Accurate traffic speed estimation supports urban planning and transportation optimization. Existing approaches often fail to account for diverse traffic patterns across different regions and times. This work is innovative because it uses clustering to identify similar traffic conditions and develops separate prediction models for each cluster.
This paper presents SpeedPro, a multi-model approach for urban traffic speed estimation using historical weather data and probe vehicle information. The work develops cluster-based prediction models that improve accuracy by grouping similar traffic conditions. The methodology integrates data from buses and weather sources to estimate real-time traffic speeds.
The paper demonstrates traffic speed prediction with RMSE error in the range of 2.9 to 3.3 miles per hour using cluster-based random forest models. Results show that accounting for weather and historical patterns improves prediction accuracy compared to models using only traffic data.
@inproceedings{Samal2017,
author = {Samal, Chinmaya and Sun, Fangzhou and Dubey, Abhishek},
booktitle = {2017 {IEEE} International Conference on Smart Computing, {SMARTCOMP} 2017, Hong Kong, China, May 29-31, 2017},
title = {SpeedPro: {A} Predictive Multi-Model Approach for Urban Traffic Speed Estimation},
year = {2017},
pages = {1--6},
abstract = {Data generated by GPS-equipped probe vehicles, especially public transit vehicles can be a reliable source for traffic speed estimation. Traditionally, this estimation is done by learning the parameters of a model that describes the relationship between the speed of the probe vehicle and the actual traffic speed. However, such approaches typically suffer from data sparsity issues. Furthermore, most state of the art approaches does not consider the effect of weather and the driver of the probe vehicle on the parameters of the learned model. In this paper, we describe a multivariate predictive multi-model approach called SpeedPro that (a) first identifies similar clusters of operation from the historic data that includes the real-time position of the probe vehicle, the weather data, and anonymized driver identifier, and then (b) uses these different models to estimate the traffic speed in real-time as a function of current weather, driver and probe vehicle speed. When the real-time information is not available our approach uses a different model that uses the historical weather and traffic information for estimation. Our results show that the purely historical data is less accurate than the model that uses the real-time information.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/smartcomp/SamalSD17},
category = {workshop},
acceptance = {37.5},
contribution = {lead},
doi = {10.1109/SMARTCOMP.2017.7947048},
file = {:Samal2017-SpeedPro_A_Predictive_Multi-Model_Approach_for_Urban_Traffic_Speed_Estimation.pdf:PDF},
keywords = {traffic speed estimation, clustering, random forests, weather data, urban transportation},
project = {smart-transit,smart-cities},
tag = {ai4cps,transit},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
url = {https://doi.org/10.1109/SMARTCOMP.2017.7947048}
}