A Non-Parametric Software Reliability Modeling Approach by Using Gene Expression Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4216

  author =       "Haifeng Li and Minyan Lu and Min Zeng and 
                 Bai-Qiao Huang",
  title =        "A Non-Parametric Software Reliability Modeling
                 Approach by Using Gene Expression Programming",
  journal =      "Journal of Information Science and Engineering",
  year =         "2012",
  volume =       "28",
  number =       "6",
  pages =        "1145--1160",
  month =        nov,
  keywords =     "genetic algorithms, genetic programming, Gene
                 Expression Programming, SBSE, software reliability
                 modelling, non-parametric model, machine learning,
                 software reliability",
  bibdate =      "2012-10-31",
  bibsource =    "DBLP,
  URL =          "http://www.iis.sinica.edu.tw/page/jise/2012/201211_10.html",
  size =         "16 pages",
  abstract =     "Software reliability growth models (SRGMs) are very
                 important for estimating and predicting software
                 reliability. However, because the assumptions of
                 traditional parametric SRGMs (PSRMs) are usually not
                 consistent with the real conditions, the prediction
                 accuracy of PSRMs are hence not very satisfying in most
                 cases. In contrast to PSRMs, the non-parametric SRGMs
                 (NPSRMs) which use machine learning (ML) techniques,
                 such as artificial neural networks (ANN), support
                 vector machine (SVM) and genetic programming (GP), for
                 reliability modelling can provide better prediction
                 results across various projects. Gene Expression
                 Programming (GEP) which is a new evolutionary algorithm
                 based on Genetic algorithm (GA) and GP, has been
                 acknowledged as a powerful ML and widely used in the
                 field of data mining. Thus, we apply GEP into
                 non-parametric software reliability modelling in this
                 paper due to its unique and pretty characters, such as
                 genetic encoding method, translation process of
                 chromosomes. This new GEP-based modelling approach
                 considers some important characters of reliability
                 modelling in several main components of GEP, i.e.
                 function set, terminal criteria, fitness function, and
                 then obtains the final NPSRM (GEP-NPSRM) by training on
                 failure data. Finally, on several real failure
                 data-sets based on time or coverage, four case studies
                 are proposed by respectively comparing GEP-NPSRM with
                 several representative PSRMs, NPSRMs based on ANN, SVM
                 and GP in the form of fitting and prediction power
                 which show that compared with the comparison models,
                 the GEP-NPSRM provides a significantly better power of
                 reliability fitting and prediction. In other words, the
                 GEP is promising and effective for reliability
                 modelling. So far as we know, it is the first time that
                 GEP is applied into constructing NPSRM.",

Genetic Programming entries for Haifeng Li Minyan Lu Min Zeng Bai-Qiao Huang