Compared to the expensive and inaccurate human surveys, the rich information in taxi GPS traces provides a new means of understanding the human mobility patterns in cities. In this chapter, we intend to employ taxi GPS traces to explore the issue of night bus route planning. Specifically, a two-phase approach is proposed for bi-directional night-bus route planning. In the first phase, we start by clustering “hot” areas with dense passenger pick-up/drop-off and then introduce effective methods to divide big “hot” areas into clusters and identify a location in each cluster as a candidate bus stop. In the second phase, considering the bus route origin, destination, candidate bus stops as well as bus operation time constraints, we derive several effective rules to build the bus route graph, and iteratively prune invalid stops and edges. Based on this graph, we further develop a Bi-directional Probability based Spreading (BPS) algorithm to generate candidate bus routes automatically. Finally, we select the best bi-directional bus route, which expects the maximum number of passengers under the given conditions and constraints. We conduct extensive empirical studies on real-world taxi GPS data and verify the effectiveness of the proposed method.
B-Planner: Planning Night Bus Routes Using Taxi Trajectory Data
Enabling Smart Urban Services with GPS Trajectory Data ; Chapter : 9 ; 193-222
2021-04-02
30 pages
Article/Chapter (Book)
Electronic Resource
English
B-Planner: Planning Bidirectional Night Bus Routes Using Large-Scale Taxi GPS Traces
Online Contents | 2014
|Taxi planner optimization: A management tool
SAGE Publications | 2008
|Taxi planner optimization: a management tool
Online Contents | 2008
|