Browse > Article
http://dx.doi.org/10.5659/JAIK.2022.38.3.189

Typification of Irregular Shaped Land Parcels Using Machine Learning  

Hong, Sungjo (Dept. of Urban Engineering, Chungbuk National University)
Lee, Yoonseo (Center for Educational Facilities and Environments Research, Korean Educational Development Institute)
Publication Information
Journal of the Architectural Institute of Korea / v.38, no.3, 2022 , pp. 189-198 More about this Journal
Abstract
The shape of land parcels greatly affects land value, the density of buildings, and the shape of a building. Although the Korean system classifies parcel shapes into 6 types, there are irregularly shaped land parcels that cannot be classified. Irregular shaped land parcels impose many restrictions on the arrangement and form of buildings, and these restrictions are even more severe with small parcels. Until now, studies on the shape of parcels have been conducted, but studies on irregularly shaped land parcels have been insufficient. Therefore, this study aims to typify irregular shaped land parcels that are difficult for humans to distinguish by applying machine learning methodology and to identify the characteristics of each type. The subject of this study is irregular shaped land parcels in the class-II general residential areas of Seoul; there were 500 sample parcels extracted and used for analysis. Irregular shaped land parcels were typified using K-means clustering, which is a representative method of unsupervised learning to solve classification problems. Afterwards, the values of Shape Index (SI), STandard Index (STI), and With-depth Ratio (WR), which are indices related to parcel shape, were compared by type. Upon analysis, the types of irregular parcels could be divided into avocado type, potato type, corner type, bell type, stick type, and L-shaped type. The stick type and L-shaped type reflected small SI values. The avocado type, corner type, and L-shaped type revealed small STI values. Lastly, the WR value was substantial for the stick type and L-shaped type.
Keywords
Irregular Shaped Land Parcel; Shape of Land Parcel; Machine Learning; K-means Clustering; Urban Spatial Structure;
Citations & Related Records
Times Cited By KSCI : 9  (Citation Analysis)
연도 인용수 순위
1 Choi, J., Sim, J., & Kim, B. (2015). A Study on Improvement of Land Characteristic Survey. Daegu, Research Institute of REB.
2 Choi, J., & Lee, S. (2017), A study on the method of land shape recognition using the geometric feature information of parcel and the technique of decision tree, Journal of Real Estate Analysis, 3(1), 19-34.   DOI
3 Chun, H. (2020). A study on office rent prediction using extreme learning machine and vector autoregression model, Journal of the Korea Real Estate Management Review, 22, 55-74.   DOI
4 Heo, S., Kim, J., & Moon, T. (2018). Predicting crime risky area using machine learning, Journal of the Korean Association of Geographic Information Studies, 21(4), 64-80.   DOI
5 Hong, I. (2017). Land use classification using LBSN (Location-Based Social Network) data and machine learning technique, Journal of Korean Cartographic Association, 17(3), 59-67.   DOI
6 Jeon, S., Duhirwe, P., Yun, G. (2020). Predicting indoor air quality in Korean schools using machine learning techniques, Proceedings of the Conference of the Korea Institute of Ecological Architecture and Environment, 112-113.
7 Kang, M., Jung, Y., & Jang, D. (2017). A study on the search of optimal aquaculture farm condition based on machine learning, The Journal of The Institute of Internet, Broadcasting and Communication, 17(2), 135-140.   DOI
8 Kim, D., & Jung, S. (2021). Comparison of crime forecasting models based on spatio-temporal data and machine learning, Journal of the Architectural Institute of Korea, 37(1), 135-143.   DOI
9 Kim, K. (2020). Analysis on Mechanism of Individual Building Development in Low-Rise Residential Area of Seoul using Machine Learning-based Decision Tree, Ph.D. Dissertation, University of Seoul, 40.
10 Kim, S., & Ha, M. (2020). A model for the analysis of crime risk by street based on the principles of CPTED, Proceedings of the Conference of the Architectural Institute of Korea, 40(1), 233-234.
11 Ko, Y. (2016). A Comparative Analysis of Floor Area Ratio According to the Standardization of Small-size Irregular Parcel, Master Dissertation, Seoul National University of Science and Technology.
12 Lee, J., Park, S., Cho, S., & Kim, J. (2021). Comparison of models to forecast real estates index introducing machine learning, Journal of the Architectural Institute of Korea, 37(1), 191-199.   DOI
13 Lee, I., Lim, S., & Kim, C. (2009). Analysis of the effect of parcel shape on the development density, Journal of the Urban Design Institute of Korea, 10(5), 151-162.
14 Lee, S., & Tae, S. (2020). Building case-based greenhouse gas reduction decision support model using machine learning. KIEAE Journal, 20(3), 39-46.   DOI
15 Lee, Y., Yoon, Y., & Moon, H. (2020). A model for classification of occupant behavior based on building environmental data by seasons, Journal of the Architectural Institute of Korea, 36(11), 239-245.   DOI
16 Oh, J., & Kim, J. (2018). Nonlinear effects of physical characteristics of apartment on housing prices: focusing on multivariate adaptive regression spline, Appraisal Studies, 17(3), 5-26.   DOI
17 Park, H. (2020). Self-study Machine Learning and Deep Learning, Seoul, Hanbit Media.
18 Shin, D. (2019). Machine learning based architecture and urban data analysis: construction of floating population model using deep learning, Journal of KIBIM, 9(1), 22-31.   DOI
19 Lee, S., Jung, S., & Lim, K. (2019). An analysis of energy consumption types considering life patterns of single-person households, Journal of the Architectural Institute of Korea, 35(1), 37-46.
20 Park, K., & Lee, S. (2018). Application and validation of a deep learning model to predict the walking satisfaction on street level, Journal of the Urban Design Institute of Korea Urban Design, 19(6), 19-34.   DOI
21 McGarigal, K., & Marks, B. (1995). FRAGSTATS: Spatial Pattern Analysis Program for Quantifying Landscape Structure, Portland, U.S. Department of Agriculture, Forest Service, Pacific Northwest Research Station.
22 Min, M. (2018). Classification of Seoul metro stations based on boarding/alighting patterns using machine learning clustering, The Journal of The Institute of Internet, Broadcasting and Communication, 18(4), 13-18.   DOI
23 MOLIT. (2019). Guidelines for Investigation and Calculation of Individual Official Land Price Applied in 2020, Sejong, MOLIT, 105-107.
24 MOLIT. (2020). Guidelines for Investigation and Calculation of Individual Official Land Price Applied in 2021, Sejong, MOLIT, 108-113.
25 MOLIT. & LH. (2021). 2020 Urban Planning Status, Sejong, MOLIT, 101-136.
26 National Institute of the Korean Language (n.d.) Standard Korean Dictionary, Retrieved November 16, 2021 from https://stdict.korean.go.kr
27 Yoon, K., Lee, J., Ko, S., Kim, H., & Kim, J. (2021). Analysing impact of price ceiling system on housing market using machine learning, Journal of the Architectural Institute of Korea, 37(8), 221-228.   DOI
28 Won, S., & Hwang, C. (2018). Simulating land use change using decision tree and SVM model - a case study of North Koreas city after the unification, The Korea Spatial Planning Review, 97, 41-56.   DOI
29 Yang, S. (1994). Study on the type of urban tissue of Seoul in the late Choseon dynasty, Ph.D. Dissertation, Seoul National University.
30 Yoo, D., Kim, K., Choi, C., Cho, S., & Jang. H. (2021). Development of a machine learning-based low-rise residential building energy consumption prediction model, Journal of Korean Institute of Architectural Sustainable Environment and Building Systems, 15(2), 152-165.
31 Yun, S.B., Mun, S., Park, S.Y., & Kim, T. (2021). Data-driven analysis for future land-use change prediction: case study on Seoul, Journal of Broadcast Engineering, 25(2), 176-184.   DOI
32 National Spatial Data Infrastructure Portal (n.d.) Retrieved November 16, 2021 from http://www.nsdi.go.kr