The travel time between bus stops has obvious characteristics of time interval distribution, and the bus is a typical space-time process object, and its operation has a state transition. In order to predict the travel time between bus stations accurately, a support vector machine (SVM) algorithm is proposed based on the measured travel time between bus stations. Through a large number of GPS data in different periods of time for a reasonable classification summary bin selected the appropriate kernel function to verify. The algorithm is verified by the actual operation data of No. 6 bus in Qingdao Economic and technological Development Zone. The results show that the results of support vector machine model operation are basically in agreement with the actual measured data, and the accuracy is relatively high, and it can even be used to predict bus travel time.
[1]
Liping Fu,et al.
Optimization of headways with stop‐skipping control: a case study of bus rapid transit system
,
2015
.
[2]
Lelitha Vanajakshi,et al.
Analytical Approach to Identify the Optimum Inputs for a Bus Travel Time Prediction Method
,
2015
.
[3]
Deron Liang,et al.
Software Development of Automatic Data Collector for Bus Route Planning System
,
2014
.
[4]
Zhenliang Ma,et al.
Modeling Bus Travel Time Reliability with Supply and Demand Data from Automatic Vehicle Location and Smart Card Systems
,
2015
.
[5]
Omar J. Ibarra-Rojas,et al.
Planning, operation, and control of bus transport systems: A literature review
,
2015
.