Research Article
A Generic Predictive Model for On-Street Parking Availability
@INPROCEEDINGS{10.1007/978-3-030-38822-5_4, author={Eren Unlu and Jean-Baptiste Delfau and Bich Nguyen and Eric Chau and Mehdi Chouiten}, title={A Generic Predictive Model for On-Street Parking Availability}, proceedings={Intelligent Transport Systems. From Research and Development to the Market Uptake. Third EAI International Conference, INTSYS 2019, Braga, Portugal, December 4--6, 2019}, proceedings_a={INTSYS}, year={2020}, month={1}, keywords={On-street parking Machine learning Smart city}, doi={10.1007/978-3-030-38822-5_4} }- Eren Unlu
Jean-Baptiste Delfau
Bich Nguyen
Eric Chau
Mehdi Chouiten
Year: 2020
A Generic Predictive Model for On-Street Parking Availability
INTSYS
Springer
DOI: 10.1007/978-3-030-38822-5_4
Abstract
Despite the previously demonstrated considerable negative effects of on-street parking availability on a city’s traffic flux, the developed literature on this issue is far from being voluminous. It is shown that, the duration for finding a vacant parking space consume a sizeable portion of a driver’s time. Especially, for huge megacities, even small, local traffic disturbances can generate chaotic results due to their complex, inter-connected nature. Hence, being able to predict the probability of finding a vacant on-street parking place on a spot at a given time up to a reasonable degree shall be at paramount of interest for future smart-city oriented conurbations. In this paperwork, we present a generic framework supported by a machine learning model, which predicts the spatio-temporal on-street parking availability, where spots are characterized according to amenities in their vicinity.