Skip to main content

Research Repository

Advanced Search

CityFlow: Supporting Spatial-Temporal Edge Computing for Urban Machine Learning Applications

Kawano, Makoto; Yonezawa, Takuro; Tanimura, Tomoki; Giang, Nam Ky; Broadbent, Matthew; Lea, Rodger; Nakazawa, Jin


Makoto Kawano

Takuro Yonezawa

Tomoki Tanimura

Nam Ky Giang

Matthew Broadbent

Rodger Lea

Jin Nakazawa


A growing trend in smart cities is the use of machine learning techniques to gather city data, formulate learning tasks and models, and use these to develop solutions to city problems. However, although these processes are sufficient for theoretical experiments, they often fail when they meet the reality of city data and processes, which by their very nature are highly distributed, heterogeneous, and exhibit high degrees of spatial and temporal variance. In order to address those problems, we have designed and implemented an integrated development environment called CityFlow that supports developing machine learning applications. With CityFlow, we can develop, deploy, and maintain machine learning applications easily by using an intuitive data flow model. To verify our approach, we conducted two case studies: deploying a road damage detection application to help monitor transport infrastructure and an automatic labeling application in support of a participatory sensing application. These applications show both the generic applicability of our approach, and its ease of use; both critical if we wish to deploy sophisticated ML based applications to smart cities.

Presentation Conference Type Conference Paper (Published)
Conference Name EAI International Conference on IoT in Urban Space
Start Date Nov 21, 2018
End Date Nov 22, 2018
Online Publication Date Nov 14, 2019
Publication Date 2019
Deposit Date Mar 9, 2022
Publisher Springer
Pages 3-15
Series ISSN 2522-8609
Book Title 3rd EAI International Conference on IoT in Urban Space
ISBN 978-3-030-28924-9
Keywords Urban computing, Smart city, Edge processing, Road damage detection, Participatory sensing
Public URL