Recurrent Radial Basis Function Network for Failure Time Series Prediction

An adaptive software reliability prediction model using evolutionary connectionist approach based on Recurrent Radial Basis Function architecture is proposed. Based on the currently available software failure time data, Fuzzy Min-Max algorithm is used to globally optimize the number of the k Gaussian nodes. The corresponding optimized neural network architecture is iteratively and dynamically reconfigured in real-time as new actual failure time data arrives. The performance of our proposed approach has been tested using sixteen real-time software failure data. Numerical results show that our proposed approach is robust across different software projects, and has a better performance with respect to next-steppredictability compared to existing neural network model for failure time prediction.

Authors:

• Ryad Zemouri
• Paul Ciprian Patic

Keywords:

• Neural network
• Prediction error
• Recurrent RadialBasis Function Network
• Reliability prediction.

References:

[1] Adnan, W.A., Yaacob, M.H., 1994. An integrated neural-fuzzy system
of software reliability prediction. In: Proceedings of the 1st International
Conference on Software Testing, Reliability and Quality Assurance. pp.
154-158.
[2] Adnan, W.A., Yaacob, M.H., Anas, R., Tamjis, M.R., 2000. Artificial
neural network for software reliability assessment. In: 2000 TENCON
Proceedings of Intelligent Systems and Technologies for the New
Millennium. pp. 446-451.
[3] Aljahdali, S.H., Sheta, A., Rine, D., 2001. Prediction of software
reliability: a comparison between regression and neural network nonparametric
models. In: Proceedings of ACS/IEEE International
Conference on Computer Systems and Applications. pp. 470-473.
[4] Aljahdali, S.H., Sheta, A., Rine, D., 2002. Predicting accumulated faults
in software testing process using radial basis function network models.
In: Proceedings of the 17th International Conference on Computers and
their Applications. pp. 26-29.
[5] Cai, K.Y., Cai, L., Wang, W.D., Yu, Z.Y., Zhang, D., 2001. On the
neural network approach in software reliability modeling. The Journal of
Systems and Software 58 (1), 47-62.
[6] Cai, K.Y., Wen, C.Y., Zhang, M.L., 1991. A critical review on software
reliability modeling. Reliability Engineering and System Safety 32 (3),
357-371.
[7] Chappelier J.C., Grumbach A., «A Kohonen Map for Temporal
Sequences», Proceeding of neural Networks and Their Application,
NEURAP'96, IUSPIM, Marseille, mars 1996, p. 104-110.
[8] Chua, C.G., Goh, A.T.C., 2003. A hybrid Bayesian back-propagation
neural network approach to multivariate modeling. International Journal
for Numerical and Analytical Methods in Geomechanics 27(8),651-667.
[9] Elman J.L., « Finding Structure in Time », Cognitive Science, vol. 14,
juin 1990, p. 179-211.
[10] Fahlman, S.E., Lebiere, C., 1990. The cascade-correlation learning
architecture. Technical Report CMU-CS-90-100, School of Computer
Science, Carnegie Mellon University.
[11] Ho, S.L., Xie, M., Goh, T.N., 2003. A study of the connectionist models
for software reliability prediction. Computers and Mathematics with
Applications 46 (7), 1037-1045.
[12] Hochman, R., Khoshgoftaar, T.M., Allen, E.B., Hudepohl, J.P., 1996.
Using the genetic algorithm to build optimal neural networks for faultprone
module detection. In: Proceedings of the 7th International
Symposium on Software Reliability Engineering. pp. 152-162.
[13] Hochman, R., Khoshgoftaar, T.M., Allen, E.B., Hudepohl, J.P., 1997.
Evolutionary neural networks: a robust approach to software reliability
problems. In: Proceedings of the 8th International Symposium on
Software Reliability Engineering. pp. 13-26.
[14] Karunanithi, N., Whitley, D., Malaiya, Y.K., 1992a. Prediction of
software reliability using connectionist models. IEEE Transactions on
Software Engineering 18 (7), 563-574.
[15] Karunanithi, N., Whitley, D., Malaiya, Y.K., 1992b. Using neural
networks in reliability prediction. IEEE Software 9 (4), 53-59.
[16] Kohonen T., Self-organised formation of topologically correct feature
maps, Biol. Cybern. 43 (1982) 59-69 (reprinted in Anderson and
Rosen.eld, 1988).
[17] Leung, F.H.F., Lam, H.K., Ling, S.H., Tam, P.K.S., 2003. Tuning of the
structure and parameters of a neural network using an improved genetic
algorithm. IEEE Transactions on Neural Networks 14 (1), 79-88.
[18] Park, J.Y., Lee, S.U., Park, J.H., 1999. Neural network modeling for
software reliability prediction from failure time data. Journal of
Electrical Engineering and Information Science 4 (4), 533-538.
[19] Sitte, R., 1999. Comparison of software-reliability-growth predictions:
neural networks vs. parametric-recalibration. IEEE Transactions on
Reliability 48 (3), 285-291.
[20] Tsoi C.T., Back A.D., « Locally Recurrent Globally Feedforward
Networks : A Critical Review of Architectures », IEEE Transaction on
Neural Networks Vol.05, pp. 229-239, 1994.
[21] Tsoukalas, L.H., Uhrig, R.E., 1996. Fuzzy and Neural Approaches in
Engineering. Practical Aspects of Using Neural Networks. John Wiley &
Sons, New York, Chapter 11, pp. 385-405.
[22] Utkin, L.V., Gurov, S.V., Shubinsky, M.I., 2002. A fuzzy software
reliability model with multiple-error introduction and removal.
International Journal of Reliability, Quality and Safety Engineering 9
(3), 215-227.
[23] Zemouri, R., Patic P.C., The effect of different basis functions for
system output prediction, 15th IEEE International Conference on
Emerging Technologies and Factory Automation, ETFA-2010,
September 13-16, 2010, Bilbao Spain (Submitted for publication).
[24] Zemouri, R., Patic P.C., Prediction Error Feedback for Time Series
Prediction: a way to improve the accuracy of predictions, Proceedings of
the 4th EUROPEAN COMPUTING CONFERENCE (ECC '10), April
20-22, 2010, Bucharest, Romania, p. 58-62, ISSN 1790-5117, ISBN
978-960-474-178-6.