OD-HyperNet: A Data-Driven Hyper-Network Model for Origin-Destination Matrices Completion Using Partially Observed Data

Yuxuan Xiu (), Wanda Li (), Jing Yang (Sunny) Xi and Wai Kin (Victor) Chan ()
Additional contact information
Yuxuan Xiu: Tsinghua University Shenzhen
Wanda Li: Tsinghua University Shenzhen
Jing Yang (Sunny) Xi: Tsinghua University Shenzhen
Wai Kin (Victor) Chan: Tsinghua University Shenzhen

A chapter in LISS 2020, 2021, pp 335-350 from Springer

Abstract: Abstract Estimating the inter-city population flow is critical for modeling the spread of COVID-19. However, for most cities, it is difficult to extract accurate population numbers for inflow and outflow. On the other hand, mobile carriers and Internet companies can estimate the distribution of population flow by tracking their users; but their data only cover part of the travelers. In this paper, we present a data-driven hyper-network model to aggregate these two types of data and complete the inter-city OD matrix. We first propose a cross-layer breadth-first traversal algorithm to estimate the inflow and outflow population of each city, then complete the OD matrix with an optimization model. Our experiments on a real-world dataset prove the accuracy and efficiency of our model.

Keywords: Hyper-network; Data-driven modeling; Origin-destination matrix (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-33-4359-7_24

Ordering information: This item can be ordered from
http://www.springer.com/9789813343597

DOI: 10.1007/978-981-33-4359-7_24

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().