Abstract
Compressive strength of concrete is an important parameter in concrete design. Accurate prediction of compressive strength of concrete can lower costs and save time. Therefore, thecompressive strength of concrete prediction performance of artificial intelligence methods (adaptive neuro fuzzy inference system, random forest, linear regression, classification and regression tree, support vector regression, k-nearest neighbour and extreme learning machine) are compared in this study using six different multinational datasets. The performance of these methods is evaluated using the correlation coefficient, root mean square error, mean absolute error, and mean absolute percentage error criteria. Comparative results show that the adaptive neuro fuzzy inference system (ANFIS) is more successful in all datasets.
Highlights
Concrete is the most extensively used construction material in the world due to its various advantages
R, root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) metrics were used for model performance comparisons
The highest prediction accuracy was obtained with the adaptive neuro fuzzy inference system (ANFIS) method according to all evaluation metrics for all datasets
Summary
Concrete is the most extensively used construction material in the world due to its various advantages. Topçu and Sarıdemir [4] and Başyiğit et al [6] used artificial neural networks and fuzzy logic models for predicting compressive strength of concrete containing fly ash. Sarıdemir [5] compared artificial neural networks and fuzzy logic models for prediction of compressive strength of mortars containing metakaolin at the age of 3, 7, 28, 60, and 90 days. Sarıdemir [7] developed two models in the gene expression programming (GEP) approach for the prediction of compressive strength of concrete containing rice husk ash at the age of 1, 3, 7, 14, 28, 56 and 90 days. Atici [26] used multiple regression analysis and an artificial neural network to predict compressive strength of concrete containing various amounts of supplementary materials (blast furnace slag and fly ash) at different curing times (3, 7, 28, 90, and 180 days). The correlation coefficient (R), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and P-value criteria are used to evaluate the success of AI methods used in this study
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of the Croatian Association of Civil Engineers
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
