Real-time Bus Routing and Traffic Prediction Via Machine Learning-based Methods

With the development of advance telecommunication systems, new opportunities for real-time public transport monitoring has been created. Traffic congestion in the vehicular ad-hoc network can be typically caused by an accident, construction zones, special events, and adverse weather. This research presents a cognitive framework to address real-time routing problem and and arrival time prediction for bus system using a machine learning method. First we build and analysis a dataset comprises several individual bus trips that contains the arrival time, the bus identifier, bus direction and speed. In order to collect data on the state of traffic, we employ the information of deployed sensors, including metering stations, on certain strategic road segments allowing to distinguish cars from buses and to quantify the traffic. This set provides a real-time data flow of the sensors deployed on the network. Secondly, we extract most important features using Linear Discriminant Analysis to reduce the number of features in our data set. Finally, we propose a solution and compare with baseline machine learning algorithms to find the best routs for buses system with the objective of minimizing the passengers waiting time, the operating expense and capital costs, and carbon footprint cause by traffic jam.

Faculty Supervisor:

Gabriela Nicolescu

Student:

Partner:

BusPas Inc.

Discipline:

Computer science

Sector:

Transportation (excluding aerospace); Information and Communications Technology

University:

Polytechnique Montréal

Program: