Travel speed forecasting algorithm based on data fusion - Details

Author：

Zhai, Yaoqiao (Zhai, Yaoqiao.) | Weng, Jiancheng (Weng, Jiancheng.) | Rong, Jian (Rong, Jian.) (Scholars：荣建) | Liu, Xiaoming (Liu, Xiaoming.) (Scholars：刘小明)

Indexed by：

EI Scopus

Abstract：

Due　to　the　variety　of　equipment　and　collection　condition,　different　traffic　data　collection　methods　have　their　own　application　fields　and　different　precision.　Therefore,　in　order　to　acquire　more　reliable　analysis　results,　the　data　from　different　detectors　needs　to　be　fused.　And　then　travel　speed　estimation　should　be　carried　out　based　on　the　data　fusion　results.　The　paper　presents　a　short-term　forecasting　algorithm　for　travel　speed　based　on　Kalman　filter　data　fusion.　After　the　pretreatment　and　traffic　states　division,　the　multi-source　data　including　microwave　detector　data,　loop　detector　data　and　Floating　Car　Data　(FCD)　are　fused　to　estimate　travel　speed　according　to　the　different　traffic　states.　This　research　determines　parameters　for　Kalman　filter,　and　computes　the　states　Transfer　Matrix　by　using　the　artificial　neural　network　(ANN).　The　analysis　result　of　model　validation　shows　that　the　average　accuracy　of　travel　speed　forecasting　algorithm　is　over　90　percents.　Copyright　ASCE　2009.

Keyword：

Traffic control Transfer matrix method Data fusion Forecasting Kalman filters Speed Neural networks Data handling

Author Community：

[ 1 ] [Zhai, Yaoqiao]Beijing Key Laboratory of Transportation Engineering, Beijing University of Technology, Beijing, 100124, China
[ 2 ] [Weng, Jiancheng]Beijing Key Laboratory of Transportation Engineering, Beijing University of Technology, Beijing, 100124, China
[ 3 ] [Rong, Jian]Beijing Key Laboratory of Transportation Engineering, Beijing University of Technology, Beijing, 100124, China
[ 4 ] [Liu, Xiaoming]Beijing Key Laboratory of Transportation Engineering, Beijing University of Technology, Beijing, 100124, China