Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Application and development of a machine learning based model for identification of apartment building types - Analysis of apartment site characteristics based on main building shape -

머신러닝 기반 아파트 주동형상 자동 판별 모형 개발 및 적용 - 주동형상에 따른 아파트 개발 특성분석을 중심으로 -

  • Sanguk HAN (Ulsan National Institute of Science and Technology, Department of Urban and Environmental Engineering) ;
  • Jungseok SEO (Ulsan National Institute of Science and Technology, Department of Urban and Environmental Engineering) ;
  • Sri Utami Purwaningati (Ulsan National Institute of Science and Technology, Department of Urban and Environmental Engineering) ;
  • Sri Utami Purwaningati (Ulsan National Institute of Science and Technology, Department of Urban and Environmental Engineering) ;
  • Jeongseob KIM (Ulsan National Institute of Science and Technology, Department of Urban and Environmental Engineering)
  • 한상욱 (울산과학기술원 도시환경공학과 ) ;
  • 서정석 (울산과학기술원 도시환경공학과 ) ;
  • ;
  • ;
  • 김정섭 (울산과학기술원 도시환경공학과 )
  • Received : 2023.05.10
  • Accepted : 2023.05.30
  • Published : 2023.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aims to develop a model that can automatically identify the rooftop shape of apartment buildings using GIS and machine learning algorithms, and apply it to analyze the relationship between rooftop shape and characteristics of apartment complexes. A database of rooftop data for each building in an apartment complex was constructed using geospatial data, and individual buildings within each complex were classified into flat type, tower type, and mixed types using the random forest algorithm. In addition, the relationship between the proportion of rooftop shapes, development density, height, and other characteristics of apartment complexes was analyzed to propose the potential application of geospatial information in the real estate field. This study is expected to serve as a basic research on AI-based building type classification and to be utilized in various spatial and real estate analyses.

본 연구의 목적은 GIS와 머신러닝 알고리즘을 활용하여 아파트 단지의 주동형상을 자동으로 판별해주는 모형을 개발하고, 이를 주동형상과 단지특성 관의 관계 분석에 적용하는 것이다. 지리정보데이터를 사용하여 아파트단지별 주동 데이터베이스를 구축하고 랜덤포레스트 알고리즘을 활용하여 단지 내 개별동을 형태에 따라 판상형, 탑상협, 혼합형으로 분류하였다. 또한, 아파트단지별 주동형상별 비중과 개발밀도, 층수 등 단지특성 정보간의 관계를 분석하여 부동산 분야 지리정보응용 가능성을 제안하였다. 본 연구는 인공지능 기반 건축물 유형 분류와 관련한 기초연구로서 다양한 공간분석 및 부동산 분석에 활용될 것으로 예상한다.

Keywords

Acknowledgement

이 논문은 한국국토정보공사 공간정보연구원 산학협력R&D사업의 지원을 받아 수행된 연구임.(과제명:노후계획도시 재정비를 위한 디지털트윈 기반 정비사업 시뮬레이션 및 평가체계 개발, 과제번호:2022-503)

References

  1. Choi, M.H. 1997. A study on the characteristics of the physical form and the spatial layout of multi-family housing in Taegu., Journal of the Architectural Institute of Korea Structure & Construction 13(2):117-124.
  2. Heo, S.Y., J.Y. Kim, and T.H. Moon, 2018. Predicting crime risky area using machine learning. Journal of the Korean Association of Geographic Information Studies 21(4):64-80.
  3. Kim, H.J., Y.S. Kim. S.J. Kim, J.G. Jo, and C.K. Park, 2010. An analysis on the layout patterns and their trends in the apartment housing design competitions of Sejong city. Journal of the Korea Academia -Industrial cooperation Society 11(4): 1381-1390. https://doi.org/10.5762/KAIS.2010.11.4.1381
  4. Kim, Y.B. 2005. An architectural study on changes of the apartment housing layout techniques : focused on the cases capital area during 1970~2000. Thesis, Univ. of Hanyang. Seoul. Korea. 85pp.
  5. Ko, S.I. and J.J. Lee. 2022. A study of the building types and arrangements of apartment building complex using image analysis. Journal of the Architectural Institute of Korea Structure & Construction 42(2):340-343.
  6. Lee, J.E. and J.M. Kim. 2015. A study on the preference of residents about apartment building space and arrangement. Journal of the Architectural Institute of Korea Structure & Construction 31(7):39-47
  7. Lee, J.E. and G.U. Lee. 2014. Comparison of daylighting and dnergy performance according to apartment floor shapes. Journal of the Architectural Institute of Korea Structure & Construction 30(3):113-120.
  8. Population Census Division, Census Management Bureau. 2022, The results of the 2022 and 2021 population and housing census. Statistical Office
  9. Son, S.G. and G.H. Kang. 2001. A study on the change in the characteristic of outdoor planning of Korean public apartment project. Journal of the Korean Housing Association 12(4):1-8.
  10. Yoo, B.H. and S.H. Han. 2005. Image-based modeling of urban buildings using aerial photographs and digital maps. Journal of the Korean Association of Geographic Information Studies 8(1):49-62.