Geopolymer Concrete Compressive Strength via Artificial Neural Network, Adaptive Neuro Fuzzy Interface System, and Gene Expression Programming With K-Fold Cross Validation

The ultrafine fly ash (FA) is a hazardous material collected from coal productions, which has been proficiently employed for the manufacturing of geopolymer concrete (GPC). In this study, three artificial intelligence (AI) techniques, namely, neural network (ANN), adaptive neuro-fuzzy interface (ANFIS), and gene expression programming (GEP) are used to establish reliable accurate model estimate compressive strength (f′c) ash–based (FGPC). A database 298 instances developed peer-reviewed published work. consists ten most prominent explanatory variables id="minf2">f′c FGPC as response parameter. statistical error checks criteria suggested in literature considered verification predictive models. measures study MAE, RSE, RMSE, RRMSE, R, performance index id="minf3">(ρ) . These verify that ANFIS gives an outstanding followed by GEP ANN validation stage, coefficient correlation (R) ANFIS, GEP, 0.9783, 0.9643, 0.9314, respectively. All models also fulfill external criterion literature. Generally, ideal it delivers simplistic easy mathematical equation future use. k-fold cross-validation (CV) conducted, verifies robustness model. Furthermore, parametric carried via proposed expression. This confirms accurately covers influence all prediction id="minf4">f′c FGPC. Thus, can be preliminary design