Scholarlink

<p>Timely navigation of emergency vehicles in smart traffic squares is essential to ensure the safety and wellbeing of both the population and the very cities in which they reside. The current traffic systems have the limitation in that they are not dynamic, which delays the emergency vehicles traveling to their specific destinations. The purpose of the paper was to enhance the navigation of emergency vehicles using a combination of reinforcement learning along with accurate traffic sense recommendation. A Proposed Deep Q-Learning Algorithm was developed and tested against AlexNet, VGG16, VGG19, ResNet 50, ResNet 101 and ResNet152. Results from the study showed that the Proposed Deep Q-Learning Algorithm had a higher accuracy of 0.98 and precision of 0.98, recall of 0.98, and F1-score of 0.97 than all the other methods. The method has been shown to have reduced travel time, which improves the traffic flow method. The improved method of traffic sense recommendation and integration are paramount in the improvement of smart traffic squares.</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 Emergency Vehicle Navigation in Smart Traffic Squares with Reinforcement Learning and Accurate Traffic Sense Recommendations

  • 期刊论文

  • 发表日期：

    2025年7月24日

查看全文
  • Bharat Pahadiya,
  • Rekha Ranawat

摘要

Timely navigation of emergency vehicles in smart traffic squares is essential to ensure the safety and wellbeing of both the population and the very cities in which they reside. The current traffic systems have the limitation in that they are not dynamic, which delays the emergency vehicles traveling to their specific destinations. The purpose of the paper was to enhance the navigation of emergency vehicles using a combination of reinforcement learning along with accurate traffic sense recommendation. A Proposed Deep Q-Learning Algorithm was developed and tested against AlexNet, VGG16, VGG19, ResNet 50, ResNet 101 and ResNet152. Results from the study showed that the Proposed Deep Q-Learning Algorithm had a higher accuracy of 0.98 and precision of 0.98, recall of 0.98, and F1-score of 0.97 than all the other methods. The method has been shown to have reduced travel time, which improves the traffic flow method. The improved method of traffic sense recommendation and integration are paramount in the improvement of smart traffic squares.