ICNC 2005: Advances in Natural Computation pp 619-629 | Cite as
Recurrent Support Vector Machines in Reliability Prediction
Conference paper
Abstract
Support vector machines (SVMs) have been successfully used in solving nonlinear regression and times series problems. However, the application of SVMs for reliability prediction is not widely explored. Traditionally, the recurrent neural networks are trained by the back-propagation algorithms. In the study, SVM learning algorithms are applied to the recurrent neural networks to predict system reliability. In addition, the parameter selection of SVM model is provided by Genetic Algorithms (GAs). A numerical example in an existing literature is used to compare the prediction performance. Empirical results indicate that the proposed model performs better than the other existing approaches.
Keywords
Recurrent neural networks Support vector machines Genetic algorithms Reliability predictionPreview
Unable to display preview. Download preview PDF.
References
- 1.Liu, M.C., Sastri, T., Kuo, W.: An exploratory study of a neural network approach for reliability data analysis. Quality and Reliability Engineering International 11, 107–112 (1995)CrossRefGoogle Scholar
- 2.Su, C.T., Tong, L.I., Leou, C.M.: Combining time series and neural network approaches. Journal of the Chinese Institute of Industrial Engineers 4, 419–430 (1997)Google Scholar
- 3.Amjady, N., Ehsan, M.: Evaluation of power systems reliability by artificial neural network. IEEE Transactions on Power Systems 14, 287–292 (1999)CrossRefGoogle Scholar
- 4.Ho, S.L., Xie, M., Goh, T.N.: A comparative study of neural network and Box-Jenkins ARIMA modeling in time series prediction. Computers & Industrial Engineering 42, 371–375 (2002)CrossRefGoogle Scholar
- 5.Xu, K., Xie, M., Tang, L.C., Ho, S.L.: Application of neural networks in forecasting engine system reliability. Applied Soft computing 2, 255–268 (2003)CrossRefGoogle Scholar
- 6.Tay, F.E.H., Cao, L.J.: Application of support vector machines in financial time series forecasting. Omega: The International Journal of Management Science 29, 309–317 (2001)CrossRefGoogle Scholar
- 7.Cao, L., Gu, Q.: Dynamic support vector machines for non-stationary time series forecasting. Intelligent Data Analysis 6, 67–83 (2002)MATHGoogle Scholar
- 8.Tay, F.E.H., Cao, L.: Modified support vector machines in financial time series forecasting. Neurocomputing 48, 847–861 (2002)MATHCrossRefGoogle Scholar
- 9.Cao, L.: Support vector machines experts for time series forecasting. Neurocomputting 51, 321–339 (2003)CrossRefGoogle Scholar
- 10.Wang, W., Xu, Z., Lu, J.W.: Three improved neural network models for air quality forecasting. Engineering Computations 20, 192–210 (2003)MATHCrossRefGoogle Scholar
- 11.Mohandes, M.A., Halawani, T.O., Rehman, S., Hussain, A.A.: Support vector machines for wind speed prediction. Renewable Energy 29, 939–947 (2004)CrossRefGoogle Scholar
- 12.Pai, P.F., Lin, C.S.: Using support vector machines in forecasting production values of machinery industry in Taiwan. International Journal of Advanced Manufacturing Technology (2004) DOI: 10.1007/ s00170-004-2139-yGoogle Scholar
- 13.Kechriotis, G., Zervas, E., Manolakos, E.S.: Using recurrent neural networks for adaptive communication channel equalization. IEEE Transaction on Neural Networks 5, 267–278 (1994)CrossRefGoogle Scholar
- 14.Jordan, M.I.: Attractor dynamics and parallelism in a connectionist sequential machine. In: Proceeding of 8th Annual Conference of the Cognitive Science Society, Hillsdale, pp. 531–546 (1987)Google Scholar
- 15.Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
- 16.Williams, R., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Computation 1, 270–280 (1989)CrossRefGoogle Scholar
- 17.Tsoi, A.C., Back, A.D.: Locally recurrent globally feedforward networks: Acritical review of architectures. IEEE Transaction on Neural Networks 5, 229–239 (1994)CrossRefGoogle Scholar
- 18.Jhee, W.C., Lee, J.K.: Performance of Neural Networks in Managerial Forecasting. International Journal of Intelligent Systems in Accounting, Finance, and Management 2, 55–71 (1993)Google Scholar
- 19.Suykens, J.A.K., van Gestel, T., De Brabanter, J., De Moor, B., Vandewalle, J., Leuven, K.U. (eds.): Least Squares Support Vector Machines. World Scientific Publishing Co., Ltd., Belgium (2002)MATHGoogle Scholar
- 20.Kecman, V. (ed.): Learning and Soft Computing, Support Vector machines, Neural Networks and Fuzzy Logic Models. The MIT Press, Cambridge (2001)MATHGoogle Scholar
- 21.Wang, L.P. (ed.): Support Vector Machines: Theory and Application. Springer, Heidelberg (2005)Google Scholar
- 22.Mercer, J.: Function of positive and negative type and their connection with the theory of integral equations. Philosophical Transaction Royal Society London A 209, 415–446 (1909)CrossRefGoogle Scholar
- 23.Holland, J. (ed.): Adaptation in Natural and Artificial System. University of Michigan Press, Ann Arbor (1975)Google Scholar
- 24.Ayaz, E., Seker, S., Barutcu, B., Türkcan, E.: Comparisons between the various types of neural networks with the data of wide range operational conditions of the Borssele NPP. Progress in Nuclear Energy 43, 381–387 (2003)CrossRefGoogle Scholar
- 25.Connor, J.T., Martin, R.D., Atlas, L.E.: Recurrent neural networks and robust time series prediction. IEEE Transactions on Neural Networks 5, 240–254 (1994)CrossRefGoogle Scholar
- 26.Gencay, R., Liu, T.: Nonlinear modeling and prediction with feedforward and recurrent networks. Physica D 108, 119–134 (1997)CrossRefGoogle Scholar
- 27.Kermanshahi, B.: Recurrent neural network for forecasting next 10 years loads of nine Japanese utilities. Neurocomputing 23, 125–133 (1998)CrossRefGoogle Scholar
- 28.Mandic, D.P., Chambers, J.A. (eds.): Recurrent Neural Networks for Prediction. John Wiley and Sons, New York (2001)Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2005