Paper Title:
Application of Intelligent Data Mining Method for Traffic Forecasting
  Abstract

Potential knowledge useful for traffic management optimization is hidden in a huge amount of data. Previous works use the prior data pattern labels to train the artificial neural network to attain the intelligent data mining models. The performance of the models suffers from the experts’ experience. To relieve the impact of the human factor, a new hybrid intelligent data mining model is proposed in this work based on self-organizing map (SOM) and support vector machine (SVM). The SOM was firstly used to capture the clustering information of the database through an unsupervised manner. Then the identified samples were treated as input to train the SVM. To optimize the SVM model, the particle swarm optimization (PSO) algorithm was employed to tune the SVM parameters and hence the satisfactory SVM data mining model was obtained. 2000 practical data sets from the Intelligent Transportation Systems (ITS) were applied to the validation of the proposed mining model. The analysis results show that the proposed method can extract the underlying rules of the testing data and can predict the future traffic state with the accuracy beyond 97%. Hence, the new SOM-PSO-SVM data mining model can provide practical application for the ITS.

  Info
Periodical
Chapter
Green Power Systems and Power Electronic Circuits
Edited by
Aimin Yang, Jingguo Qu and Xilong Qu
Pages
405-409
DOI
10.4028/www.scientific.net/AMM.84-85.405
Citation
W. He, J. Xiong, "Application of Intelligent Data Mining Method for Traffic Forecasting", Applied Mechanics and Materials, Vols. 84-85, pp. 405-409, 2011
Online since
August 2011
Authors
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Wang Lan Tian
Abstract:Fuzzy neural network, which can deal with complex data and prediction process that other algorithms can not accomplish, has become a focus in...
930
Authors: Shan Chen
Abstract:In this paper, data mining algorithms have been refined and optimized to achieve the intelligent detection of network data. Winsock2 SPI used...
2248
Authors: Bing Chen, Xue Qin Hu, Bei Zhan Wang, Yin Huan Zheng
Chapter 5: Biotechnology, Chemical and Materials Engineering
Abstract:This paper proposed a new hybrid spectral clustering algorithm in which Mean Impact Value (MIV) was used in the cost dimension reduction. The...
695
Authors: Cui Fang Zheng, Long Jiang, Li Qing Jiang, Zhi Jie Wu
Chapter 5: Information Processing and Computational Science
Abstract:Data mining techniques give us a feasible method to deal with great amount of data, which is generated during the software developing. Many...
738
Authors: Tatiana Simankina, Olga Popova
Chapter 7: Architecture and Urban Planning
Abstract:The algorithm for clustering based on neural network modeling using T. Kohonen's self-organizing maps for the analysis of the housing stock...
1057