Skip to main navigation Skip to search Skip to main content

Sensors and Data Driven Approaches in Transport

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

Abstract

Sensors play an important role in collecting real-time information for transportation systems. Nowadays, several different sensor technologies, ranging from traditional ones to mobile sensors in smartphones, are being used to collect a massive data volume on the real-time location and dynamics of users. For example, most of the modern smartphones are equipped with multiple motion sensors, such as accelerometer and magnetometer sensors, which can provide an unprecedented opportunity for the monitoring of the motion status of mobile phone users. On the other hand, there are a wide variety of data mining and prediction techniques, which can support transportation researchers in analyzing raw travel data collected from sensor technologies. This article provides a review of various applications of sensor technologies in transport networks, including travel time estimation, origin–destination matrices estimation, safety analysis, driver behavior monitoring, and transportation mode inference.
Original languageEnglish
Title of host publicationTransport Policy and Planning
EditorsRoger Vickerman
PublisherElsevier
Chapter66
Pages426-431
ISBN (Electronic)978-008102671-7
ISBN (Print)978-008102672-4
DOIs
Publication statusE-pub ahead of print/First online - 17 May 2021
Externally publishedYes

Publication series

NameInternational Encyclopedia of Transportation
PublisherElsevier
Volume6

Keywords

  • NLA
  • Driver behavior monitoring
  • Machine learning methods
  • Origin–destination matrices estimation
  • Safety analysis
  • Sensors
  • Sensor fusion approaches
  • Smartphone-based sensors
  • Traffic data
  • Traffic network surveillance
  • Transportation mode inference
  • Travel time estimation

Fingerprint

Dive into the research topics of 'Sensors and Data Driven Approaches in Transport'. Together they form a unique fingerprint.

Cite this