Citywide Estimation of Travel Time Distributions with Bayesian Deep Graph Learning

Yu，James J.Q.

2021

10.1109/TKDE.2021.3117986

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING   影响因子和分区

1041-4347

1558-2191

Estimation of road link travel time serves a critical role in intelligent transportation operation and management. Due to the uncertainty nature contributed by the volatile traffic, travel time estimates are better described by probability distributions than deterministic models. Existing travel time distribution estimation approaches are mostly based on predefined probability distributions. Other approaches, while relaxing the constraint, fail to utilize the topological information and are data-inefficient. In this paper, we propose a novel Bayesian and geometric deep learning-based approach to estimate the travel time distributions of road links within citywide transportation networks based on vehicular GPS trajectories. Particularly, historical or real-time trajectories are first pre-processed to construct partial travel time maps, which are input into a tailor-made Bayesian graph autoencoder to reconstruct multiple complete travel time maps. We further adopt an auxiliary neural network to facilitate the parameter training of the proposed approach following adversarial training principles. To evaluate the proposed approach, we employ a real-world vehicular trajectory dataset in a series of comprehensive case studies. The empirical results indicate that the proposed approach outperforms the best-performing state-of-the-art baseline with an approximately 10% Kullback-Leibler divergence reduction.

adversarial training Bayes methods Bayesian inference deep learning Deep learning Estimation graph convolution Roads Training Trajectory Transportation Travel time distribution estimation

EI ; SCI

英语

第一

20214811225578

Bayesian networks ; Deep learning ; Inference engines ; Probability distributions ; Roads and streets ; Traffic control ; Travel time ; Uncertainty analysis

Roads and Streets:406.2 ; Air Transportation:431 ; Highway Transportation:432 ; Railroad Transportation:433 ; Waterway Transportation:434 ; Ergonomics and Human Factors Engineering:461.4 ; Expert Systems:723.4.1 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4 ; Probability Theory:922.1

ENGINEERING

2-s2.0-85119617630

Scopus

Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, Guangdong, China, 518055 (e-mail: yujq3@sustech.edu.cn)

Yu，James J.Q.. Citywide Estimation of Travel Time Distributions with Bayesian Deep Graph Learning[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2021,PP(99):1-1.

Yu，James J.Q..(2021).Citywide Estimation of Travel Time Distributions with Bayesian Deep Graph Learning.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,PP(99),1-1.

Yu，James J.Q.."Citywide Estimation of Travel Time Distributions with Bayesian Deep Graph Learning".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING PP.99(2021):1-1.