Ваш браузер устарел.

Для того, чтобы использовать все возможности сайта, загрузите и установите один из этих браузеров.

скрыть

Article

  • Title

    Software failures prediction using RBF neural network

  • Authors

    Yakovyna Vitaliy S.

  • Subject

    COMPUTER AND INFORMATION NETWORKS AND SYSTEMS. MANUFACTURING AUTOMATION

  • Year 2015
    Issue 2(46)
    UDC 004.052.3:004.032.26
    DOI 10.15276/opu.2.46.2015.20
    Pages 111-118
  • Abstract

    One of the prospective techniques for software reliability prediction are those based on nonparametric models, in particular on artificial neural networks. In this paper the study of influence of number of input neurons of network based on radial basis function on the efficiency of software failures prediction presented in the form of time series is carried out. Software faults time series are constructed using Chromium and Chromium-OS open source software systems testing data with proposed further processing as a normalized values of the number of software failures in equal intervals, followed by transfer to man-days. It is demonstrated that the closest prediction can be achieved using Inverse Multiquadric activation function with 10…20 input layer neurons and 30 hidden neurons.

  • Keywords software, reliability, failure, RBF neural network, time series
  • Viewed: 1415 Dowloaded: 15
  • Download Article
  • References

    Література
    1.    Pham, H. System Software Reliability / H. Pham. — London: Springer, 2007. — 440 p.
    2.    Khoshgoftaar, T.M. Predicting software quality, during testing, using neural network models: A comparative study / T.M. Khoshgoftaar, R.M. Szabo // International Journal of Reliability, Quality and Safety Engineering. — 1994. — Vol. 1, Issue 3. — PP. 303—319.
    3.    Zheng, J. Predicting software reliability with neural network ensembles / J. Zheng // Expert Systems with Applications. — 2009. — Vol. 36, Issue 2. — PP. 2116—2122.
    4.    Paliwal, M. Neural networks and statistical techniques: A review of applications / M. Paliwal, U.A. Kumar // Expert Systems with Applications. — 2009. — Vol. 36, Issue 1. — PP. 2—17.
    5.    Karlik, B. Performance analysis of various activation functions in generalized MLP architectures of neural networks / B. Karlik, A.V. Olgac // International Journal of Artificial Intelligence and Expert Systems. — 2010. — Vol. 1, Issue 4. — PP. 111—122.
    6.    Buhmann, M.D. Radial Basis Functions: Theory and Implementations / M.D. Buhmann. — Cambridge: Cambridge University Press, 2009. — 272 p.
    7.    Broomhead, D.S. Multivariable functional interpolation and adaptive networks / D.S. Broomhead, D. Lowe // Complex Systems. — 1988. — Vol. 2, Issue 3. — PP. 321—355.
    8.    Yee, P.V. Regularized Radial Basis Function Networks: Theory and Applications / P.V. Yee, S. Haykin. — New York: Wiley, 2001. — 191 p.
    9.    Comparing support vector machines with Gaussian kernels to radial basis function classifiers / B. Schölkopf, K.-K. Sung, C.J.C. Burges, etc. // IEEE Transactions on Signal Processing. — 1997. — Vol. 45, Issue 11. — PP. 2758—2765.
    10.    Han, X. Approximate interpolation by neural networks with the inverse multiquadric functions / X. Han // Proceedings of Second International Symposium on Advances in Computation and Intelligence (ISICA 2007), Wuhan, China, September 21–23, 2007. — Berlin: Springer-Verlag, 2007. — PP. 296—304.
    11.    Yakovyna, V. Influence of the activation function of RBF neural network on software reliability time series prediction / V. Yakovyna, V. Ketsman // Proceedings of the VIIIth International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH’2012), Polyana—Svalyava, Ukraine, April 18–21, 2012. — Lviv: Publishing House of Lviv Polytechnic National University, 2012. — PP. 91—92.
    12.    On the possibility of software reliability prediction using RBF neural network / V. Yakovyna, O. Synytska, T. Kremen, V. Smirnov // Proceedings of the VIth International Scientific and Technical Conference „Computer Science and Information Technologies“ (CSIT’2011), Lviv, Ukraine, November 16–19, 2011. — Lviv: Publishing House Vezha & Co., 2011. — PP. 39—42.
    13.    Chromium: An open-source project to help move the web forward [Електронний ресурс] / Google. — Режим доступу: https://code.google.com/p/chromium/issues/list (Дата звернення: 10.03.2015).
    14.    Chromium-OS [Електронний ресурс] / Google. — Режим доступу: https://code.google.com/p/chromium-os/issues/list (Дата звернення: 10.03.2015).
    15.    Yakovyna, V. Influence of input neurons count for RBF neural network with Gaussian activation function on software faults prediction efficiency / V. Yakovyna, I. Garandzha // Proceedings of International conference “Intellectual Systems for Decision Making and Problems of Computational Intelligence” (ISDMCI’2013), Yevpatoria, Ukraine, May 20–24, 2013. — Kherson: Kherson National Technical University, 2013. — PP. 520—522.

    References

    1.    Pham, H. (2007). System Software Reliability. London: Springer.
    2.    Khoshgoftaar, T.M. and Szabo, R.M. (1994). Predicting software quality, during testing, using neural network models: A comparative study. International Journal of Reliability, Quality and Safety Engineering, 1(3), 303—319.
    3.    Zheng, J. (2009). Predicting software reliability with neural network ensembles. Expert Systems with Applications, 36(2), 2116—2122.
    4.    Paliwal, M. and Kumar, U.A. (2009). Neural networks and statistical techniques: A review of applications. Expert Systems with Applications, 36(1), 2—17.
    5.    Karlik, B. and Olgac, A.V. (2010). Performance analysis of various activation functions in generalized MLP architectures of neural networks. International Journal of Artificial Intelligence and Expert Systems, 1(4), 111—122.
    6.    Buhmann, M.D. (2009). Radial Basis Functions: Theory and Implementations. Cambridge: Cambridge University Press.
    7.    Broomhead, D.S. and Lowe, D. (1988). Multivariable functional interpolation and adaptive networks. Complex Systems, 2(3), 321—355.
    8.    Yee, P.V. and Haykin, S. (2001). Regularized Radial Basis Function Networks: Theory and Applications. New York: Wiley.
    9.    Schölkopf, B., Sung, K.-K., Burges, C.J.C., Girosi, F., Niyogi, P., Poggio, T. and Vapnik, V. (1997). Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Transactions on Signal Processing, 45(11), 2758—2765.
    10.    Han, X. (2007). Approximate interpolation by neural networks with the inverse multiquadric functions. In L. Kang, Y. Liu, S. Zeng (Eds.), Proceedings of Second International Symposium on Advances in Computation and Intelligence (ISICA 2007) (pp. 296—304). Berlin: Springer-Verlag.
    11.    Yakovyna, V. and Ketsman, V. (2012). Influence of the activation function of RBF neural network on software reliability time series prediction. In Proceedings of the VIIIth International Conference on Perspective Technologies and Methods in MEMS Design (MEMSTECH’2012) (pp. 91—92). Lviv: Publishing House of Lviv Polytechnic National University.
    12.    Yakovyna, V., Synytska, O., Kremen, T. and Smirnov, V. (2011). On the possibility of software reliability prediction using RBF neural network. In Proceedings of the VIth International Scientific and Technical Conference „Computer Science and Information Technologies“ (CSIT’2011) (pp. 39—42). Lviv: Publishing House Vezha & Co.
    13.    Chromium: An open-source project to help move the web forward. Retrieved from https://code.google.com/p/chromium/issues/list
    14.    Chromium-OS. Retrieved from https://code.google.com/p/chromium-os/issues/list
    15.    Yakovyna, V. and Garandzha, I. (2013). Influence of input neurons count for RBF neural network with Gaussian activation function on software faults prediction efficiency. In Proceedings of International Conference “Intellectual Systems for Decision Making and Problems of Computational Intelligence” (ISDMCI’2013) (pp. 520—522). Kherson: Kherson National Technical University.


  • Creative Commons License by Author(s)