In the last three decades the soft computing methods were used by the research community in almost every branch of construction, providing successful and convenient solutions for different problems in civil engineering. This paper presents some of the applications of these methods - especially neural networks (NN) and support vector machine (SVM) - in sustainable construction, i.e. its economic, social and environmental aspects. Soft computing applications were made in the last several years by our research team at the Faculty of Civil Engineering in Skopje, N. Macedonia, in collaboration with other authors from our and other countries. Several predictive models were developed using: general regression neural network (GRNN), support vector machine (SVM) and radial basis function neural network (RBF NN), using predictive modelling software DTREG. Applications of these models cover most of the aspects of sustainability in construction. Models were focused on predicting: road structure construction costs, bidding price in construction, sustainability assessment at early facilities design phase, predicting construction cost and construction time and predicting consumption of energy in buildings. Some of the mentioned developed predictive models are hybrid, composed of process-based and data driven models which contributed very much to the improvement of the accuracy of the predicting. The general conclusion is that the soft computing methods are a useful tool for developing models in the area of all aspects of sustainability and their application can lead to increasing sustainability in construction.

Full document

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document
Back to Top

Document information

Published on 25/09/20
Submitted on 23/09/20

DOI: 10.23967/dbmc.2020.164
Licence: CC BY-NC-SA license

Document Score


Views 11
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?