BriefGPT.xyz
Nov, 2024
SPTTE:一种时空概率框架用于旅行时间估计
SPTTE: A Spatiotemporal Probabilistic Framework for Travel Time Estimation
HTML
PDF
Chen Xu, Qiang Wang, Lijun Sun
TL;DR
本研究解决了多次旅行时间分布的时变建模难题,提出了SPTTE框架,将估计任务公式化为时空随机过程回归,以应对稀疏观察带来的挑战。SPTTE利用RNN基础的时间高斯过程参数化,显著提升了在稀疏和不均匀数据分布下的旅行时间估计准确性,超过现有方法10.13%。
Abstract
Accurate
Travel Time Estimation
is essential for navigation and itinerary planning. While existing research employs
Probabilistic Modeling
to assess travel time uncertainty and account for correlations between mu
→