Predicting modulus elasticity of recycled aggregate concrete using M5′ model tree algorithm

The use of recycled aggregates in concrete is on the rise, driven by economic and environmental concerns. However, most of the existing models to predict the value of elastic modulus of concrete were developed for virgin aggregates and, as a result, they may often be inaccurate when applied to concrete made with recycled aggregate. In this study, the M5' model tree algorithm was used to predict the elastic modulus of recycled aggregate concrete. The main advantages of the model tree algorithms are: (a) they output relatively simple mathematical models (formulas) and (b) are more convenient to develop and employ compared with other soft computing methods. To develop the model tree presented in this paper, over 450 data records were collected from internationally published literature. Error measures were used to compare the performance of the M5' algorithm output to the output from other existing models. The results showed that the model developed using the M5' algorithm has accuracy over 80 percent, which is well above the accuracy the other models. (C) 2015 Elsevier Ltd. All rights reserved.