Forecasting of sports fields construction costs aided by ensembles of neural networks
Authors:
- Michał Juszczyk,
- Krzysztof Zima,
- Wojciech Lelek
Abstract
The paper presents an original approach to construction cost analysis and development of predictive models based on ensembles of artificial neural networks. The research was focused on the application of two alternative approaches of ensemble averaging that allow for combining a number of multilayer perceptron neural networks and developing effective models for cost predictions. The models have been developed for the purpose of forecasting construction costs of sports fields as a specific type of construction objects. The research included simulation and selection of numerous neural networks that became the members of the ensembles. The ensembles included either the networks of different types in terms of their structure and activation functions or the networks of the same type. The research also included practical implementation of the developed models for cost analysis based on a sports field BIM model. This case study examined and confirmed all of the four models’ predictive capabilities and superiority over models based on single networks for the particular problem. Verification including testing and the case study enabled selection of the best ensemble-based model that combined ten networks of different types. The proposed approach is prospective for fast cost analyses and conceptual estimates in construction projects.
- Record ID
- CUT7a47e1575f704d08b28f4fe8823c26ca
- Publication categories
- ;
- Author
- Journal series
- Journal of Civil Engineering and Management, ISSN 1392-3730, e-ISSN 1822-3605
- Issue year
- 2019
- Vol
- 25
- No
- 7
- Pages
- 715-729
- Other elements of collation
- fot.; plany; rys.; schem.; tab.; wykr.; Bibliografia (na s.) - 727-729; Oznaczenie streszczenia - Abstr.; Numeracja w czasopiśmie - Vol. 25, No. 7
- Keywords in English
- construction cost management, conceptual estimates, neural networks, ensembles, artificial intelligence, building information modelling, sport fields
- DOI
- DOI:10.3846/jcem.2019.10534 Opening in a new tab
- URL
- https://journals.vgtu.lt/index.php/JCEM/article/view/10534 Opening in a new tab
- Language
- eng (en) English
- License
- Score (nominal)
- 70
- Additional fields
- Indeksowana w: Web of Science
- Uniform Resource Identifier
- https://cris.pk.edu.pl/info/article/CUT7a47e1575f704d08b28f4fe8823c26ca/
- URN
urn:pkr-prod:CUT7a47e1575f704d08b28f4fe8823c26ca
* presented citation count is obtained through Internet information analysis, and it is close to the number calculated by the Publish or PerishOpening in a new tab system.