Crowdsourcing for Smart Transportation Systems
Primary Faculty Mentor’s Name
Dr. Danda Rawat
Proposal Track
Student
Session Format
Poster
Abstract
Vehicle transportation is essential for the majority of the population. Efficient transportation systems are positively correlated to a stronger economy. There are added social benefits that include more employment and investment opportunities. Traffic systems that are inefficient and unreliable attribute to lower qualities of life and hamper socioeconomic development in first and third world countries alike. Altering the current infrastructure is a costly endeavor. However, by supplying the players in the traffic system smart traffic data, the overall network will experience less delay and more cohesion. Our main focus is applying a few intelligent communication techniques to optimize traffic flow and to alert drivers or autonomous vehicles of anomalies or accidents in the system. By using the power of crowdsourcing, we can create a database of logistical data that can be utilized in novel ways to alleviate congestion. From the point of view of the user, they would connect to a secure database via a smartphone application and submit data relating to their positioning. This system is intended to be convenient and secure to every user. The real-time data will be put through a number of algorithms to direct the driver to the most efficient route possible. An extension of this application is to have the data clustered to create localized heat maps of drivers and hazardous areas. Through algorithms and observational data, we can forecast future conditions on both the macro and micro level. As data is being inputted, users can be updated in real time of the most optimal route for the traffic system. As the number of users grows, we can supply more accurate status updates to everyone that is a part of the network. In this work, we show the configuration of our proposed application and some experimental data resulting from crowd-sourced location information.
Location
Concourse and Atrium
Presentation Year
2015
Start Date
11-7-2015 2:10 PM
End Date
11-7-2015 3:20 PM
Publication Type and Release Option
Presentation (Open Access)
Recommended Citation
source:http://digitalcommons.georgiasouthern.edu/gurc/2015/2015/5/
Crowdsourcing for Smart Transportation Systems
Concourse and Atrium
Vehicle transportation is essential for the majority of the population. Efficient transportation systems are positively correlated to a stronger economy. There are added social benefits that include more employment and investment opportunities. Traffic systems that are inefficient and unreliable attribute to lower qualities of life and hamper socioeconomic development in first and third world countries alike. Altering the current infrastructure is a costly endeavor. However, by supplying the players in the traffic system smart traffic data, the overall network will experience less delay and more cohesion. Our main focus is applying a few intelligent communication techniques to optimize traffic flow and to alert drivers or autonomous vehicles of anomalies or accidents in the system. By using the power of crowdsourcing, we can create a database of logistical data that can be utilized in novel ways to alleviate congestion. From the point of view of the user, they would connect to a secure database via a smartphone application and submit data relating to their positioning. This system is intended to be convenient and secure to every user. The real-time data will be put through a number of algorithms to direct the driver to the most efficient route possible. An extension of this application is to have the data clustered to create localized heat maps of drivers and hazardous areas. Through algorithms and observational data, we can forecast future conditions on both the macro and micro level. As data is being inputted, users can be updated in real time of the most optimal route for the traffic system. As the number of users grows, we can supply more accurate status updates to everyone that is a part of the network. In this work, we show the configuration of our proposed application and some experimental data resulting from crowd-sourced location information.
