Title :
Method for defective traffic flow data mending based on SARBF neural networks
Author :
Wu Jian ; Chen Ning
Author_Institution :
Sch. of Mech. & Automotive Eng., Zhejiang Univ. of Sci. & Technol., Hang Zhou, China
Abstract :
Defective data to collect urban traffic flow message are always occurred due to the sensor failure. To mend the defective data, a new approach named SACRBF 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 is shown that the method is practicable.
Keywords :
data handling; radial basis function networks; regression analysis; traffic engineering computing; RBF neural network fitting method; SACRBF neural network fitting; defective traffic flow data; regression analysis; sensor failure; spatial autocorrelation; traffic grid; urban traffic flow message; Artificial neural networks; Correlation; Electronic mail; Fitting; Geographic Information Systems; Indexes; MATLAB; Defective Traffic Flow Data; Mending; SARBF Neural Network Fitting; Spatial Autocorrelation;
Conference_Titel :
Control Conference (CCC), 2010 29th Chinese
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6263-6
