DocumentCode :
2168748
Title :
A Study on Software Reliability Prediction Based on Transduction Inference
Author :
Lou, Jungang ; Jiang, Jianhui ; Shuai, Chunyan ; Wu, Ying
fYear :
2010
fDate :
1-4 Dec. 2010
Firstpage :
77
Lastpage :
80
Abstract :
Non-parametric statistical methods are applied to verdict that early failure behavior of the testing process may have less impact on later failure process, so it happens in software failure time prediction that one does not have enough information to estimate the software failure process well but do have enough information to estimate the failure data at given instance. The prediction accuracy of software reliability prediction models based on recurrent neural network, feed-forward neural network, relevance vector machine, support vector machine and some nonhomogeneous Poisson process models is compared. Experimental results show that software failure time prediction models based on transduction inference theory could achieve higher prediction accuracy.
Keywords :
failure analysis; feedforward neural nets; inference mechanisms; nonparametric statistics; program testing; recurrent neural nets; software fault tolerance; support vector machines; failure behavior; failure data; feed-forward neural network; non-parametric statistical methods; nonhomogeneous Poisson process models; prediction accuracy; recurrent neural network; relevance vector machine; software failure process; software failure time prediction models; software reliability prediction models; support vector machine; testing process; transduction inference; Artificial neural networks; Computational modeling; Predictive models; Software; Software reliability; Support vector machines; Training; Relevance vector machine; Software reliability prediction; Support vector machine; Transduction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Test Symposium (ATS), 2010 19th IEEE Asian
Conference_Location :
Shanghai
ISSN :
1081-7735
Print_ISBN :
978-1-4244-8841-4
Type :
conf
DOI :
10.1109/ATS.2010.22
Filename :
5692226
Link To Document :
بازگشت