SPTTE models time-varying travel time distributions with a GRU-based Gaussian parameterization and prior-based graph smoothing, reporting modest gains over ProbETA.
Efficiency of eta prediction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SPTTE: A Spatiotemporal Probabilistic Framework for Travel Time Estimation
SPTTE models time-varying travel time distributions with a GRU-based Gaussian parameterization and prior-based graph smoothing, reporting modest gains over ProbETA.