킥보드 불법 주차 문제 해결을 위한 도착지 중심 스테이션 증설 알고리즘
Station Extension Algorithm Considering Destinations to Solve Illegal Parking of E-Scooters
0
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
본 연구는 공유 전동 킥보드 불법 주차 문제를 해결하고 서비스 품질을 개선하기 위하여 새로운스테이션 선정 알고리즘을 제안하는 것을 목표로 한다. 최근 도시 교통 문제의 해결 방안으로 대중교통과 최종 목적지를 연결하는 퍼스트-라스트 마일 수단으로 공유 전동 킥보드가 주목받고 있다. 그에 따라 공유 전동 킥보드 시장도 급속도로 성장하면서 그로 인한 문제 또한 심화되고 있다. 이에본 연구에서는 문제의 본질을 파악하기 위해 텍스트 데이터를 수집하여 ‘LDA 토픽 모델링’으로 공유 킥보드에 관한 이슈를 보행자와 이용자 관점에서 살펴보고 이를 바탕으로 스테이션 증설 알고리즘을 마련하려 한다. 기존에 이미 일부 주차장이 설치되어 있지만 기존의 주차장 위치는 실제 견인다발 지역과 불일치한다. 따라서 본 연구에서는 ‘서울특별시 전동 킥보드 견인 현황’ 데이터와 여러요인을 반영하여 DBSCAN을 통한 1차 클러스터링 후, K-means를 적용하는 혼합형 클러스터링 기법으로 실제 견인 밀도가 높은 곳에 스테이션을 설치할 수 있는 알고리즘을 제안한다.
Abstract
In this paper, we propose a new station selection algorithm to solve the illegal parking problem of shared electric scooters and improve the service quality. Recently, as a solution to the urban transportation problem, shared electric scooters are attracting attention as the first and last mile means between public transportation and final destinations. As a result, the shared electric scooter market grew rapidly, problems caused by electric scooters are becoming serious. Therefore, in this study, text data are collected to understand the nature of the problem, and the problems related to shared scooters are viewed from the perspective of pedestrians and users in ‘LDA Topic Modeling’, and a station extension algorithm is based on this. Some parking lots have already been installed, but the existing parking lot location is different from the actual area of tow. Therefore, in this study, we propose an algorithm that can install stations at high actual tow density using mixed clustering technology using K-means after primary clustering by DBSCAN, reflecting the ‘current state of electric scooter tow in Seoul’.
참고문헌 (42)
- "A Topical Dictionary"[URL]
- "Monthly Topic"[URL]
- "Global companies packing in Korea in one year of strengthening regulations on electric scooters"[URL]
- Shin Huicheol, "Activation Plan for Future Personal Mobility", Monthly KOTI Magazine on Transport, 268, pp.31~37 (2020)
- "An e-scooter accident... 9 out of 10 ‘have safety concerns’"[URL]
- Korea Transportation Research Institute, "What is the solution to shared e-scooter parking?", Monthly KOTI Magazine on Transport, 268, pp.77~77 (2020)
- "As civil complaints increase, processing costs rise’What should I do with a shared e-scooter?"[URL]
- "I came here after looking at the app but there is no e-scooter"[URL]
- Jo Jeonghun, "A Comparison study on Micro-mobility Usage Pattern : focusing on Bike-sharing service and E-Scooter share service in Seoul", Fall Conference of the Korean ITS, pp.237~242 (2020)
- 김수재, "공유 전동킥보드 이용 특성 및 영향요인에 관한 연구", 한국ITS학회 논문지, 20(1), pp.40~53 (2021), 한국ITS학회[DOI]
- 장은진, "공유형 전동킥보드의 효율적 회수를 위한 새로운 IoT 관리시스템 설계", 한국인터넷방송통신학회 논문지, 21(1), pp.189~194 (2021), 한국인터넷방송통신학회[DOI]
- Choi Seonil, "Modular Autonomous Parking System for Shared Scooters", ICROS Annual Conference, pp.693~694 (2022)
- 최혜정, "대중교통 이용률을 높이기 위한 공유 전동킥보드의 수요 주도형 배분 방법 연구", 한국지적정보학회지, 24(1), pp.126~137 (2022), 한국지적정보학회
- 한재원, "서울시 Personal Mobility 우선 공급 지역 분석 : First-Last Mile 통행특성을 중심으로", 국토계획, 57(1), pp.42~56 (2022), 대한국토·도시계획학회[DOI]
- Kurniawan, Dwi Ely, "Clustering of Social Conditions in Batam, Indonesia Using K-Means Algorithm and Geographic Information System", International Journal of Earth Sciences and Engineering (IJEE), 10(5), pp.1076~1080 (2017)
- Annas, Suwardi, Uca, U., "Using k-Means and Self Organizing Maps in Clustering Air Pollution Distribution in Makassar City, Indonesia", Jambura Journal of Mathematics, 4(1), pp.167~176 (2022)
- Lee Byeonggil, "Commercial district extraction using spatial data mining technique in business GIS", Korean GIS Journal, 11(2), pp.171~184 (2003)
- David M. Blei, "Latent Dirichlet Allocation", Journal of Machine Learning Research, 3, pp.993~1022 (2003)
- "Paris considers e-scooter rental ban amid successive deaths"[URL]
- "Shared E-scooter ‘War’ in Gangnam"[URL]
- "Illegal parking and sharing e-scooter tow is implemented"[URL]
- "The e-scooter industry appeals for the burden of 'immediate tow' 450 million won for tow and storage only"[URL]
- "Strengthening shared e-scooter regulations: 100million monthly tow fee ‘Cost is passed on to the consumer’"[URL]
- "Seoul Population Density Statistics" (2021)[URL]
- "Seoul Living Migration"[URL]
- Ester, M., "A density-based algorithm for discovering clusters in large spatial databases with noise", kdd, 96(34), pp.226~231 (1996)
- Murugesan, N., "Benchmarking in cluster analysis: a study on spectral clustering, DBSCAN, and K-Means", Data Analysis and Rationality in a Complex World, 16, pp.175~185 (2021)
- 최은석, "DBSCAN 기반의 제조 공정 데이터 불량 위치의 검출", 한국콘텐츠학회 논문지, 17(7), pp.182~192 (2017), 한국콘텐츠학회[DOI]
- Wang, K., "Extracting Electricity Patterns from High-dimensional Data: A comparison of K-Means and DBSCAN algorithms", IOP Conference Series: Earth and Environmental Science, 1101(2), pp.022007~ (2022)
- Vassilvitskii, S, "k-means++: The advantages of careful seeding", Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, pp.1027~1035 (2006)
- MacQueen, J., "Classification and analysis of multivariate observations", 5th Berkeley Symp. Math. Statist. Probability, pp.281~297 (1967)
- Savvas, I. K., "A study of comparative clustering of EU countries using the DBSCAN and k-means techniques within the theoretical framework of systemic geopolitical analysis", Int. J. Grid Util. Comput, 8(2), pp.94~108 (2017)[DOI]
- Ran, X., "A novel K-means clustering algorithm with a noise algorithm for capturing urban hotspots", Applied Sciences, 11(23), pp.11202~ (2021)[DOI]
- Kotyrba, M., "Comparison of modern clustering algorithms for twodimensional data", Proceedings-28th European Conference on Modelling and Simulation, pp.346~351 (2014), ECMS
- Onapa Limwattanapibool, "Determination of the appropriate parameters for K‐means clustering using selection of region clusters based on density DBSCAN (SRCDDBSCAN)", Expert Systems, 34(3), pp.12204~ (2017), Wiley[DOI]
- 김태경, "DBSCAN을 이용한 교통사고 잦은 곳 선정에 관한 연구 : 경부고속도로를 중심으로", 교통연구, 21(3), pp.55~63 (2014), 한국교통연구원[DOI]
- 조홍준, "K-means를 이용한 토지 거래사례 선정범위 분석", 한국데이터정보과학회지, 30(3), pp.525~537 (2019), 한국데이터정보과학회[DOI]
- Ahmed Fahim, "K and starting means for k-means algorithm", Journal of Computational Science, 55, pp.101445~ (2021), Elsevier BV[DOI]
- Tianhui Fan, "Consumer clusters detection with geo-tagged social network data using DBSCAN algorithm: a case study of the Pearl River Delta in China", GeoJournal, 86(1), pp.317~337 (2019), Springer Science and Business Media LLC[DOI]
- 이성규, "평균연결법과 K-means 혼합클러스터링 기법을 이용한 공시지가 유사가격권역의 설정", 대한지리학회지, 41(1), pp.121~135 (2006), 대한지리학회
- Peter J. Rousseeuw, "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis", Journal of Computational and Applied Mathematics, 20, pp.53~65 (1987), Elsevier BV[DOI]