Congestion Detection and Propagation in Urban Areas Using Histogram Models

Hesham El-Sayed, Gokulnath Thandavarayan

    Research output: Contribution to journalArticlepeer-review

    8 Citations (Scopus)

    Abstract

    Rapid growth of urbanization makes the roadways exacerbate many problems like traffic congestion, road accidents, and passenger discomfort. Many actions have been taken globally to solve or reduce this impact but still the congestion problem seems to be persistent globally. In this paper, we propose a new histogram-based model for congestion detection. We subsequently extended our model with the base platform concept and use Intelligent Transportation System (ITS) technologies to provide a novel rerouting strategy. The proposed model enables the microscopic visualization of the traffic patterns for every individual lane and predicts the congestion in priori and takes actions proactively. The rerouting strategy used in our approach provides a novel solution to the congestion problem by taking precaution measures prior to the critical point of congestion occurrence. The proposed algorithm is compared with various existing algorithms and the simulation results show that the proposed model addresses the congestion problem effectively and provides better solution compared to existing algorithms.

    Original languageEnglish
    Article number7847390
    Pages (from-to)3672-3682
    Number of pages11
    JournalIEEE Internet of Things Journal
    Volume5
    Issue number5
    DOIs
    Publication statusPublished - Oct 2018

    Keywords

    • Congestion estimation
    • congestion propagation
    • histograms
    • intelligent transportation system (ITS)
    • route guidance

    ASJC Scopus subject areas

    • Signal Processing
    • Information Systems
    • Hardware and Architecture
    • Computer Science Applications
    • Computer Networks and Communications

    Fingerprint

    Dive into the research topics of 'Congestion Detection and Propagation in Urban Areas Using Histogram Models'. Together they form a unique fingerprint.

    Cite this