TY - JOUR
T1 - Hierarchical travel demand estimation using multiple data sources
T2 - A forward and backward propagation algorithmic framework on a layered computational graph
AU - Wu, Xin
AU - Guo, Jifu
AU - Xian, Kai
AU - Zhou, Xuesong
N1 - Funding Information:
This research project, especially the large-scale Beijing test network and various traffic data set, has been supported through Beijing Key Laboratory of Urban Traffic Operation Simulation and Decision Support and Beijing International Science and Technology Cooperation Base of Urban Transport. This research project is also supported by National Natural Science Foundation of China project no. 71734004 , tilted “Research on advanced theories for urban transportation governance”. The last author is partially funded by National Science Foundation–United States under NSF Grant No. CMMI 1538105 “Collaborative Research: Improving Spatial Observability of Dynamic Traffic Systems through Active Mobile Sensor Networks and Crowdsourced Data” and NSF Grant No. CMMI 1663657. “Real-time Management of Large Fleets of Self-Driving Vehicles Using Virtual Cyber Tracks”. The last author thanks Mr. Brian Gardner from Federal Highway Administration (FHWA) for his constructive comments. We also thank some kind comments from the collaborating team from Beihang University (China). The work presented in this paper remains the sole responsibility of the authors.
Funding Information:
This research project, especially the large-scale Beijing test network and various traffic data set, has been supported through Beijing Key Laboratory of Urban Traffic Operation Simulation and Decision Support and Beijing International Science and Technology Cooperation Base of Urban Transport. This research project is also supported by National Natural Science Foundation of China project no.71734004, tilted “Research on advanced theories for urban transportation governance”. The last author is partially funded by National Science Foundation–United States under NSF Grant No. CMMI 1538105 “Collaborative Research: Improving Spatial Observability of Dynamic Traffic Systems through Active Mobile Sensor Networks and Crowdsourced Data” and NSF Grant No. CMMI 1663657. “Real-time Management of Large Fleets of Self-Driving Vehicles Using Virtual Cyber Tracks”. The last author thanks Mr. Brian Gardner from Federal Highway Administration (FHWA) for his constructive comments. We also thank some kind comments from the collaborating team from Beihang University (China). The work presented in this paper remains the sole responsibility of the authors.
Publisher Copyright:
© 2018 Elsevier Ltd
PY - 2018/11
Y1 - 2018/11
N2 - Aiming to develop a theoretically consistent framework to estimate travel demand using multiple data sources, this paper first proposes a multi-layered Hierarchical Flow Network (HFN) representation to structurally model different levels of travel demand variables including trip generation, origin/destination matrices, path/link flows, and individual behavior parameters. Different data channels from household travel surveys, smartphone type devices, global position systems, and sensors can be mapped to different layers of the proposed network structure. We introduce Big data-driven Transportation Computational Graph (BTCG), alternatively Beijing Transportation Computational Graph, as the underlying mathematical modeling tool to perform automatic differentiation on layers of composition functions. A feedforward passing on the HFN sequentially implements 3 steps of the traditional 4-step process: trip generation, spatial distribution estimation, and path flow-based traffic assignment, respectively. BTCG can aggregate different layers of partial first-order gradients and use the back-propagation of “loss errors” to update estimated demand variables. A comparative analysis indicates that the proposed methods can effectively integrate different data sources and offer a consistent representation of demand. The proposed methodology is also evaluated under a demonstration network in a Beijing subnetwork.
AB - Aiming to develop a theoretically consistent framework to estimate travel demand using multiple data sources, this paper first proposes a multi-layered Hierarchical Flow Network (HFN) representation to structurally model different levels of travel demand variables including trip generation, origin/destination matrices, path/link flows, and individual behavior parameters. Different data channels from household travel surveys, smartphone type devices, global position systems, and sensors can be mapped to different layers of the proposed network structure. We introduce Big data-driven Transportation Computational Graph (BTCG), alternatively Beijing Transportation Computational Graph, as the underlying mathematical modeling tool to perform automatic differentiation on layers of composition functions. A feedforward passing on the HFN sequentially implements 3 steps of the traditional 4-step process: trip generation, spatial distribution estimation, and path flow-based traffic assignment, respectively. BTCG can aggregate different layers of partial first-order gradients and use the back-propagation of “loss errors” to update estimated demand variables. A comparative analysis indicates that the proposed methods can effectively integrate different data sources and offer a consistent representation of demand. The proposed methodology is also evaluated under a demonstration network in a Beijing subnetwork.
KW - Back propagation
KW - Computational graph
KW - Multi-source data
KW - Travel demand estimation
UR - http://www.scopus.com/inward/record.url?scp=85054456619&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85054456619&partnerID=8YFLogxK
U2 - 10.1016/j.trc.2018.09.021
DO - 10.1016/j.trc.2018.09.021
M3 - Article
AN - SCOPUS:85054456619
SN - 0968-090X
VL - 96
SP - 321
EP - 346
JO - Transportation Research Part C: Emerging Technologies
JF - Transportation Research Part C: Emerging Technologies
ER -