Preliminary communication

https://doi.org/10.14256/JCE.3066.2020

Comparison of artificial intelligence methods for predicting compressive strength of concrete

Mehmet Timur Cihan

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.

Keywords

artificial intelligence; regression; ANFIS; concrete compressive strength; multinational data

Hrčak ID:

260821

URI

https://hrcak.srce.hr/260821

Publication date:

22.7.2021.

Article data in other languages: croatian

Visits: 1.500 *