Scholarlink

<p>The increase in vehicle ownership and urban population puts a strain on roads and increases traffic congestion within developed and developing nations. Congestion affects an individual’s time and increases an individual’s fuel consumption and pollution output, undercutting efforts towards smart/ sustainable cities. Outdated statistical congestion predicting methods do not account for the non-linear, dynamic nature of congestion with regards to external factors such as, weather, road incidents, and infrastructure. The adoption of machine and deep learning develops the framework towards adaptable and data-driven congestion predicting methods. This study develops a framework that combines the fundamentals of machine learning algorithms, Queuing Theory, Decision Trees, Random Forests, and Deep Belief Networks (DBN) for robust and interprefig traffic congestion forecasting. The traffic flow micro-dynamics integration with Queuing Theory and the use of historical/ real-time multimodal data such as sensor feeds, GPS trajectories, and incident reports as a basis for forecasting helps in robust congestion prediction. Polynomials of moving and rest queues with defined traffic characteristics fuel flow mechanisms. The designed framework uses the DBN and Queuing Theory for robust traffic forecasting.</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

Prediction of traffic congestion through Decision Tree, Queuing Theory, Deep Belief Network and Random Forest methods

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月20日

查看全文
  • Aditi Jha,
  • R. S. Pandey,
  • Gyanendra Tiwary,
  • Gaurav Vishnu Londhe

摘要

The increase in vehicle ownership and urban population puts a strain on roads and increases traffic congestion within developed and developing nations. Congestion affects an individual’s time and increases an individual’s fuel consumption and pollution output, undercutting efforts towards smart/ sustainable cities. Outdated statistical congestion predicting methods do not account for the non-linear, dynamic nature of congestion with regards to external factors such as, weather, road incidents, and infrastructure. The adoption of machine and deep learning develops the framework towards adaptable and data-driven congestion predicting methods. This study develops a framework that combines the fundamentals of machine learning algorithms, Queuing Theory, Decision Trees, Random Forests, and Deep Belief Networks (DBN) for robust and interprefig traffic congestion forecasting. The traffic flow micro-dynamics integration with Queuing Theory and the use of historical/ real-time multimodal data such as sensor feeds, GPS trajectories, and incident reports as a basis for forecasting helps in robust congestion prediction. Polynomials of moving and rest queues with defined traffic characteristics fuel flow mechanisms. The designed framework uses the DBN and Queuing Theory for robust traffic forecasting.