Scholarlink

<p>This study examines how professional and general drivers adapt their behavior when receiving smartphone-based traffic information under real congestion. A randomized field experiment involving 300 drivers was conducted in Bengaluru, India, where four types of information content were delivered via a mobile application. Behavioral responses were analyzed using a Cluster-and-Synthesize (C&amp;S) framework that integrates k-means clustering and principal component analysis (PCA). The C&amp;S analysis identified distinct adaptation patterns: professional drivers showed stable and proactive reactions, while general drivers displayed delayed or reactive responses to informational cues. These differences were reflected in acceleration and steering stability indicators. The findings demonstrate that tailored information content can effectively influence driver behavior and improve traffic flow in urban networks. This data-driven framework contributes to the development of Intelligent Mobility Systems. And this data-driven framework contributes to the development of Intelligent Mobility Systems and provides practical insight for smart infrastructure design and adaptive mobility management toward safer and more sustainable transport systems.</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

Traffic Congestion and Drivers Behavior Analysis in India

  • 期刊论文

  • 发表日期：

    2026年1月13日

查看全文
  • Tsutomu Tsuboi,
  • Hajime Oshima,
  • Mika Mizukami

摘要

This study examines how professional and general drivers adapt their behavior when receiving smartphone-based traffic information under real congestion. A randomized field experiment involving 300 drivers was conducted in Bengaluru, India, where four types of information content were delivered via a mobile application. Behavioral responses were analyzed using a Cluster-and-Synthesize (C&S) framework that integrates k-means clustering and principal component analysis (PCA). The C&S analysis identified distinct adaptation patterns: professional drivers showed stable and proactive reactions, while general drivers displayed delayed or reactive responses to informational cues. These differences were reflected in acceleration and steering stability indicators. The findings demonstrate that tailored information content can effectively influence driver behavior and improve traffic flow in urban networks. This data-driven framework contributes to the development of Intelligent Mobility Systems. And this data-driven framework contributes to the development of Intelligent Mobility Systems and provides practical insight for smart infrastructure design and adaptive mobility management toward safer and more sustainable transport systems.