DOI QR코드

DOI QR Code

토지 보상비 결정 요인 분석 - 건설CALS 데이터 중심으로

Analysis on the Determinants of Land Compensation Cost: The Use of the Construction CALS Data

  • Lee, Sang-Gyu (Korea Institute of Civil Engineering and Building Technology) ;
  • Seo, Myoung-Bae (Korea Institute of Civil Engineering and Building Technology) ;
  • Kim, Jin-Uk (Korea Institute of Civil Engineering and Building Technology)
  • 투고 : 2020.07.09
  • 심사 : 2020.10.05
  • 발행 : 2020.10.31

초록

본 연구는 건설 전주기 (기획, 설계, 시공, 관리) 과정에서 생성되는 건설 CALS(Continuous Acquisition & Life-Cycle Support) 시스템 내의 데이터 셋 (443개)을 활용하여 토지보상비에 영향을 주는 주요 결정 요인을 분석한다. 해당 분석을 위해 기존 토지 비용 관련 연구에서 활용된 주요 변수를 활용하였다. 이를 기반으로 8개 (토지면적, 개별 공시지가, 감정평가액, 지목, 용도지역 1, 지형 고저, 지형 형상, 도로 접면)의 주요 변수를 활용하였다. 더불어, 해당 변수는 기계학습 알고리즘 기반의 Xgboost 알고리즘을 통해 변수별 중요도 평가를 진행하였고, 해당 변수 중, 개별공시지가가 가장 중요도가 높은 변수로 확인하였다. 토지보상비 결정 요인에 대한 분석 및 검증을 위해 선형다중회귀분석을 사용하였다. 검증을 위해 구성되는 변수로 종속변수는 개별공시지가 변수를 활용하였고, 독립변수는 연속형 변수 1개 (면적), 범주형 변수는 5개 (지목, 용도지역1, 지형고저, 지형형상, 도로접면)를 활용하였다. 본 연구의 모델에 대한 검증결과, 지목, 용도지역 1, 도로접면에 대한 독립 변수가 유의미한 것으로 확인하였다.

This study analyzed the determinants of land compensation costs using the CALS (Continuous Acquisition & Life-Cycle Support) system to generate data for the construction (planning, design, building, management) process. For analysis, variables used in the related research on land costs were used, which included eight variables (Land Area, Individual Public Land Price, Appraisal & Assessment, Land Category, Use District 1, Terrain Elevation, Terrain Shape, and Road). Also, the variables were analyzed using the machine learning-based Xgboost algorithm. Individual Public Land Price was identified as the most important variable in determining land cost. We used a linear multiple regression analysis to verify the determinants of land compensation. For this verification, the dependent variable included was the Individual Public Land Price, and the independent variables were the numeric variable (Land Area) and factor variables (Land Category, Use District 1, Terrain Elevation, Terrain Shape, Road). This study found that the significant variables were Land Category, Use District 1, and Road.

키워드

참고문헌

  1. S. Ryu, J. Yoo, "A Study on Improvement of Preliminary Feasibility Studies for Road Project," Gyeonggi Research Institute, 2017.
  2. "Guidelines of Preliminary Feasibility Study Operating Costs," Ministry of Economy and Finance, 2018.
  3. S. Lee, S. Park, S. Hong, "A Similar Price Zone Determination of Public Land Price Using a Hybrid Clustering Technique," Journal of the Korean Geographical Society, Vol. 4, No. 2, pp. 121-135, 2006.
  4. S. Lew, J. Kang, "A Study on the Influence Factors of Land Value by Urban Spatial Constitution," Journal of the Korean Society of Civil Engineers, Vol. 32 No. 1, pp. 61-69, 2012.
  5. J. Jeong, C. Kim., "A Study on Application Transfer of Development Rights(TDR) for Preservation of Historic Cultural Resources - Focusing on the Areas of Joong-gu, Daegu," Journal of the Urban Design Institute of Korea Urban Design, Vol. 17 No. 5, pp. 5-21, 2016.
  6. "Valuation Method of Land Compensation Cost Included Question and Answer," Korea Development Institute PIMAC(Public and Private Infrastructure Investment Management Center), 2018.
  7. G. Lee, K. Kim, "A Study on the Spatial Mismatch between the Assessed Land Value and Housing Market Price: Exploring the Scale Effect of the MAUP," Journal of the Korean Geographical Society, Vol. 48, No. 6, pp. 879-896, 2013.
  8. Y. Kim, H. Kim, "A Policy Direction for the Readjustment of Officially Announced Standard Land Price," Journal of the Korean Urban Management Association, Vol. 19, No. 3, pp. 3-22, 2007.
  9. S. Kim, K. Kwon, "A study on determinant factors for the realization rate of publicly notified individual land price," Journal of the Korean Cadastre Information Association, Vol. 15, No. 2, pp. 149-162, 2013.
  10. D. Lee, S. Jung, "Research into the Effect of Jeju Olle Tails on Nearby Land Prices using Feasirable Generalized Least Squares," Journal of Korea Real Estate Review, Vol. 24, No. 1, pp. 63-76, 2014.
  11. H. Jung, "Opportunity Cost of Protected Area Designation for Conservation of Terrestrial Ecosystem," Master's Thesis of Seoul National University, 2017.
  12. Y. Kang, H. Kim, "The Impact of Transit Facilities on Land Prices: Experiences at Seoul Station and Cheongnyangni Station," Journal of the Korean Urban Management Association, Vol. 25, No. 1, pp. 139-159, 2012.
  13. Y. Ahn, M. Lee, "The Impact of Topographical Factors on Land Price of Dilapidated Residential Complex : The Case of Cheong-ju," Journal of the Architectural Institute of Korea Planning & Design, Vol. 24, No. 6, pp. 265-272, 2008.
  14. I. Chung, "Improvement Direction of Facility Management System(FMS) through Related Systems Analysis," Korea Academy Industrial Cooperation Society, Vol. 16, No. 10, pp. 6751-6758, 2015. DOI: https://doi.org/10.5762/KAIS.2015.16.10.6751
  15. H. Ok, J. Kim, "A Research on Development Measures of Information Services for Construction Technology," Journal of the Korea Academia-Industrial cooperation Society, Vol. 16, No. 8, pp. 5707-5715, 2015. DOI: https://doi.org/10.5762/KAIS.2015.16.8.5707
  16. M. Seo, N. Kim, "Research about sharing of compensation data between owner and contractor for construction CALS improvement," The Korean Institute of Information Scientists and Engineers, Vol. 37, No. 1, pp. 144-147, 2010.
  17. J. Kim, N. Kim, "The Status and Development Direction of Construction CALS," Proceedings of Korean Institute of Information Technology Conference, pp. 1-5, 2012.
  18. S. Kim, B. Kim, T. Kim, N. Kim, "A Study on Project Information Integrated Management Measures Using Life Cycle Information in Road Construction Projects," Korea Academy Industrial Cooperation Society, Vol. 20, No. 11, pp. 208-216, 2019. DOI: https://doi.org/10.5762/KAIS.2019.20.11.208
  19. S. Yang, N. Kim, "A plan of improvement and DB analysis for the elevation of CALS System performance," The Korean Institute of Information Scientists and Engineers, Vol. 39, No. 1, pp. 31-33, 2012.
  20. S. Kim, H. Ok, "A Study of Establishing the Development Strategy of Construction Project Management System Using SWOT Analysis," Korea Academy Industrial Cooperation Society, Vol. 13, No. 10, pp. 4837-4844, 2012. DOI: https://doi.org/10.5762/KAIS.2016.17.11.86
  21. H. Lee, J. Heo, D. Hwang, "Performance Comparison of Machine Learning Algorithms for Malware Detection," The Korean Society Of Computer And Information, Vol. 26, pp. 143-146, 2018.
  22. J. Ha, H. Shin, Z. Lee, "Korean Text Classification Using Randomforest and XGBoost Focusing on Seoul Metropolitan Civil Complaint Data," The Korean journal of bigdata, Vol. 2, No. 2, pp. 95-104, 2017. https://doi.org/10.36498/kbigdt.2017.2.2.95
  23. J. Hebert, "Predicting Rare Failure Event using Classification Trees on Large Scale Manufacturing Data with Complex Interactions," IEEE International Conference on Big Data, pp. 2024-2028, 2016.
  24. T. Chen, C. Guestrin, "XGBoost: A scalable tree boosting system," Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785-794, 2016. DOI: https://doi.org/10.1145/2939672.2939785
  25. Y.Jia, S. Jin, P. Savi, Y. Gao, J. Tang, Y. Chen, W. Li, "GNSS-R Soil Moisture Retrieval Based on a XGboost Machine Learning Aided Method: Performance and Validation," Remote Sensing, Vol. 11, No. 14, pp. 1655, 2019. DOI: https://doi.org/10.3390/rs11141655
  26. D. Zhang, L. Qian, B. Mao, C. Huang, B. Huang, Y. Si, "A data-driven design for fault detection of wind turbines using random forests and xgboost," IEEE Access, Vol. 6, pp. 21020-21031, 2018. DOI: https://doi.org/10.1109/ACCESS.2018.2818678