%0 Journal Article
%T The Use of Machine Learning Models in Estimating the Compressive Strength of Recycled Brick Aggregate Concrete
%J Computational Engineering and Physical Modeling
%I Pouyan Press
%Z 2588-6959
%A Khademi, Atefehossadat
%A Behfarnia, Kiachehr
%A Kalman Šipoš, Tanja
%A Miličević, Ivana
%D 2021
%\ 10/01/2021
%V 4
%N 4
%P 1-25
%! The Use of Machine Learning Models in Estimating the Compressive Strength of Recycled Brick Aggregate Concrete
%K Concrete
%K cement
%K Compressive strength
%K ANFIS
%K Artificial Neural Network
%K Regression
%R 10.22115/cepm.2021.297016.1181
%X The focus of this study is to investigate the applicability of Adaptive Neuro-Fuzzy Inference System (ANFIS), Artificial Neural Network (ANN), and Multiple Linear Regression (MLR) in modeling the compressive strength of Recycled Brick Aggregate Concrete (RBAC). A comparative study on the application of the aforementioned models is developed based on statistical tools such as coefficient of determination, mean absolute error, root mean squared error, and some others, and the application potential of each of these models is investigated. To study the effects of RBAC factors on the performance of representative data-driven models, the Sensitivity Analysis (SA) method is used. The findings revealed that ANN with R2 value of 0.9102 has a great application potential in predicting the compressive strength of concrete. In the absence of ANN, ANFIS with R2 value of 0.8538 is also an excellent substitute for predictions. MLR was shown to be less effective than the preceding models and is only recommended for preliminary estimations. In addition, Subsequent sensitivity analysis on the database indicates the reliability of the prediction models have a strong correlation to the number of input parameters. The application of ANN and ANFIS as a precursor to traditional methods can eliminate the need for old-style tests, thus, constituting a significant reduction in time and expense needed for design and/or repairs.
%U http://www.jcepm.com/article_136944_9225826aecc887623dcecdf80b592eea.pdf