Feature Mapping the Seoul Metro Station Areas Based on a Self-Organizing Map
Bibliographic Data
| ID | 15318614 |
|---|---|
| Authors | Keemin Sohn (0000-0002-7270-7094, Russian State Agrarian Correspondence University, corresponding author) |
| Year | 2013 |
| Volume | 20 |
| Issue | 4 |
| Pages | 23-42 |
| Publication date | 2013-10-01 |
| Open Access | No |
| Type | ARTICLE |
| Venue | Journal of Urban Technology (JOURNAL) |
| Journal identifiers | ISSN: 1063-0732 • E-ISSN: 1466-1853 |
| Publisher | Taylor & Francis (PUBLISHER • GB) |
| DOI | 10.1080/10630732.2013.855514 |
| OpenAlex | W2021733411 |
| Language | EN |
| Citations received | 4 |
| References cited | 27 |
Land in the vicinity of railway stations in the Seoul metropolitan area has been spotlighted as a target for redevelopment in accordance with the principles of transit-oriented development (TOD). In order to understand the nature of station areas as a whole, it is required to identify their current status with respect to their built environments, demographic characteristics, socioeconomic status, and transport aspects. Most of the previous studies that have focused on characterizing urban areas assumed that clearly separable clustering is possible and tried to find a robust methodology for that. Many researchers have used either supervised classifiers requiring a pre-classified dataset for training, or K-means-like unsupervised classifiers demanding a predetermined number of clusters. The present study focused on the fact that it was hard to find such a clear separation in station areas in Seoul. A more abstract technology was necessary to position the current status of each station area and to find how different station areas are from one another. A robust unsupervised classifier, called the self-organizing map (SOM), was employed to investigate the similarities and differences among station areas in Seoul. The SOM results revealed many informative findings for policy development without any classification
Cartography · Civil engineering · Classifier (UML · Cluster analysis · Data mining · Geography · Machine learning · Metropolitan area · Redevelopment · Self-organizing map · Transit-oriented development · Urban planning · Computer Science · Engineering · Human Mobility and Location-Based Analysis · Urban Design and Spatial Analysis · Urban Transport and Accessibility · Artificial Intelligence
Housing market segmentation and hedonic prediction accuracy
The perceptron
Public Transportation Access
Do housing submarkets really matter?
Self-organized formation of topologically correct feature maps
Defining Housing Submarkets
The self-organizing map
Travel demand and the 3Ds
An analysis of Metro ridership at the station-to-station level in Seoul
House building and product differentiation
Factors generating boardings at Metro stations in the Seoul metropolitan area
Forecasting Housing Prices under Different Market Segmentation Assumptions
A Multiple-perspectives Construct of the American Global City
Identifying the Impact on Land Prices of Replacing At-grade or Elevated Railways with Underground Subways in the Seoul Metropolitan Area
Classification of Residential Areas in the Three Largest Dutch Cities Using Multidimensional Data
| Citations per year | 0.57 |
|---|---|
| Citation span | 2019 - 2026 (8) |
| Highly cited | No |