文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > IT/计算机 > The Applications of Data Mining Method in Urban Traffic Flow
侵权投诉

The Applications of Data Mining Method in Urban Traffic Flow

数据挖掘 英文

Journal of Computational Information Systems3:5(2007) 1957-1962

Available at doc.guandang.net

The Applications of Data Mining Method in Urban Traffic Flow

Prediction

Zhenghong PENG 1 , Bin SONG 2

1

2 School of Urban Studies, Wuhan University, Wuhan 430072, China School of Electrical Engineering, Wuhan University, Wuhan 430072, China

Abstract

Data mining, which is also referred to as knowledge discovery in databases, is the process of extracting valid previously unknown, comprehensible and actionable information from large databases and using it to make crucial decisions. In this paper, to effectively guide the traffic flow, its status must be analyzed and predicted in real-time, we present the data mining process from traffic flow data extraction to characteristic vectors by grey relational analysis, and corresponding algorithms. We then use practical data to evaluate these feature selection methods. Results from this study show that the method is a great improvement in prediction accuracy.

Keywords: Data Mining; Traffic Flow; GRA

1. Introduction

Now, automobiles play an important role in our daily life. With the rapid expansion of urban regions, however, urban traffic gives rise to many problems. Urban traffic congestion is a problem that adversely and significantly affects all aspects of the quality of life in, particularly larger, cities. As such, it comes as little surprise that intelligent transportation systems technologies make a conscious effort toward dealing with congestion in urban areas. Advanced traffic control technologies may lead to more efficient use of existing street near the center of Wuhan. One of the major elements in these systems is a flow prediction model, which forecasts the future traffic flows based on the times series traffic data measured from the network. This paper proposes a model for predicting urban region traffic flow using data mining techniques that have found many applications in disparate fields.

Recently, some researchers partly used methods related to data mining to predict real-time traffic status to improve current prediction ways. Some prediction models have also been developed. But most of the models have weakness in combination, evaluation and selection optimization of prediction methods, which lead the low accuracy, scalability and adaptability [1-3]. In this paper, a novel grey relational analysis method is presented for the prediction of the urban traffic flow. Corresponding author.

Email addresses: (Zhenghong PENG)

1553-9105/ Copyright © 2007 Binary Information Press

September, 2007

第1页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email