Published: Građevinar 70 (2018) 9
Paper type: Preliminary report
Download article (Croatian): PDF
Download article (English): PDF
Estimation of recycling capacity using ANN and SVM
Abstract
This paper presents estimation of the quantity of concrete and reinforcement that can be recycled for residential buildings constructed as skeleton structures. Models based on artificial intelligence, involving the use of Artificial Neural Networks (ANNs) and the Support Vector Machines (SVM) methods, were formed in order to estimate quantities of these materials. The results show that the application of ANNs and SVM methods is a good solution for the estimation of recycling capacity. The mean absolute percentage error (MAPE) for the selected ANNs for predicting quantity of concrete and reinforcement is 8.74 % and 12.58 %, respectively.
Keywordsbuildings, recycling, concrete, reinforcement, artificial neural networks, support vector machine method