All Issue

2026 Vol.44, Issue 4 Preview Page

Article

Cluster Analysis of Bus Stops Based on Point of Interest and Travel Characteristics by Transportation Vulnerable Groups

POI 데이터 기반 버스 정류장 유형화 및 교통약자 유형별 통행 특성 분석

Minkyung SONG1
,
Minhye CHOI2
,
Jiho YEO3*
송 민경1
,
최 민혜2
,
여 지호3*
1Master’s Degree, Department of Smart City, Gachon University, Seongnam 13120, Korea
2Senior Researcher, Mobility Research Department, Korea Transportation Safety Authority, Gimcheon 39660, Korea
3Associate Professor, Department of Smart City, Gachon University, Seongnam 13120, Korea
1가천대학교 스마트시티융합학과 석사과정
2한국교통안전공단 모빌리티연구처 선임연구원
3가천대학교 스마트시티학과 부교수
*Corresponding Author
31 August 2026. pp. 641-665
PDF XML Citation
Abstract

This study analyzes the travel purposes and mobility patterns of transportation- disadvantaged groups—children, older adults, and people with disabilities—by integrating smart card transaction data with point of interest (POI) data in the Seoul metropolitan area. While smart card data provide detailed spatio-temporal information on boarding and alighting events, they offer limited insight into passengers’ underlying travel purposes. To address this limitation, this study incorporates spatial contextual information surrounding bus stops. POI data within a defined buffer distance around each bus stop were collected, and a TF-IDF (Term Frequency–Inverse Document Frequency) algorithm was applied to correct for imbalances in facility distributions and to derive feature vectors representing bus stop environments. Based on these vectors, K-means clustering was performed to classify bus stops into 13 functional types. The resulting bus stop typology was combined with origin–destination (OD) data from smart card records to examine visit patterns across transportation-disadvantaged groups, and a chi-square test was conducted to assess statistical differences among groups. The results reveal significant group-specific differences in destination preferences. Children showed a higher tendency to visit bus stop types characterized by educational facilities, while people with disabilities more frequently accessed areas combining commercial and medical functions. Older adults were more likely to use bus stop types associated with cultural, leisure, and transportation hub functions. This study demonstrates that incorporating bus stop typology enables a context- aware interpretation of travel purposes and provides empirical evidence to support the development of tailored public transport policies and bus stop environment improvements for transportation-disadvantaged populations.

Keywords
bus stop functional typology
K-means clustering
POI (Point of Interest)
smart card data
TF-IDF
transportation vulnerable

본 연구는 수도권 지역을 대상으로 스마트카드 교통 데이터와 관심지점(Point of Interest, POI) 데이터를 결합하여 교통약자(어린이, 고령자, 장애인)의 통행 목적과 이동 패턴을 분석하는 것을 목적으로 한다. 기존의 스마트카드 기반 연구는 승·하차 시점의 시공간 정보에 의존함으로써 이동량 분석에는 유용하였으나, 구체적인 통행 목적을 해석하는 데에는 한계가 있었다. 이에 본 연구는 버스 정류장 주변의 POI 데이터를 활용하여 정류장 환경의 공간적 특성을 정량화하고, 이를 통행 분석에 반영하였다. 정류장 반경 내 POI 유형의 구성 비율에 TF-IDF(Term Frequency–Inverse Document Frequency) 알고리즘을 적용하여 시설 분포의 불균형을 보정하고, 정류장별 특성 벡터를 산출하였다. 이를 기반으로 K-means 군집 분석을 수행하여 수도권 버스 정류장을 13개의 기능적 유형으로 분류하였다. 도출된 정류장 유형은 교통카드 OD(Origin–Destination) 데이터와 결합되어 교통약자 유형별 방문 특성 분석에 활용되었으며, 카이제곱 검정을 통해 집단 간 방문 패턴의 통계적 유의성을 검증하였다. 분석 결과, 교통약자 유형에 따라 정류장 유형별 방문 분포에 유의미한 차이가 나타났다. 어린이는 교육 관련 시설이 밀집된 정류장 유형을 상대적으로 선호하였으며, 장애인은 상업 및 의료 시설이 복합된 유형을, 고령자는 문화·여가 시설 및 교통 결절점 기능을 포함한 유형을 주로 이용하는 경향을 보였다. 본 연구는 정류장 유형화를 통해 대중교통 이용 환경의 공간적 맥락을 체계적으로 반영하고, 이를 교통약자 통행 목적 분석에 연결하였다는 점에서 의의를 가지며, 교통약자 맞춤형 교통 정책 및 정류장 환경 개선을 위한 기초 자료를 제공한다.

키워드
정류장 기능 유형
K-means 군집화
관심지점(POI)
스마트카드 데이터
TF-IDF
교통약자
References
1

Alsger A., Tavassoli A., Mesbah M., Ferreira L., Hickman M. (2018), Public Transport Trip Purpose Inference Using Smart Card Fare Data, Transp. Res. Part C: Emerg. Technol., 87, Elsevier, 123-137.

10.1016/j.trc.2017.12.016
2

Bai H., Zhu X., Liu Y., Zhang T., Jia C., Cao J. et al. (2025), Analysis of Urban Functional Areas Based on Graph Clustering Neural Networks, J. Urban Manage., 14(2), Elsevier, 607-614.

10.1016/j.jum.2025.01.003
3

Chen L., Chen Y., Wang Y., Li Y. (2024), Research on the Classification of Rail Transit Stations and Passenger Flow Patterns—A Case From Xi'an, China, Buildings, 14(4), MDPI, 1068.

10.3390/buildings14041068
4

Daniels R., Mulley C. (2013), Explaining Walking Distance to Public Transport: The Dominance of Public Transport Supply, J. Transp. Land Use, 6(2), World Society for Transport and Land Use Research, 5-20.

10.5198/jtlu.v6i2.308
5

Dhananjaya D. D., Sivakumar T. (2022), Enhancing the POI Data for Trip Purpose Inference Using Machine Learning Techniques, Proc. IEEE Int. Conf. Intell. Transp. Syst. (ITSC), IEEE, 3496-3501.

10.1109/ITSC55140.2022.9922534
6

El-Geneidy A., Grimsrud M., Wasfi R., Tétreault P., Surprenant-Legault J. (2014), New Evidence on Walking Distances to Transit Stops: Identifying Redundancies and Gaps Using Variable Service Areas, Transportation, 41(1), Springer, 193-210.

10.1007/s11116-013-9508-z
7

Ewing R., Cervero R. (2010), Travel and the Built Environment: A Meta-Analysis, J. Am. Plan. Assoc., 76(3), Routledge, 265-294.

10.1080/01944361003766766
8

Faroqi H., Mesbah M. (2021), Inferring Trip Purpose by Clustering Sequences of Smart Card Records, Transp. Res. Part C: Emerg. Technol., 127, Elsevier, 103131.

10.1016/j.trc.2021.103131
9

Han Y., Ku J., Kim Y., Hwang J. (2022), Analyzing the Accessibility of Subway Stations for Transport-Vulnerable Population Segments in Seoul: Case of Bus-to-Subway Transfer, Case Stud. Transp. Policy, 10(1), Elsevier, 166-174.

10.1016/j.cstp.2021.11.014
10

He L., Agard B., Trépanier M. (2020), A Classification of Public Transit Users With Smart Card Data Based on Time Series Distance Metrics and a Hierarchical Clustering Method, Transportmetrica A: Transp. Sci., 16(1), Taylor & Francis, 56-75.

10.1080/23249935.2018.1479722
11

Hussain E., Bhaskar A., Chung E. (2021), Transit OD Matrix Estimation Using Smartcard Data: Recent Developments and Future Research Challenges, Transp. Res. Part C: Emerg. Technol., 125, Elsevier, 103044.

10.1016/j.trc.2021.103044
12

Kang E., Park S., Seo Y., Kim H. (2023), Introducing Autonomous Shuttle Services Based on Travel Patterns for the Elderly, J. Adv. Transp., 2023, Wiley/Hindawi, Article 2206625.

10.1155/2023/2206625
13

Kim E.-J., Kim Y., Kim D.-K. (2020), Interpretable Machine-Learning Models for Estimating Trip Purpose in Smart Card Data, Proc. Inst. Civ. Eng. Munic. Eng., 174(2), ICE Publishing, 108-117.

10.1680/jmuen.20.00003
14

Korea Transportation Safety Authority (2022), 2022 Survey on Mobility Convenience for the Transportation Disadvantaged, Korea Transportation Safety Authority, 195-201.

15

Kwon M. Y., Kim Y., Ku J. (2021), Evaluation of Transit Transfer Pattern for the Mobility Handicapped Using Traffic Card Big Data: Focus on Transfer Between Bus and Metro (교통카드데이터를 활용한 교통약자 대중교통 환승통행패턴 분석: 버스 지하철 간 환승을 중심으로), J. Korean Soc. Intell. Transp. Syst., 20(2), Korean Society of Intelligent Transport Systems, 58-71.

10.12815/kits.2021.20.2.58
16

Lee H. J., Ha J., Lee S. G. (2017), An Analysis on the Equity of Public Transit Service Using Smart Card Data in Seoul, Korea: Focused on the Mobility of the Disadvantaged Population Groups, J. Korean Reg. Sci. Assoc., 33(3), Korean Regional Science Association, 101-113.

10.22669/KRSA.2017.33.3.101
17

Lee S. G., Hickman M. (2014), Trip Purpose Inference Using Automated Fare Collection Data, Public Transp., 6(1-2), Springer, 1-20.

10.1007/s12469-013-0077-5
18

Luo G., Ye J., Wang J., Wei Y. (2023), Urban Functional Zone Classification Based on POI Data and Machine Learning, Sustainability, 15(5), MDPI, 4631.

10.3390/su15054631
19

Ma L., Kent J., Mulley C. (2018), Transport Disadvantage, Social Exclusion, and Subjective Well-Being: The Role of the Neighborhood Environment—Evidence From Sydney, Australia, J. Transp. Land Use, 11(1), World Society for Transport and Land Use Research, 31-47.

10.5198/jtlu.2018.1008
20

Ministry of Land, Infrastructure and Transport (2022), The 4th Plan for Improving Mobility Convenience for the Transportation Disadvantaged (2022-2026), Ministry of Land, Infrastructure and Transport, 8.

21

Ministry of Land, Infrastructure and Transport (2025), 2024 Survey on Mobility Convenience for the Transportation Disadvantaged, Ministry of Land, Infrastructure and Transport, 1.

22

Niu H., Silva E. A. (2021), Delineating Urban Functional Use From Points of Interest Data With Neural Network Embedding: A Case Study in Greater London, Comput. Environ. Urban Syst., 88, Elsevier, 101651.

10.1016/j.compenvurbsys.2021.101651
23

Patil D. S., Bailey A., George S., Hyde M., Ashok L. (2023), Unpacking the Role of Transport Inequalities Among Older Adults for Accessing Healthcare in Bengaluru, India, Glob. Public Health, 18(1), Taylor & Francis, 2274438.

10.1080/17441692.2023.2274438
24

Qu S., Ran J., Wang H., Jia H., Hu S. (2025), Uncovering Urban Functional Areas Differences Through POI-Based Spatial Metrics: Evidence From Jianghan District, Wuhan, Int. J. Digital Earth, 18(1), Taylor & Francis, 2605842.

10.1080/17538947.2025.2605842
25

Ravensbergen L., Van Liefferinge M., Jimenez I., Zhang M., El-Geneidy A. (2022), Accessibility by Public Transport for Older Adults: A Systematic Review, J. Transp. Geogr., 103, Elsevier, 103408.

10.1016/j.jtrangeo.2022.103408
26

Uber Engineering (2018), Uber H3: A Hexagonal Hierarchical Spatial Index, https://www.uber.com/blog/h3, 2024.12.23.

27

van der Waerden P., van der Waerden J., Burger M. (2024), Exploring the Role of Public Transport Service and Walking Route Related Factors to Identify Maximum Walking Distances to Bus Stops in the Netherlands, J. Public Transp., 26, Elsevier, 100083.

10.1016/j.jpubtr.2024.100096
28

Wang H., Loo B. P. Y. (2024), The Public Transport Disadvantaged in a Highly Transit-Oriented City: An Analytical Framework, Key Challenges and Opportunities, J. Transp. Geogr., 120, Elsevier, 103983.

10.1016/j.jtrangeo.2024.103983
29

Wang Z., Ma D., Sun D., Zhang J. (2021), Identification and Analysis of Urban Functional Area in Hangzhou Based on OSM and POI Data, PLoS ONE, 16(5), PLoS, e0251988.

10.1371/journal.pone.025198834043670PMC8159005
30

Xu L., Ren H., Mao R., Yao J., Zhang C., Wu S. et al. (2025), Metro Station Area Functional Classification Based on Graph Convolutional Networks and Integrated Metro Passenger Flow Data, Trans. GIS, 29(7), Wiley, e70151.

10.1111/tgis.70151
31

Yuan J., Zheng Y., Xie X. (2012), Discovering Regions of Different Functions in a City Using Human Mobility and POIs, Proc. ACM SIGKDD, ACM, 186-194.

10.1145/2339530.2339561
32

Zhang N., Yang Q. (2024), Public Transport Inclusion and Active Aging: A Systematic Review on Elderly Mobility, J. Traffic Transp. Eng. (English Ed.), 11(2), Elsevier, 312-347.

10.1016/j.jtte.2024.04.001
33

Zhang P., Yang M., Wang Y., Yang T., Yu H., Yan X. (2024), Integrating Metro Passenger Flow Data to Improve the Classification of Urban Functional Regions Using a Heterogeneous Graph Neural Network, Int. J. Digital Earth, 17(1), Taylor & Francis, 2443468.

10.1080/17538947.2024.2443468
34

Zhang Y., Zheng M. (2026), Comparative Analysis of Urban Functional Zone Identification Methods Based on POI Data: Improvements Using Network Constraints and Cell Declustering, Trans. GIS, 30, Wiley, e70209.

10.1111/tgis.70209
35

Zhao D., Zhou W., Wang W., Hua X. (2024), Trip Purpose Prediction Using Travel Survey Data With POI Information via Gradient Boosting Decision Trees, IET Intell. Transp. Syst., 18(1), IET, 42-55.

10.1049/itr2.12450
36

Zhao P., Cao Y. (2020), Identifying Metro Trip Purpose Using Multi-Source Geographic Big Data and Machine Learning Approach, J. Geo-Inf. Sci., 22(9), Science Press, 1753-1765.

37

Zhong S., Xu X., Yu C., Xia L. (2021), A Classification Method of Rail Transit Stations Based on POI Data and TF-IDF Index, Proc. CICTP, ASCE, 2337-2346.

10.1061/9780784483565.225
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 44
  • No :4
  • Pages :641-665
  • Received Date : 2026-03-16
  • Revised Date : 2026-04-06
  • Accepted Date : 2026-04-20
  • DOI :https://doi.org/10.7470/jkst.2026.44.4.641
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • scopus
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close