Bus signal priority is a key component for achieving bus priority, and it has provided the basis for predicting bus travel time. Firstly, the GPS data from nine bus vehicles of Route 7 with road right priority are selected. Then, the preprocessing methods which follow the order of segmenting the studied road section in terms of signalized intersection location, removing useless and failure data, matching bus GPS data with segmented road section based on minimum enclosing rectangle method, and correcting the matched data based on point projection method are applied for improving data quality. Furthermore, a calibrated bus travel time prediction model is established based on the autoregressive integrated moving average (ARIMA) model. Finally, prediction practice for Route 7 is conducted; verifying the validation of the calibrated model, i.e., the maximum relative error and the mean absolute percentage error between predicted data and measured data are 17.39% and 12.61%, respectively.
Bus Travel Time Prediction Based on GPS Data: A Case Study of Nanjing City
18th COTA International Conference of Transportation Professionals ; 2018 ; Beijing, China
CICTP 2018 ; 587-595
2018-07-02
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
How do passengers use travel time? A case study of Shanghai–Nanjing high speed rail
Online Contents | 2017
|How do passengers use travel time? A case study of Shanghai–Nanjing high speed rail
Online Contents | 2017
|Application of Google-based Data for Travel Time Analysis: Kaunas City Case Study
DOAJ | 2017
|City Reports - Nanjing - Metro supports urban development
Online Contents | 2003