论文信息 - Prediction of Scour Depth in Downstream of Ski-Jump Spillways Using Soft Computing Techniques

Prediction of Scour Depth in Downstream of Ski-Jump Spillways Using Soft Computing Techniques

Abstract Scour of bed in downstream of a ski-jump spillway is a critical phenomenon that can endanger the spillway stability. The present paper deals with application of soft computing techniques like classification and regression tree (CART), support vector machine (SVM) and M5 for the prediction of downstream scour of the spillways. The results of testing data set present CART model as the best among the other computing methods. The results of models showed that CART produces better prediction of the scour in the downstream of the spillway compared to other techniques. However, the other techniques are better than the available empirical relationships for the prediction of scour.

[1] P. B. Deolalikar,et al. Neural Networks for Estimation of Scour Downstream of a Ski-Jump Bucket , 2005 .

[2] J. Mahjoobi,et al. Prediction of significant wave height using regressive support vector machines , 2009 .

[3] S. Sathiya Keerthi,et al. Improvements to the SMO algorithm for SVM regression , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4] H. Md. Azamathulla,et al. Alternative neural networks to estimate the scour below spillways , 2008, Adv. Eng. Softw..

[5] John C. Platt,et al. Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[6] J. R. Quinlan. Learning With Continuous Classes , 1992 .

[7] Bernhard Schölkopf,et al. A tutorial on support vector regression , 2004, Stat. Comput..

[8] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[9] D. Solomatine,et al. Model trees as an alternative to neural networks in rainfall—runoff modelling , 2003 .

[10] A. Etemad-Shahidi,et al. COMPARISON BETWEEN M5 MODEL TREE AND NEURAL NETWORKS FOR PREDICTION OF SIGNIFICANT WAVE HEIGHT IN LAKE SUPERIOR , 2009 .

[11] Wei-Yin Loh,et al. Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..