Using Connected Vehicle Trajectory Data to Evaluate the Effects of Speeding

Abstract

Speeding remains a key factor in traffic fatalities, prompting transportation agencies to propose speed management solutions. While studies have examined speeding percentages above limits, few address its impact on individual journeys. Most studies rely on detector speed data, lacking route insights. This research employs connected vehicle trajectory data to analyze driver paths and variables, predicting speeding levels with various learning models. Extreme Gradient Boosting performed best, achieving 75.6% accuracy. This model elucidates how journey factors influence speeding and forecasts high-speed zones. Results reveal a driver’s total travel time significantly affects speeding, along with environmental features like residential area proportions. These findings aid transportation agencies in understanding trip-specific speeding factors, potentially informing better road safety measures.

Keywords

• Probe vehicle data
• connected vehicle data
• speeding
• machine learning