Recurrent Radial Basis Function Network for Failure Time Series Prediction

Autor: Zemouri, Ryad, Patic, Paul Ciprian
Jazyk: angličtina
Rok vydání: 2010
Předmět:
DOI: 10.5281/zenodo.1072369
Popis: 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.
{"references":["Adnan, W.A., Yaacob, M.H., 1994. An integrated neural-fuzzy system\nof software reliability prediction. In: Proceedings of the 1st International\nConference on Software Testing, Reliability and Quality Assurance. pp.\n154-158.","Adnan, W.A., Yaacob, M.H., Anas, R., Tamjis, M.R., 2000. Artificial\nneural network for software reliability assessment. In: 2000 TENCON\nProceedings of Intelligent Systems and Technologies for the New\nMillennium. pp. 446-451.","Aljahdali, S.H., Sheta, A., Rine, D., 2001. Prediction of software\nreliability: a comparison between regression and neural network nonparametric\nmodels. In: Proceedings of ACS/IEEE International\nConference on Computer Systems and Applications. pp. 470-473.","Aljahdali, S.H., Sheta, A., Rine, D., 2002. Predicting accumulated faults\nin software testing process using radial basis function network models.\nIn: Proceedings of the 17th International Conference on Computers and\ntheir Applications. pp. 26-29.","Cai, K.Y., Cai, L., Wang, W.D., Yu, Z.Y., Zhang, D., 2001. On the\nneural network approach in software reliability modeling. The Journal of\nSystems and Software 58 (1), 47-62.","Cai, K.Y., Wen, C.Y., Zhang, M.L., 1991. A critical review on software\nreliability modeling. Reliability Engineering and System Safety 32 (3),\n357-371.","Chappelier J.C., Grumbach A., «A Kohonen Map for Temporal\nSequences», Proceeding of neural Networks and Their Application,\nNEURAP'96, IUSPIM, Marseille, mars 1996, p. 104-110.","Chua, C.G., Goh, A.T.C., 2003. A hybrid Bayesian back-propagation\nneural network approach to multivariate modeling. International Journal\nfor Numerical and Analytical Methods in Geomechanics 27(8),651-667.","Elman J.L., « Finding Structure in Time », Cognitive Science, vol. 14,\njuin 1990, p. 179-211.\n[10] Fahlman, S.E., Lebiere, C., 1990. The cascade-correlation learning\narchitecture. Technical Report CMU-CS-90-100, School of Computer\nScience, Carnegie Mellon University.\n[11] Ho, S.L., Xie, M., Goh, T.N., 2003. A study of the connectionist models\nfor software reliability prediction. Computers and Mathematics with\nApplications 46 (7), 1037-1045.\n[12] Hochman, R., Khoshgoftaar, T.M., Allen, E.B., Hudepohl, J.P., 1996.\nUsing the genetic algorithm to build optimal neural networks for faultprone\nmodule detection. In: Proceedings of the 7th International\nSymposium on Software Reliability Engineering. pp. 152-162.\n[13] Hochman, R., Khoshgoftaar, T.M., Allen, E.B., Hudepohl, J.P., 1997.\nEvolutionary neural networks: a robust approach to software reliability\nproblems. In: Proceedings of the 8th International Symposium on\nSoftware Reliability Engineering. pp. 13-26.\n[14] Karunanithi, N., Whitley, D., Malaiya, Y.K., 1992a. Prediction of\nsoftware reliability using connectionist models. IEEE Transactions on\nSoftware Engineering 18 (7), 563-574.\n[15] Karunanithi, N., Whitley, D., Malaiya, Y.K., 1992b. Using neural\nnetworks in reliability prediction. IEEE Software 9 (4), 53-59.\n[16] Kohonen T., Self-organised formation of topologically correct feature\nmaps, Biol. Cybern. 43 (1982) 59-69 (reprinted in Anderson and\nRosen.eld, 1988).\n[17] Leung, F.H.F., Lam, H.K., Ling, S.H., Tam, P.K.S., 2003. Tuning of the\nstructure and parameters of a neural network using an improved genetic\nalgorithm. IEEE Transactions on Neural Networks 14 (1), 79-88.\n[18] Park, J.Y., Lee, S.U., Park, J.H., 1999. Neural network modeling for\nsoftware reliability prediction from failure time data. Journal of\nElectrical Engineering and Information Science 4 (4), 533-538.\n[19] Sitte, R., 1999. Comparison of software-reliability-growth predictions:\nneural networks vs. parametric-recalibration. IEEE Transactions on\nReliability 48 (3), 285-291.\n[20] Tsoi C.T., Back A.D., « Locally Recurrent Globally Feedforward\nNetworks : A Critical Review of Architectures », IEEE Transaction on\nNeural Networks Vol.05, pp. 229-239, 1994.\n[21] Tsoukalas, L.H., Uhrig, R.E., 1996. Fuzzy and Neural Approaches in\nEngineering. Practical Aspects of Using Neural Networks. John Wiley &\nSons, New York, Chapter 11, pp. 385-405.\n[22] Utkin, L.V., Gurov, S.V., Shubinsky, M.I., 2002. A fuzzy software\nreliability model with multiple-error introduction and removal.\nInternational Journal of Reliability, Quality and Safety Engineering 9\n(3), 215-227.\n[23] Zemouri, R., Patic P.C., The effect of different basis functions for\nsystem output prediction, 15th IEEE International Conference on\nEmerging Technologies and Factory Automation, ETFA-2010,\nSeptember 13-16, 2010, Bilbao Spain (Submitted for publication).\n[24] Zemouri, R., Patic P.C., Prediction Error Feedback for Time Series\nPrediction: a way to improve the accuracy of predictions, Proceedings of\nthe 4th EUROPEAN COMPUTING CONFERENCE (ECC '10), April\n20-22, 2010, Bucharest, Romania, p. 58-62, ISSN 1790-5117, ISBN\n978-960-474-178-6."]}
Databáze: OpenAIRE
Externí odkaz: