Defective data to collect urban traffic flow message is always occurred due to the sensor failure. To mend the defective data, a new approach named SARBF neural network fitting is presented. It combines analysis based on spatial autocorrelation and RBF neural network fitting method. The complete data is determined to mend the defective data according to the spatial autocorrelation of traffic grid. Not only the mending precision is improved and also the limitation of regression analysis is avoided by using RBF neural network. Finally, the experiment to mend the defective traffic flow data in Hangzhou City is shown that the method is practicable.
A New Fitting Method for Mending Defective Urban Traffic Flow Data
Second International Conference on Transportation Engineering ; 2009 ; Southwest Jiaotong University, Chengdu, China
2009-07-29
Conference paper
Electronic Resource
English
Highways and roads , Information technology (IT) , Transportation management , Construction , Data analysis , Freight transportation , Traffic flow , Neural networks , Water transportation , Air transportation , Rail transportation , Urban areas , Optimization , Public transportation , Traffic management
A New Fitting Method for Mending Defective Urban Traffic Flow Data
British Library Conference Proceedings | 2009
|Online Contents | 1997
SAE Technical Papers | 1998
TIBKAT | 1973
|Emerald Group Publishing | 1985