Authors:
Kathrin Rodriguez
1
;
Marco A. Casanova
1
;
Luiz André Paes Leme
2
;
Hélio Lopes
1
;
Rafael Nasser
1
and
Bruno Guberfain do Amaral
1
Affiliations:
1
Pontifical Catholic University of Rio de Janeiro, Brazil
;
2
Fluminense Federal University, Brazil
Keyword(s):
Traffic Modelling, Trajectory Data Mining, Data Stream Processing.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Coupling and Integrating Heterogeneous Data Sources
;
Data Engineering
;
Data Mining
;
Databases and Data Security
;
Databases and Information Systems Integration
;
Enterprise Information Systems
;
Intelligent Transportation System
;
Large Scale Databases
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Strategic Decision Support Systems
Abstract:
Buses, equipped with active GPS devices that continuously transmit their positions, can be understood as mobile traffic sensors. Indeed, bus trajectories provide a useful data source for analyzing traffic, if the city is served by a dense bus network and the city traffic authority makes the bus trajectories available openly, timely and in a continuous way. This paper explores the design of a traffic observatory application based on bus trajectories, defined as an application developed to detect when the traffic patterns of selected streets of a city, observed during certain periods of time, deviate from the typical traffic patterns. The major contributions of the paper are a list of requirements for traffic observatory applications, a detailed discussion of key operations on bus trajectories and a description of experiments with a traffic observatory prototype using bus trajectories made available by the traffic authority of the City of Rio de Janeiro.