A wide vehicular network has a huge potential to collect city-data, specially with respect to city mobility, one of the top concerns of the municipalities. In this work, we propose the use of the mobility data generated by the movement of the connected buses to deliver a new set of tools to support both the bus passengers and bus fleet operator use cases. Considering the bus passengers, it is possible to build smart schedules, which deliver an estimated time of arrival based on the city dynamics along time, and that can be accessed directly in the smartphone. Considering the bus fleet operator, it is possible to characterize the behaviour of buses and bus lines. Using the GPS trace of buses and map-matching algorithm, we are able to discover the line each bus is assigned to. Estimated times of arrival and predictions are implemented recurring to time estimations and predictions, using both data mining and machine learning approaches. Proof-of-concept applications were implemented to demonstrate the real-life applicability, including a mobile app for the citizens, and a web dashboard for the fleet operator.
[1]
Alípio Mário Jorge,et al.
Comparing state-of-the-art regression methods for long term travel time prediction
,
2012,
Intell. Data Anal..
[2]
Tsunenori Mine,et al.
Empirical Study of Travel Time Variability Using Bus Probe Data
,
2016,
2016 IEEE International Conference on Agents (ICA).
[3]
T. Vincenty.
DIRECT AND INVERSE SOLUTIONS OF GEODESICS ON THE ELLIPSOID WITH APPLICATION OF NESTED EQUATIONS
,
1975
.
[4]
Alexander Mendiburu,et al.
A Review of Travel Time Estimation and Forecasting for Advanced Traveler Information Systems
,
2012
.
[5]
Fumitaka Kurauchi,et al.
Using Bus Probe Data for Analysis of Travel Time Variability
,
2009,
J. Intell. Transp. Syst..