|
Abstract
|
Article Information:
A New Method for Traffic Forecasting Based on the Data Mining Technology with Artificial Intelligent Algorithms
Wei He, Tao Lu and Enjun Wang
Corresponding Author: Wei He
Submitted: October 17, 2012
Accepted: November 23, 2012
Published: April 10, 2013 |
Abstract:
|
This study aims to investigate the traffic information forecasting based on the data mining technology. As well known, useful knowledge in traffic management system often hides in a large amount of traffic data. Generally, prior data pattern labels have been used to train the Artificial Neural Network (ANN) to identify the traffic conditions in the traffic information forecasting. The performance of the ANN models suffers from the prior information of the experts. To relieve this impact in the traffic information forecasting, a new ANN model is proposed based on the data mining technology in this study. The Self-Organized Feature Map (SOFM) is firstly employed to cluster the traffic data through an unsupervised learning and provide the labels for these data. Then the labeled data were used to train the GA-Chaos optimized RBF neural network. Herein, the GA-Chaos algorithm is used to train the RBF parameters. Experimental tests use practical data sets from the Intelligent Transportation Systems (ITS) were implemented to validate the performance of the proposed ANN model. The analyses results demonstrate that the proposed method can extract the potential patterns hidden in the traffic data and can accurately predict the future traffic state. The prediction accuracy is beyond 95%. Hence, the new data mining model can provide practical application for traffic information forecasting in the ITS system.
Key words: Artificial neural network, data mining, optimization, traffic forecasting, , ,
|
|
Abstract
|
PDF
|
HTML |
|
Cite this Reference:
Wei He, Tao Lu and Enjun Wang , . A New Method for Traffic Forecasting Based on the Data Mining Technology with Artificial Intelligent Algorithms. Research Journal of Applied Sciences, Engineering and Technology, (12): 3417-3422.
|
|
|
|
 |
ISSN (Online): 2040-7467
ISSN (Print): 2040-7459 |
 |
| Information |
|
|
|
|
| Sales & Services |
|
|
|
|
