Title
Online Support Vector Regression Model for Short-term Traffic Forecasting
Abstract
In this paper, a new short-term traffic flow prediction model and method based on online support vector regression (OSVR) is proposed, according to the data collected sequentially by the probe vehicle or the loop detectors, which can update the forecasting function in real time via online learning way. As a result, it is fitter for a real engineering application. The OSVR model was tested by using I-880 database, the result shows that this model is superior to the back-propagation neural network (BPNN) model.
Year
DOI
Venue
2007
10.1109/IMSCCS.2007.66
IMSCCS
Keywords
Field
DocType
support vector regression,prediction model,regression analysis,support vector machines,data collection,real time,traffic flow
Online learning,Data mining,Traffic flow,Regression analysis,Computer science,Support vector machine,Artificial intelligence,Artificial neural network,Detector,Machine learning
Conference
Volume
Issue
ISBN
null
null
0-7695-3039-7
Citations 
PageRank 
References 
2
0.38
3
Authors
3
Name
Order
Citations
PageRank
Haowei Su1151.73
Ling Zhang214314.77
Shu Yu320.38