Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 4.74 MB
Add to list
  1. Search results
  2. The best place in Tokyo for anything ...

The best place in Tokyo for anything : classifying stations by walkability to specific amenities

Aaron Bramson (UGent) and Megumi Hori
(2022) ADVANCES IN ARTIFICIAL INTELLIGENCE. In Advances in Intelligent Systems and Computing 1423. p.106-117
Author
Organization
Abstract
Walkability analyses have recently gained attention for economic, health, and environmental reasons [5,8, 13] . We examine the walkable store profiles for train stations of central Tokyo and use machine learning to find clusters of similarly walkable areas. First, we use a breadth-first search algorithm on the road network to determine the walkable areas within 5, 10, and 15 min of each station. We then collect the establishments within 50 m of any traversed edge. We perform three analyses: (1) classifying regions by the numbers of stores of each type, (2) recursive feature selection and reclassification, and (3) scoring areas by their specialization in one of the store categories. We find that classification without feature selection produces more useful results, and that the <15 min isochrones yield the best results. These methods can be broadened to identify regions that are over- and under-serviced by amenities with impacts for both policy and business planning.
Keywords
Walkability, Geospatial analysis, Machine learning, Network analysis, Transportation networks

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 4.74 MB

Citation

Please use this url to cite or link to this publication:

MLA
Bramson, Aaron, and Megumi Hori. “The Best Place in Tokyo for Anything : Classifying Stations by Walkability to Specific Amenities.” ADVANCES IN ARTIFICIAL INTELLIGENCE, vol. 1423, Springer International Publishing Ag, 2022, pp. 106–17, doi:10.1007/978-3-030-96451-1_10.
APA
Bramson, A., & Hori, M. (2022). The best place in Tokyo for anything : classifying stations by walkability to specific amenities. ADVANCES IN ARTIFICIAL INTELLIGENCE, 1423, 106–117. https://doi.org/10.1007/978-3-030-96451-1_10
Chicago author-date
Bramson, Aaron, and Megumi Hori. 2022. “The Best Place in Tokyo for Anything : Classifying Stations by Walkability to Specific Amenities.” In ADVANCES IN ARTIFICIAL INTELLIGENCE, 1423:106–17. Cham: Springer International Publishing Ag. https://doi.org/10.1007/978-3-030-96451-1_10.
Chicago author-date (all authors)
Bramson, Aaron, and Megumi Hori. 2022. “The Best Place in Tokyo for Anything : Classifying Stations by Walkability to Specific Amenities.” In ADVANCES IN ARTIFICIAL INTELLIGENCE, 1423:106–117. Cham: Springer International Publishing Ag. doi:10.1007/978-3-030-96451-1_10.
Vancouver
1.
Bramson A, Hori M. The best place in Tokyo for anything : classifying stations by walkability to specific amenities. In: ADVANCES IN ARTIFICIAL INTELLIGENCE. Cham: Springer International Publishing Ag; 2022. p. 106–17.
IEEE
[1]
A. Bramson and M. Hori, “The best place in Tokyo for anything : classifying stations by walkability to specific amenities,” in ADVANCES IN ARTIFICIAL INTELLIGENCE, ELECTR NETWORK, 2022, vol. 1423, pp. 106–117.
@inproceedings{8763132,
  abstract     = {{Walkability analyses have recently gained attention for economic, health, and environmental reasons [5,8, 13] . We examine the walkable store profiles for train stations of central Tokyo and use machine learning to find clusters of similarly walkable areas. First, we use a breadth-first search algorithm on the road network to determine the walkable areas within 5, 10, and 15 min of each station. We then collect the establishments within 50 m of any traversed edge. We perform three analyses: (1) classifying regions by the numbers of stores of each type, (2) recursive feature selection and reclassification, and (3) scoring areas by their specialization in one of the store categories. We find that classification without feature selection produces more useful results, and that the <15 min isochrones yield the best results. These methods can be broadened to identify regions that are over- and under-serviced by amenities with impacts for both policy and business planning.}},
  author       = {{Bramson, Aaron and Hori, Megumi}},
  booktitle    = {{ADVANCES IN ARTIFICIAL INTELLIGENCE}},
  isbn         = {{9783030964511}},
  issn         = {{2194-5357}},
  keywords     = {{Walkability,Geospatial analysis,Machine learning,Network analysis,Transportation networks}},
  language     = {{eng}},
  location     = {{ELECTR NETWORK}},
  pages        = {{106--117}},
  publisher    = {{Springer International Publishing Ag}},
  title        = {{The best place in Tokyo for anything : classifying stations by walkability to specific amenities}},
  url          = {{http://doi.org/10.1007/978-3-030-96451-1_10}},
  volume       = {{1423}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: