DocumentCode :
1976967
Title :
Ship traffic volume forecast in bridge area based on enhanced hybrid radial basis function neural networks
Author :
Liang Yang ; Yong Hao ; Qing Liu ; Xiangyu Zhu
Author_Institution :
Hubei Key Lab. of Inland Shipping Technol., Wuhan Univ. of Technol., Wuhan, China
fYear :
2015
fDate :
25-28 June 2015
Firstpage :
38
Lastpage :
43
Abstract :
Forecasting the vessel traffic flow in the bridge areas is focused on this study. Based on Hybrid Radial Basis Function Neural Network, another novel predictive statistic modeling technique called Enhanced Hybrid Radial Basis Function Neural Network (EHRBF-NN) is proposed in the paper. EHRBF-NN is a flexible forecasting technique that integrates regression trees, particle swarm optimization, with radial basis function neural networks. In this technique, the regression tree is used to determine the centers and radius of the radial basis functions. The Particle Swarm Optimization (PSO) is used to avoid the over fitting and determine the weights of the neural network. Computer simulations have been implemented to validate the EHRBF-NN. Compared forecasting results with actual data, the algorithm of HRBF-NN is more effective than ordinary RBF-NN, RBF-NN with least square method and HRBF-NN, while it uses less computing resources and shorter computing time.
Keywords :
bridges (structures); digital simulation; forecasting theory; particle swarm optimisation; radial basis function networks; regression analysis; ships; traffic; traffic engineering computing; trees (mathematics); EHRBF-NN; PSO; bridge area; computer simulations; enhanced hybrid radial basis function neural network; forecasting technique; particle swarm optimization; predictive statistic modeling technique; radial basis function neural networks; regression trees; ship traffic volume forecasting; vessel traffic flow forecasting; Bridges; Forecasting; Genetic algorithms; Neurons; Radial basis function networks; Regression tree analysis; RBF neural network; forecast; particle swarm optimization(PSO); regression tree; vessel traffic volume; waterway transportation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Transportation Information and Safety (ICTIS), 2015 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4799-8693-4
Type :
conf
DOI :
10.1109/ICTIS.2015.7232077
Filename :
7232077
Link To Document :
بازگشت