Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Quantification analysis and prediction model for residential building construction waste using machine learning technique

Quantification analysis and prediction model for residential building construction waste using... Prediction of construction waste is one of the successful techniques to reduce the amount of waste generation at source. Estimation of construction waste at each stage or phase of project is very essential to accurately compute and predict the total waste generation. The study aims to quantify the amount of construction waste at different stages of construction project so as to develop a machine learning model to accurately predict the amount of generated waste at various stages and from variable sources. About 134 construction sites were inspected to collect the generated waste data. As the construction activities are very dynamic in nature, it is very important to precisely compute the waste generation, to analyze the data prediction model, and enable to predict the sources and the amount of waste likely to generate. The decision tree and the K-nearest neighbors algorithm are used for analyzing, and the neural networks performance was studied by providing gross floor area and material estimation. The results indicate that an appreciable amount of waste is generated at every stage of project having considerable high cost, and a particular pattern has been observed for waste materials at typical stages of projects. The model has average RSME values of 0.49 which indicates the accuracy of model is satisfactory for use to perform the predictions. The combined average accuracy of the decision tree and KNN was found to be 88.32 and 88.51, respectively. These findings can provide basic data support and reference for the management and utilization of construction waste. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Asian Journal of Civil Engineering Springer Journals

Quantification analysis and prediction model for residential building construction waste using machine learning technique

Download PDF
15 pages

Loading next page...
 
/lp/springer-journals/quantification-analysis-and-prediction-model-for-residential-building-MSLPn4eedk

References (35)

Publisher
Springer Journals
Copyright
Copyright © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
ISSN
1563-0854
eISSN
2522-011X
DOI
10.1007/s42107-023-00580-x
Publisher site
See Article on Publisher Site

Abstract

Prediction of construction waste is one of the successful techniques to reduce the amount of waste generation at source. Estimation of construction waste at each stage or phase of project is very essential to accurately compute and predict the total waste generation. The study aims to quantify the amount of construction waste at different stages of construction project so as to develop a machine learning model to accurately predict the amount of generated waste at various stages and from variable sources. About 134 construction sites were inspected to collect the generated waste data. As the construction activities are very dynamic in nature, it is very important to precisely compute the waste generation, to analyze the data prediction model, and enable to predict the sources and the amount of waste likely to generate. The decision tree and the K-nearest neighbors algorithm are used for analyzing, and the neural networks performance was studied by providing gross floor area and material estimation. The results indicate that an appreciable amount of waste is generated at every stage of project having considerable high cost, and a particular pattern has been observed for waste materials at typical stages of projects. The model has average RSME values of 0.49 which indicates the accuracy of model is satisfactory for use to perform the predictions. The combined average accuracy of the decision tree and KNN was found to be 88.32 and 88.51, respectively. These findings can provide basic data support and reference for the management and utilization of construction waste.

Journal

Asian Journal of Civil Engineering – Springer Journals

Published: Sep 1, 2023

Keywords: Construction waste management; Quantification of waste and waste minimization; Machine learning; Prediction model

There are no references for this article.