全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于GGA的RBF神经网络及其在交通信息预测中的应用

, PP. 831-835

Keywords: 遗传梯度算法(GGA),RBF神经网络,遗传算法(GA),梯度下降算法,交通信息预测

Full-Text   Cite this paper   Add to My Lib

Abstract:

准确可靠的交通信息预测是实现智能交通诱导和交通管理的关键.本文提出一种两步学习算法:遗传梯度算法,用于RBF神经网络的学习,并应用到交通信息预测中.算法充分利用遗传算法的全局优化能力和梯度下降算法的局部搜索能力,一方面加快网络收敛速度,另一方面优化网络结构,并在一定程度上提高网络的推广能力.宁波市实时交通速度信息预测的实验结果论证该算法的有效性.

References

[1]  Yang Zhaosheng. The Inducing System of Urban Traffic Flow. Beijing, China: Chinese Railway Publishing House, 2004 (in Chinese) (杨兆升.城市交通流诱导系统.北京:中国铁道出版社, 2004)
[2]  Smith B L, Demetsky M J. Traffic Flow Forecasting: Comparison of Modelling Approaches. Journal of Transportaion Engineering, 1997, 123(4): 261-266
[3]  Okotani I, Stephanedes Y J. Dynamic Prediction of Traffic Volumn through Kalman Filtering Theory. Transportation Reasearch: Part B, 1984, 18(1): 1-11
[4]  Hobeika A G, Chang K K. Traffic-Flow-Prediction Systems Based on Upstream Traffic // Proc of the Vehicle Navigation and Information System Conference. Berlin, Germany, 1994: 456-462
[5]  Hussein D. An Object-Oriented Neural Network Approach to Short-Term Traffic Forecasting. European Journal of Operations Research, 2001,131(2): 253-261
[6]  Wu C H, Ho J M, Lee D T. Travel-Time Prediction with Support Vector Regression. IEEE Trans on Intelligent Transportation Systems, 2004, 5(4): 276-281
[7]  Zhao W B, Huang D S. The Structure Optimization of Radial Basis Probabilistic Neural Networks Based on Genetic Algorithms // Proc of the International Joint Conference on Neural Networks. Honolulu, USA, 2002: 1086-1091
[8]  Gomm J B, Yu D L. Selecting Radial Basis Function Network Centers with Recursive Orthogonal Least Squares Training. IEEE Trans on Neural Networks, 2000, 11(2): 306-314
[9]  Fastentrath D U. Floating Car Data on a Larger Scale [EB/OL]. [1997-05-01]. http://www.ddg.de/pdf_dat/ddgfcd.pdf
[10]  Wang Jiajie, Fang Tingjian, Jchfer R P. China First FCD Application at NingBo City // Proc of 12th World Congress on Intelligent Transport Systems and Services. San Francisco, USA, 2005: 1250-1256

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133