Predicting pedestrian-vehicle interaction severity at unsignalized intersections.

Journal: Traffic injury prevention
PMID:

Abstract

OBJECTIVES: This study aims to develop and validate a novel deep-learning model that predicts the severity of pedestrian-vehicle interactions at unsignalized intersections, distinctively integrating Transformer-based models with Multilayer Perceptrons (MLP). This approach leverages advanced feature analysis capabilities, offering a more direct and interpretable method than traditional models.

Authors

  • Kaliprasana Muduli
    Department of Civil Engineering, Indian Institute of Technology (IIT) Roorkee, Roorkee, India.
  • Indrajit Ghosh
    Department of Computer Science, Ananda Chandra College, Jalpaiguri, West Bengal, India.