A deep learning model called MotoTimePressure predicts time pressure levels in powered two-wheeler riders at 91.53% accuracy using 63 kinematic and behavioral features, and its predictions improve downstream collision risk models.
Capacity estimation of unsignalized intersections under heterogeneous traffic conditions.Canadian Journal of Civil Engineering, 47(6):651–662
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions
A deep learning model called MotoTimePressure predicts time pressure levels in powered two-wheeler riders at 91.53% accuracy using 63 kinematic and behavioral features, and its predictions improve downstream collision risk models.