Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction Performance Analysis of Total Construction Period through Normalization of Independent and Dependent Variables

독립변수와 종속변수 정규화를 통한 총 공사기간 예측성능 분석

  • Kang, Yun-Ho (Dept. of Architectural Engineering, Gyeongsang National University) ;
  • Lee, Ha-Neaul (Dept. of Architectural Engineering, Gyeongsang National University) ;
  • Yun, Seok-Heon (Dept. of Architectural Engineering, Gyeongsang National University)
  • 강윤호 (경상국립대 건축공학과) ;
  • 이하늘 (경상국립대 건축공학과) ;
  • 윤석헌 (경상국립대 건축공학과)
  • Received : 2023.09.11
  • Accepted : 2023.10.15
  • Published : 2023.11.30
⟨ Previous Next ⟩

Abstract

The estimation of the appropriate construction period in the construction project is one of the main factors for successfully completing the project. Various artificial intelligence technologies have been developed and various efforts have been made to improve prediction performance during the construction period by applying them, but it is still difficult to accurately predict the construction period. It is judged that the predictive performance of the learning data during the construction period may be poor due to the large deviation of the data between the independent variable and the dependent variable. In this study, it was intended to improve the predictive performance of the construction period by reducing the data deviation through the normalization of the dependent and independent variables of the training data. In this study, a total of 953 data from by the PPS(Public Procurement Service) in Korea were used for five years from 2017 to 2022, and to reduce the relative difference between independent and dependent variable data, three models were defined, and the training results were compared and analyzed. As a result of the analysis, it is judged that the model using Log normalization has the best prediction performance.

Keywords

Acknowledgement

본 연구는 국토교통부/국토교통과학기술진흥원의 2023년도 지원으로 수행되었음. 과제번호:RS-2021-KA163269

References

  1. Basma, M., & Osama, M. (2022). Conceptual estimation of construction duration and cost of public highway projects, Journal of Information Technology in Construction of Slovenian, 27, 595-618. doi:10.36680/j.itcon.2022.029.
  2. Hyun, C.T., Kim, S.I., & Cho, K.M. (2005). A Study on Development of Delivery Method Selection Criteria for Public Construction Project (National Land Research Institute 2005-39) Korea Sejong : KRIHS.
  3. Kim, J.S., & Kim, Y.S. (2021). Development of a Model for Calculating the Construction Duration of Urban Residential Housing Based on Multiple Regression Analysis, Journal of Land, Housing, and Urban Affairs of Korea, 12(4), 93-101.
  4. Kim, Y.J. (2018). Development of Construction Duration Prediction Model in Project Planning Phase for Mixed-use Buildings, MBA. Dissertation, Inha University.
  5. Kim, B.S., & Chun, J.K. (2005). A Study on Estimation Model of Construction Duration for Public Construction, journal of construction engineering and management of korea, 6(6), 142-151.
  6. Kim, S.W. (2021). A study to predict the duration of building structural works by introducing deep neural network, MBA. Dissertation, Hanyang University.
  7. Martin, S., & Thomas, N.G. (2003). Forecast models for actual construction time and cost, Journal of Building and Environment of United Kingdom, 38(8), 1075-1083. doi:https://doi.org/10.1016/S0360-1323(03)00067-2.
  8. Park, S.H. (2011). Judgement Model for Construction Cost Appropriateness of Multi-Family Housing Projects in Planning Phase, MBA. Dissertation, University of Seoul.
  9. Sdhabhon, B., & Stephen, O.O. (1999). Application of artificial neural network to forecast construction duration of buildings at the predesign stage, Journal of Engineering Construction & Architectural Management of United Kingdom, 6(2), 133-144. doi:10.1108/eb021106.