Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/23288
Title: On the neural network approach in software reliability modeling
Authors: Cai, KY
Cai, L
Wang, WD
Yu, ZY
Zhang, D 
Keywords: Empirical probability density distribution
Filtering
Network architecture
Neural network
Scaling function
Software operational profile
Software reliability modeling
Issue Date: 2001
Publisher: Elsevier
Source: Journal of systems and software, 2001, v. 58, no. 1, p. 47-62 How to cite?
Journal: Journal of systems and software 
Abstract: Previous studies have shown that the neural network approach can be applied to identify defect-prone modules and predict the cumulative number of observed software failures. In this study we examine the effectiveness of the neural network approach in handling dynamic software reliability data overall and present several new findings. Specifically, we find 1. The neural network approach is more appropriate for handling datasets with 'smooth' trends than for handling datasets with large fluctuations. 2. The training results are much better than the prediction results in general. 3. The empirical probability density distribution of predicting data resembles that of training data. A neural network can qualitatively predict what it has learned. 4. Due to the essential problems associated with the neural network approach and software reliability data, more often than not, the neural network approach fails to generate satisfactory quantitative results.
URI: http://hdl.handle.net/10397/23288
ISSN: 0164-1212
DOI: 10.1016/S0164-1212(01)00027-9
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

100
Last Week
0
Last month
2
Citations as of Sep 10, 2017

WEB OF SCIENCETM
Citations

73
Last Week
0
Last month
0
Citations as of Sep 22, 2017

Page view(s)

48
Last Week
1
Last month
Checked on Sep 18, 2017

Google ScholarTM

Check

Altmetric



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