Presentation 2009-05-29
A study on software reliability assessment based on a wavelet
Xiao XIAO, Tadashi DOHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently the wavelet analysis has been frequently used for not only image processing and signal processing but also time series analysis with high speed and accuracy requirements. In this article we apply a wavelet-based estimation method with the Haar-Fisz transform to estimation of non-homogeneous Poisson processes, and develop a novel software reliability assessment method. There are mainly two advantages for use of the wavelet-based estimation: (i) it does need no parametric assumptions on the software debugging scenario and (ii) the computational overhead arising in goodness-of-fit and prediction tests is rather small since the fitting procedure of data is quite easy and simple. Finally, we show through validation tests with real software fault data that our wavelet-based non-parametric estimation method can provide higher estimation performances than the conventional maximum likelihood estimation and the least squares estimation to estimate the number of detected software faults per testing date.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) software reliability / wavelet analysis / non-homogeneous Poisson process / goodness-of-fit test / non-stationary time series analysis
Paper # R2009-9
Date of Issue

Conference Information
Committee R
Conference Date 2009/5/22(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Reliability(R)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on software reliability assessment based on a wavelet
Sub Title (in English)
Keyword(1) software reliability
Keyword(2) wavelet analysis
Keyword(3) non-homogeneous Poisson process
Keyword(4) goodness-of-fit test
Keyword(5) non-stationary time series analysis
1st Author's Name Xiao XIAO
1st Author's Affiliation Department of Information Engineering, Graduate School of Engineering, Hiroshima University()
2nd Author's Name Tadashi DOHI
2nd Author's Affiliation Department of Information Engineering, Graduate School of Engineering, Hiroshima University
Date 2009-05-29
Paper # R2009-9
Volume (vol) vol.109
Number (no) 67
Page pp.pp.-
#Pages 6
Date of Issue