An algorithmic framework employing tensor decomposition and Bayesian inference for data reconstruction in intelligent transportation systems

Hadi Salehi

doi:10.1117/12.2591181

22 March 2021 An algorithmic framework employing tensor decomposition and Bayesian inference for data reconstruction in intelligent transportation systems

Hadi Salehi

Author Affiliations +

Proceedings Volume 11592, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XV; 115920W (2021) https://doi.org/10.1117/12.2591181
Event: SPIE Smart Structures + Nondestructive Evaluation, 2021, Online Only

Abstract

Intelligent transportation systems (ITS) collect traffic data from various sensors deployed in smart cities. Yet, such information that are ubiquitous in real-world transportation systems mainly suffer from irregular spatial and temporal resolution. Consequently, missing and incomplete traffic data are inevitable as a result of detector and communication malfunctions when collecting information from ITS. Reconstructing missing values is then of great importance yet challenging due to difficulties in capturing spatiotemporal traffic patterns. This paper presents a transportation data reconstruction/imputation model that leverages Bayesian inference and tensor decomposition/completion to effectively address the missing data problem. On this basis, Bayesian tensor train (TT) decomposition is incorporated with Markov chain Monte Carlo Gibbs sampler to learn parameters of the model. Results of the experiments indicate that the proposed Bayesian TT model can effectively impute missing traffic data with acceptable accuracy.

Citation Download Citation

Hadi Salehi "An algorithmic framework employing tensor decomposition and Bayesian inference for data reconstruction in intelligent transportation systems", Proc. SPIE 11592, Nondestructive Characterization and Monitoring of Advanced Materials, Aerospace, Civil Infrastructure, and Transportation XV, 115920W (22 March 2021); https://doi.org/10.1117/12.2591181

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available