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new breed of ANN based SRGM's have been introduced by researchers in this field. While parametric models give clues to process composition and behavior, the nonparametric ANN SRGM's offer greater accuracy and flexibility [1].…”

Section: Introductionmentioning

confidence: 99%

Accuracy of Artificial Neural Network Models of Software Reliability Growth – A Survey

Saley¹,

Sreedharan²

2015

RCS

Self Cite

View full text Add to dashboard Cite

Software Engineering data is being analyzed by classical statistical methods and non parametric methods. Performance models are constructed using classical approach as a high maturity practice. Such practices are constrained by data quality and inadequacy of data analysis methods to treat data from real life projects. Data mining techniques can broaden the data analysis capability and improve prediction accuracy even with commonly presented data. Artificial neural networks are found as an improved prediction error estimation method against traditional parametric software reliability growth models. In this paper, we study prediction errors of Artificial Neural Networks (ANN) based Software Reliability Growth Models (ANN SRGM) with the objective of arriving at a criteria for selecting the methods having least prediction errors. All major works in ANN SRGM's are considered and reported errors are analyzed. Accuracy of ANN SRGM's are compared against that of parametric models. Then, inter-comparison of error performances of ANN SRGM's of different applications is made.

show abstract

Section: Introductionmentioning

confidence: 99%