Scholarlink

<p>Urban areas encounter a substantial issue of traffic congestion, particularly in smart cities where traffic control techniques must adapt to fluctuating circumstances. The efficacy of the approach can be impacted by variables such as the grade and accessibility of up-to-the-minute traffic data, computer resources and the intricacy of metropolitan road networks. This paper introduces a new method called Dynamic Tabu Search-based Gated Recurrent Units (DTS-GRU) for managing traffic congestion in smart cities. The dataset contains real-time comprising of collected traffic video from Pune city, India, as well as captured footage from highway closed-circuit television (CCTV) cameras which are used to train and assess the DTS-GRU model. The experimental findings validate the efficacy of the DTS-GRU strategy in enhancing traffic flow and mitigating congestion. The simulation was performed using Python software. Our experimental findings show that the suggested strategy is effective in terms of accuracy (93.10%), precision (94.05%), recall (94.60%) and F1-score (92.90%). The findings indicate that the suggested method has the potential to make a substantial impact on alleviating congestion, optimizing traffic movement and promoting urban mobility as a group.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing urban mobility: machine learning-powered fusion approach for intelligent traffic congestion control in smart cities

  • 期刊论文

  • 发表日期：

    2025年1月20日

查看全文
  • Ankur Chaudhary,
  • M. Meenakshi,
  • Soma Sharma,
  • Mahbubur Rahman,
  • S. Srinivasan

摘要

Urban areas encounter a substantial issue of traffic congestion, particularly in smart cities where traffic control techniques must adapt to fluctuating circumstances. The efficacy of the approach can be impacted by variables such as the grade and accessibility of up-to-the-minute traffic data, computer resources and the intricacy of metropolitan road networks. This paper introduces a new method called Dynamic Tabu Search-based Gated Recurrent Units (DTS-GRU) for managing traffic congestion in smart cities. The dataset contains real-time comprising of collected traffic video from Pune city, India, as well as captured footage from highway closed-circuit television (CCTV) cameras which are used to train and assess the DTS-GRU model. The experimental findings validate the efficacy of the DTS-GRU strategy in enhancing traffic flow and mitigating congestion. The simulation was performed using Python software. Our experimental findings show that the suggested strategy is effective in terms of accuracy (93.10%), precision (94.05%), recall (94.60%) and F1-score (92.90%). The findings indicate that the suggested method has the potential to make a substantial impact on alleviating congestion, optimizing traffic movement and promoting urban mobility as a group.