Traffic and transportation forecasting is a key issue in urban planning aimed to provide a greener and more sustainable environment to residents. Their privacy is a second key issue that requires synthetic travel data. A possible solution is offered by generative models. Here, a variational autoencoder architecture has been trained on a floating car dataset in order to grasp the statistical features of the traffic demand in the city of Rome. The architecture is based on multilayer dense neural networks for encoding and decoding parts. A brief analysis of parameter influence is conducted. The generated trajectories are compared with those in the dataset. The resulting reconstructed synthetic data are employed to compute the traffic fluxes and geographic distribution of parked cars. Further work directions are provided.

Traffic Request Generation through a Variational Auto Encoder Approach

Chiesa S.;Taraglio S.
2022-01-01

Abstract

Traffic and transportation forecasting is a key issue in urban planning aimed to provide a greener and more sustainable environment to residents. Their privacy is a second key issue that requires synthetic travel data. A possible solution is offered by generative models. Here, a variational autoencoder architecture has been trained on a floating car dataset in order to grasp the statistical features of the traffic demand in the city of Rome. The architecture is based on multilayer dense neural networks for encoding and decoding parts. A brief analysis of parameter influence is conducted. The generated trajectories are compared with those in the dataset. The resulting reconstructed synthetic data are employed to compute the traffic fluxes and geographic distribution of parked cars. Further work directions are provided.
2022
Generative models
Traffic model
Urban mobility
Variational autoencoder
File in questo prodotto:
File Dimensione Formato  
Traffic Request Generation through a Variational Auto Encoder Approach.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 4.21 MB
Formato Adobe PDF
4.21 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12079/71490
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
social impact