대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제39권3호
  • /
  • Pages.179-187
  • /
  • 2023
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

Decision tree 기반 알고리즘을 활용한 해체폐기물 발생량 예측모델 개발

Development of an Predictive Model via Decision Tree-Based Algorithms for Forecasting Demolition Waste Generation

  • 차기욱 (경북대학교 과학기술실용공학부) ;
  • 홍원화 (경북대학교 건설환경에너지공학부)
  • Cha, Gi-Wook (School of Science and Technology Acceleration Engineering, Kyungpook National University) ;
  • Hong, Won-Hwa (School of Architectural, Civil, Environmental and Energy Engineering, Kyungpook National University)
  • 투고 : 2022.11.14
  • 심사 : 2023.01.19
  • 발행 : 2023.03.30
⟨ 이전 논문 다음 논문 ⟩

초록

Management of demolition waste (DW), which accounts for a large portion of waste generation (WG), is a very important issue. Therefore, many researchers tried to apply various ML algorithms to predict WG, and tried to find the decisive factors affecting WG. This study conducted a study on the development of optimal ML model for predicting demolition waste generation (DWG). In this study, decision tree (DT), random forest (RF), and gradient boost machine (GBM) algorithms were applied to develop ML models to predictive DWG. For this, data preprocessing was performed and the optimal hyper parameter was searched for each algorithm to derive an optimal ML model. In consideration of dataset size, leave one out cross validation (LOOCV) was applied to the model validation and mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R squared), and mean square error (MSE) were used as the performance evaluation index of the models. As a result of this study, it was found that the predictive performance of the RF model (MAE 72.837, MSE 12198.236, RMSE 110.446, R2 0.880) was better than one of DT (MAE 87.081, MSE 17348.052, RMSE 131.712, R2 0.829) and GBM (MAE 87.883, MSE 18175.125, RMSE 134.815, R2 0.821) models. The error from the observed mean (987.1806 kg m-2) was 8.82%, 7.38%, and 8.90% for the DT, RF, and GBM models, respectively. Therefore, it can be seen that the ML model using the DT-based algorithms is very good at predicting DWG. Finally, this study presented a reliable and optimal ML model for predicting DWG for a domestic waste management strategy.

키워드

과제정보

이 연구는 2022년도 한국연구재단 연구비 지원에 의한 결과의 일부임. 과제번호:NRF-2019R1A2C1088446

참고문헌

  1. Abdallah, M., Talib, M. A., Feroz, S., Nasir, Q., Abdalla, H., & Mahfood, B. (2020). Artificial intelligence applications in solid waste management: A systematic research review. Waste Management, 109, 231-246. https://doi.org/10.1016/j.wasman.2020.04.057
  2. Akanbi, L. A., Oyedele, A. O., Oyedele, L. O., & Salami, R. O. (2020). Deep learning model for Demolition Waste Prediction in a circular economy. Journal of Cleaner Production, 274, 122843.
  3. Butera, S., Christensen, T. H., & Astrup, T. F. (2014). Composition and leaching of construction and demolition waste: inorganic elements and organic compounds. Journal of Hazardous Materials, 276, 302-311. https://doi.org/10.1016/j.jhazmat.2014.05.033
  4. Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  5. Cha, G. W., Kim, Y. C., Moon, H. J., & Hong, W. H. (2017). New approach for forecasting demolition waste generation using chi-squared automatic interaction detection (CHAID) method. Journal of Cleaner Production, 168, 375-385.
  6. Cha, G. W., Moon, H. J., Kim, Y. M., Hong, W. H., Hwang, J. H., Park, W. J., & Kim, Y. C. (2020). Development of a prediction model for demolition waste generation using a random forest algorithm based on small datasets. International Journal of Environmental Research and Public Health, 17(19), 6997.
  7. Cha, G. W., Moon, H. J., & Kim, Y. C. (2021). Comparison of random forest and gradient boosting machine models for predicting demolition waste based on small datasets and categorical variables. International Journal of Environmental Research and Public Health, 18(16), 8530.
  8. Cha, G. W., Moon, H. J., & Kim, Y. C. (2022). A hybrid machine-learning model for predicting the waste generation rate of building demolition projects. Journal of Cleaner Production, 134096.
  9. Cheng, J., Dekkers, J. C., & Fernando, R. L. (2021). Cross-validation of best linear unbiased predictions of breeding values using an efficient leave-one-out strategy. Journal of Animal Breeding and Genetics, 138(5), 519-527. https://doi.org/10.1111/jbg.12545
  10. Choi, S. W. (2019). A study on the determinants and forecasting model of household waste generation, Master's thesis. University of Seoul (UOS)
  11. Cochran, K., Townsend, T., Reinhart, D., & Heck, H. (2007). Estimation of regional building-related C&D debris generation and composition: Case study for Florida, US. Waste management, 27(7), 921-931. https://doi.org/10.1016/j.wasman.2006.03.023
  12. Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
  13. Huang, X., & Xu, X. (2011). Legal regulation perspective of eco-efficiency construction waste reduction and utilization. Urban Development Studies, 9, 90-94.
  14. Jo, U. H., Byun, J. H., Won, J. M., Kim, E. A., Kim, Y. Y., Choi, Y. H., You, C. S., & Kim, J. S. (2019). Prediction of MSW Generation in Gyeonggi-do Using Multiple Regression Analysis. Korea society of waste management, 2019(0), 122-122.
  15. Kannangara, M., Dua, R., Ahmadi, L., & Bensebaa, F. (2018). Modeling and prediction of regional municipal solid waste generation and diversion in Canada using machine learning approaches. Waste management, 74, 3-15. https://doi.org/10.1016/j.wasman.2017.11.057
  16. Kumar, A., Samadder, S.R., Kumar, N., & Singh, C. (2018). Estimation of the generation rate of different types of plastic wastes and possible revenue recovery from informal recycling. Waste Management, 79, 781-790. https://doi.org/10.1016/j.wasman.2018.08.045
  17. Kuritcyn, P., Anding, K., Linss, E., & Latyev, S. M. (2015, February). Increasing the safety in recycling of construction and demolition waste by using supervised machine learning, In Journal of Physics: Conference Series, 588(1), 012035.
  18. Lu, W., & Yuan, H. (2011). A framework for understanding waste management studies in construction. Waste management, 31(6), 1252-1260. https://doi.org/10.1016/j.wasman.2011.01.018
  19. Namoun, A., Hussein, B. R., Tufail, A., Alrehaili, A., Syed, T. A., & BenRhouma, O. (2022). An Ensemble Learning Based Classification Approach for the Prediction of Household Solid Waste Generation. Sensors, 22(9), 3506.
  20. Osisanwo, F. Y., Akinsola, J. E. T., Awodele, O., Hinmikaiye, J. O., Olakanmi, O., & Akinjobi, J. (2017). Supervised machine learning algorithms: classification and comparison. International Journal of Computer Trends and Technology (IJCTT), 48(3), 128-138.
  21. Qi, C., & Tang, X. (2018). Slope stability prediction using integrated metaheuristic and machine learning approaches: a comparative study. Computers & Industrial Engineering, 118, 112-122. https://doi.org/10.1016/j.cie.2018.02.028
  22. Poon, C. S., Ann, T. W., & Ng, L. H. (2001). On-site sorting of construction and demolition waste in Hong Kong. Resources, conservation and recycling, 32(2), 157-172. https://doi.org/10.1016/S0921-3449(01)00052-0
  23. Rosecky, M., Somplak, R., Slavik, J., Kalina, J., Bulkova, G., & Bednar, J. (2021). Predictive modelling as a tool for effective municipal waste management policy at different territorial levels. Journal of Environmental Management, 291, 112584.
  24. Song, Y., Wang, Y., Liu, F., & Zhang, Y. (2017). Development of a hybrid model to predict construction and demolition waste: China as a case study. Waste Management. 59, 350-361.
  25. Wang, J., Li, Z., & Tam, V. W. (2015). Identifying best design strategies for construction waste minimization. Journal of cleaner production, 92, 237-247. https://doi.org/10.1016/j.jclepro.2014.12.076
  26. Wu, H., Zuo, J., Zillante, G., Wang, J., & Yuan, H. (2019). Status quo and future directions of construction and demolition waste research: A critical review. Journal of Cleaner Production, 240, 118163.