期刊文献+

基于优化RBF网络的港口船舶交通流量预测 被引量:13

Ship Traffic Volume Forecast in Port Based on Optimized RBF Neural Networks
下载PDF
导出
摘要 港口船舶交通流量预测能为港口规划、交通管理提供决策支持。RBF神经网络在交通流预测领域有着广泛的应用,但其在网络权值等参数的选取算法上存在缺陷。遗传算法具有全局搜索速度快的优点,利用该算法对RBF神经网络的权值进行遗传操作,可获得具有一定遍历性的初始权值。文章尝试将基于遗传算法优化的RBF神经网络应用到港口船舶交通流量预测领域并以芜湖港为例进行验证。结果显示,优化后的RBF神经网络的预测误差比普通的RBF神经网络小5%左右,表明优化后的RBF神经网络计算量更小、识别速度更快、预测误差更小,在港口船舶交通流量预测领域具有广阔的应用前景。 Good port planning and traffic management need accurate prediction of ship traffic volume in a port,which is made by means of the ship traffic volume forecasting algorithm.The RBF neural network has a wide range of applications in this regard.The problem with RBF is the difficulties in determining parameters,such as the weights.The genetic algorithm has the advantages of fast global searching,therefore,is good for finding the ergodic initial values of weights for the RBF neural network.The RBF neural network,optimized with the genetic algorithm,is verified through the case of Wuhu port.The results show that the optimized RBF neural network is 5 percent more accurate than ordinary RBF neural network,while it uses less computing resources and shorter computing time.
作者 郝勇 王怡
出处 《中国航海》 CSCD 北大核心 2014年第2期81-84,117,共5页 Navigation of China
关键词 水路运输 船舶交通流量 RBF神经网络 遗传算法 港口 预测 waterway transportation ship traffic volume RBF neural network genetic algorithm port forecast
  • 相关文献

参考文献10

二级参考文献31

  • 1罗松淼.宁波港船舶进出主航道分道通航方案探讨[J].宁波大学学报(理工版),2005,18(1):68-72. 被引量:6
  • 2邢桂华,朱庆保.基于模拟退火遗传算法的RBF网络的优化[J].微电子学与计算机,2005,22(7):174-177. 被引量:3
  • 3李国友,姚磊,李惠光,吴惕华.基于优化的RBF神经网络模式识别新方法[J].系统仿真学报,2006,18(1):181-184. 被引量:22
  • 4赵志刚,单晓虹.一种基于遗传算法的RBF神经网络优化方法[J].计算机工程,2007,33(6):211-212. 被引量:42
  • 5A Jonathan Howell,Hilary Buxton.Learning identity with radial basis function networks [J].Neurocomputing,1998,20:15-34.
  • 6Chen S,Cowan C F N,Grant P N.Orthogonal least squares learning algorithms for radial basis function networks[J].IEEE Trans.Neural Networks.1991,2(2):302-309.
  • 7Orr M J L.Regularization in the selection of radial basis function centers[J].Neural Computation,1995,7:606-623.
  • 8Joannou D,Huda W,Laine A F.Circle Recognition through a 2D Hough transform and radius histogramming[J].Image and vision computing,1999,17:15-26.
  • 9钱华明 马吉臣 施丽娟.基于小波神经网络的导航传感器故障诊断.电子测量与仪器学报,2007,(21):538-541.
  • 10Moshe Leshno. Multilayer Feedback Networks with a Non-polynominal Activation Function Can Approxi- mate Any Function[J]. Neural Networks, 1993, (6): 861-867.

共引文献77

同被引文献82

引证文献13

二级引证文献75

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部