Prediction of concrete mechanical properties using electrical resistivity: an ANFIS based soft computing approach

● The effects of concrete grade, specimen age, and electrical resistivity on compressive, flexural, and tensile strengths were examined experimentally.

● A lower mean deviation and a lower root mean square error (RMSE) value were obtained by the adaptive neuro-fuzzy inference system (ANFIS).

● Regression models with nonlinear and linear interaction terms were proposed to predict the mechanical properties of concrete with high R² values greater than 0.94.

● Additional datasets were used to validate the models, which showed accuracy with an average error of less than 10% when compared to experimental results.