Please use this identifier to cite or link to this item: https://doi.org/10.1109/COMPSAC.2006.130
Title: Early software reliability prediction with extended ANN model
Authors: Hu, Q.P.
Dai, Y.S.
Xie, M. 
Ng, S.H. 
Issue Date: 2006
Source: Hu, Q.P.,Dai, Y.S.,Xie, M.,Ng, S.H. (2006). Early software reliability prediction with extended ANN model. Proceedings - International Computer Software and Applications Conference 2 : 234-239. ScholarBank@NUS Repository. https://doi.org/10.1109/COMPSAC.2006.130
Abstract: Generally, software reliability models can provide accurate reliability measurement in the later phase of testing. However, predictions in the early phase of software testing are useful as cost-effective and timely feedback. Early prediction is also feasible in practice with information from previous releases or similar projects. Such information has been utilized well for early reliability prediction with NHPP models by assuming the same failure rate between two similar projects. Alternatively, in this paper, we propose to "reuse " failure data from past projects/releases with ANN models to improve early reliability for current project/release. To illustrate the proposed approach, two numerical examples are developed. Better prediction performance is observed in early phase of testing compared with original ANN model without failure data reuse. Furthermore, the optimal switching point from proposed approach to original ANN model in the whole testing phase is studied, with specific analysis on the two examples. © 2006 IEEE.
Source Title: Proceedings - International Computer Software and Applications Conference
URI: http://scholarbank.nus.edu.sg/handle/10635/72323
ISBN: 0769526551
ISSN: 07303157
DOI: 10.1109/COMPSAC.2006.130
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

12
checked on Jan 16, 2018

Page view(s)

24
checked on Jan 18, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.