Robust recurrent neural network modeling for software fault detection and correction prediction

被引:99
作者
Hu, Q. P. [1 ]
Xie, M.
Ng, S. H.
Levitin, G.
机构
[1] Natl Univ Singapore, Qual & Innovat Res Ctr, Dept Ind & Syst Engn, Singapore 119260, Singapore
[2] Israel Elect Corp Ltd, Reliabil & Equipment Dept, IL-31000 Aaifa, Israel
关键词
software reliability growth model; software fault detection; software fault correction; artificial neural networks; reliability prediction;
D O I
10.1016/j.ress.2006.04.007
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Software fault detection and correction processes are related although different, and they should be studied together. A practical approach is to apply software reliability growth models to model fault detection, and fault correction process is assumed to be a delayed process. On the other hand, the artificial neural networks model, as a data-driven approach, tries to model these two processes together with no assumptions. Specifically, feedforward backpropagation networks have shown their advantages over analytical models in fault number predictions. In this paper, the following approach is explored. First, recurrent neural networks are applied to model these two processes together. Within this framework, a systematic networks configuration approach is developed with genetic algorithm according to the prediction performance. In order to provide robust predictions, an extra factor characterizing the dispersion of prediction repetitions is incorporated into the performance function. Comparisons with feedforward neural networks and analytical models are developed with respect to a real data set. (c) 2006 Elsevier Ltd. All rights reserved.
引用
收藏
页码:332 / 340
页数:9
相关论文
共 30 条
[1]   Bayesian network based software reliability prediction with an operational profile [J].
Bai, CG .
JOURNAL OF SYSTEMS AND SOFTWARE, 2005, 77 (02) :103-112
[2]   On the neural network approach in software reliability modeling [J].
Cai, KY ;
Cai, L ;
Wang, WD ;
Yu, ZY ;
Zhang, D .
JOURNAL OF SYSTEMS AND SOFTWARE, 2001, 58 (01) :47-62
[3]  
CAI KY, 1998, KLUW INT SER SOFTW E, P1
[4]   FORECASTING THE BEHAVIOR OF MULTIVARIATE TIME-SERIES USING NEURAL NETWORKS [J].
CHAKRABORTY, K ;
MEHROTRA, K ;
MOHAN, CK ;
RANKA, S .
NEURAL NETWORKS, 1992, 5 (06) :961-970
[5]   Optimal software release scheduling based on artificial neural networks [J].
Dohi, T ;
Nishio, Y ;
Osaki, S .
ANNALS OF SOFTWARE ENGINEERING, 1999, 8 (1-4) :167-185
[6]   FINDING STRUCTURE IN TIME [J].
ELMAN, JL .
COGNITIVE SCIENCE, 1990, 14 (02) :179-211
[7]   A simulation approach to structure-based software reliability analysis [J].
Gokhale, SS ;
Lyu, MRT .
IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2005, 31 (08) :643-656
[8]   A pseudoinverse learning algorithm for feedforward neural networks with stacked generalization applications to software reliability growth data [J].
Guo, P ;
Lyu, MR .
NEUROCOMPUTING, 2004, 56 :101-121
[9]  
Ho SL, 2003, COMPUT MATH APPL, V46, P1037, DOI 10.1016/S0898-1221(03)00308-0
[10]   Cost-reliability-optimal release policy for software reliability models incorporating improvements in testing efficiency [J].
Huang, CY .
JOURNAL OF SYSTEMS AND SOFTWARE, 2005, 77 (02) :139-155