Integrating machine learning with ITS for effective traffic management under road development conditions

Intelligent transportation systems (ITS) have paved their way into modern day traffic management scenarios. These scenarios include but are not limited to diverting traffic, identifying routes, identifying accidents and propagating them over the network, etc. Due to a large number of road-based maintenance, repair and new road building works, there is a disruption in traffic flow. Proper maintenance and effective communication among these traffic nodes is of utmost importance for smooth traffic flow. This paper analyses different techniques for ITS communication that assist in maintaining optimum traffic flow under different road construction scenarios. The proposed algorithm devises a novel ITS workflow for organizing traffic under different road development conditions. The machine learning algorithm uses extended drone-based imagery to identify best traffic routes for a given traffic area. The paper also extends the proposed algorithm and adds a machine learning layer to it to further optimize the performance of traffic flow.

• Record URL:
  https://doi.org/10.1504/IJHVS.2023.134705
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/1744232X
• Supplemental Notes:
  • Copyright © 2023 Inderscience Enterprises Ltd.
• Authors:
  • Meshram, Kundan
• Publication Date: 2023

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 718-733
• Serial:
  • International Journal of Heavy Vehicle Systems
  • Volume: 30
  • Issue Number: 6
  • Publisher: Inderscience Enterprises Limited
  • ISSN: 1744-232X
  • EISSN: 1741-5152
  • Serial URL: http://www.inderscience.com/jhome.php?jcode=IJHVS

Subject/Index Terms

• TRT Terms: Advanced traffic management systems; Image analysis; Intelligent transportation systems; Machine learning; Road construction; Traffic flow
• Subject Areas: Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 01904652
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 16 2024 9:03AM