Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 14, 2026Transportmetrica A Transport Science

Behavioural mechanisms of driver compliance under lane-level variable speed limits: field evidence and predictive modeling

View Full Paper
Ask AI
Bookmark
Share

Authors

JWJunhua WangYRYiwei RenHSHao Song

Discussion

Loading...

Member takes

Overview

Observational modeling study uncovers key predictors of driver compliance under lane-level variable speed limits, suggesting traffic controls should account for vehicle heterogeneity.

Key Points

  • To examine behavioural mechanisms governing driver compliance with lane-level variable speed limits and establish an accurate predictive modeling framework using trajectory data.
  • Analyzed real-world vehicle trajectory data across various lane configurations and variable speed limit (VSL) conditions.
  • Implemented a predictive pipeline integrating Recursive Feature Elimination (RFE) and Light Gradient Boosting Machine (LGBM), benchmarked against six alternative algorithms.
  • Lane speed limits and vehicle type are the strongest determinants of compliance; posted lower limits lead to markedly lower compliance, especially in the left lane.
  • Anticipatory deceleration near the first overhead gantry and stable lane allocation are strongly associated with downstream compliance.
  • The LGBM model attained 93.5% predictive accuracy with lower computational cost relative to XGBoost.

Cite This Study

Wang et al. (2026) studied this question.

synapsesocial.com/papers/6a7ec6c6b70b84ec8b912e2dhttps://doi.org/10.1080/23249935.2026.2714899
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Design of a driver reaction-based compliance model for speed limit adherence on motorways2026
  2. 2Multi-Agent Deep Reinforcement Learning for Multi-Lane Freeways Differential Variable Speed Limit Control in Mixed Traffic Environment2024 · 2 citations
  3. 3Modeling Discretionary Lane-Changing Decisions: A Multi-Vehicle Information Enhanced Machine Learning Approach2026
  4. 4Deep Q‐network learning‐based active speed management under autonomous driving environments2024 · 5 citations
  5. 5Reinforcement learning approach to develop variable speed limit strategy using vehicle data and simulations2024 · 15 citations