Scholarlink

<p>Road traffic accidents remain a major cause of fatalities worldwide, accompanied by considerable economic and societal costs. This study aims to find the relationship between key contributing factors to accidents and road traffic violations in rural and urban areas separately, an aspect overlooked in the previous research. More specifically, the study examined the impact of traffic violations across the eight urban and rural states in the United States, analyzing variables such as driver fault, vehicle ownership, license type, function type, and speed. Frequent violations, including negligent driving, manslaughter, vehicle registration infractions, hit-and-run incidents, and reckless driving, were assessed using the Random Forest machine learning model. Performance metrics, including accuracy, F1-measure, precision, and Kappa statistics, validated the model’s effectiveness. Partial dependence plots explored the relationships between violations and contributing factors. The results revealed distinct patterns between urban and rural areas. In rural settings, violations were driven mainly by speeding, negligent driving, overcorrecting, and non-owner drivers. In urban areas, reckless driving, drug use, improper lane usage, tailgating, and failure to yield were the predominant factors. These findings underscore the need for tailored interventions to address area-specific violations, helping policymakers implement strategies to reduce violations and improve road safety.</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

Random Forest and Partial Dependence Plots Methods to understand Patterns of Road Traffic Violations in Urban and Rural Areas

  • 期刊论文

  • 发表日期：

    2026年2月26日

查看全文
  • Shumaila Feroz,
  • Sameer Ud-Din,
  • Muhammad Asif Khan,
  • Shahbaz Altaf,
  • Fazle Subhan

摘要

Road traffic accidents remain a major cause of fatalities worldwide, accompanied by considerable economic and societal costs. This study aims to find the relationship between key contributing factors to accidents and road traffic violations in rural and urban areas separately, an aspect overlooked in the previous research. More specifically, the study examined the impact of traffic violations across the eight urban and rural states in the United States, analyzing variables such as driver fault, vehicle ownership, license type, function type, and speed. Frequent violations, including negligent driving, manslaughter, vehicle registration infractions, hit-and-run incidents, and reckless driving, were assessed using the Random Forest machine learning model. Performance metrics, including accuracy, F1-measure, precision, and Kappa statistics, validated the model’s effectiveness. Partial dependence plots explored the relationships between violations and contributing factors. The results revealed distinct patterns between urban and rural areas. In rural settings, violations were driven mainly by speeding, negligent driving, overcorrecting, and non-owner drivers. In urban areas, reckless driving, drug use, improper lane usage, tailgating, and failure to yield were the predominant factors. These findings underscore the need for tailored interventions to address area-specific violations, helping policymakers implement strategies to reduce violations and improve road safety.