Dealing with Error Recovery in Traffic Flow Prediction Using Bayesian Networks Based on License Plate Scanning Data
by S. Sánchez-Cambronero, Ph.D., (corresponding author), (Assistant Professor, Dept. of Civil Engineering, Univ. of Castilla La Mancha, 13071 Ciudad Real, Spain E-mail: santos.sanchez@uclm.es), E. Castillo, Ph.D., (Professor, Dept. of Applied Mathematics and Computational Sciences, Univ. of Cantabria, 39005 Santander, Spain. E-mail: castie@unican.es), J. M. Menéndez, Ph.D., (Professor, Dept. of Civil Engineering, Univ. of Castilla La Mancha, 13071 Ciudad Real, Spain. E-mail: josemaria.menendez@uclm.es), and P. Jiménez, Ph.D., (Dept. of Civil Engineering, Univ. of Castilla La Mancha, 13071 Ciudad Real, Spain. E-mail: mariapilar.jimenez@uclm.es)
Journal of Transportation Engineering, Vol. 137, No. 9, September 2011, pp. 615-629, (doi: http://dx.doi.org/10.1061/(ASCE)TE.1943-5436.0000249)
Access full text
Purchase Subscription
Permissions for Reuse 
| Document type: |
Journal Paper |
|
Section Heading: Transportation Systems |
| Abstract: |
This paper deals with the error recovery problem when scanned license plate data are used to predict traffic flows. The aim is to reduce the effects of errors owing to lost plates or mistaken transcription, to improve estimation results. To this end, a method is given and discussed for traffic flow prediction using plate scanning data and taking into account possible errors in plate number recognition. The proposed method uses Bayesian networks because this is an efficient tool for introducing the plate scan error flow as a variable in the model and mending the mistakes in the scan pattern. Several examples are used to illustrate the proposed model. Finally, some conclusions are included. |
| Author Keywords: | 
| Traffic data updating |
| Gaussian Bayesian networks |
| Probability intervals |
| Plate scanning |
| Root-mean-square relative error |
| Error recovery |
|
