Forecasting short-term traffic speed based on multiple attributes of adjacent roads
作者：
Highlights：
• We consider only traffic attributes most relevant to speed and also their weights.
• We consider the differences of impacts on speed among adjacent roads.
• We employ piecewise correlation function between traffic speed and attributes.
• We adopt Jenks clustering with dynamic programming to determine segment intervals.
• We validate our approach based on the real data collected from two large cities.
摘要
•We consider only traffic attributes most relevant to speed and also their weights.•We consider the differences of impacts on speed among adjacent roads.•We employ piecewise correlation function between traffic speed and attributes.•We adopt Jenks clustering with dynamic programming to determine segment intervals.•We validate our approach based on the real data collected from two large cities.
论文关键词：Traffic speeds,Short-term,Speed prediction,Adjacent roads,Traffic attributes
论文评审过程：Received 9 May 2018, Revised 28 August 2018, Accepted 5 September 2018, Available online 15 September 2018, Version of Record 21 November 2018.
论文官网地址：https://doi.org/10.1016/j.knosys.2018.09.003
