Applicability of Artificial Neural Networks to Predict Mechanical and Permeability Properties of Volcanic Scoria-Based Concrete

Table 4

Results obtained for MLR models.

Models	Evaluation criteria				Number of data set samples
	R^2	DW	RMSE	MAPE
MLR1	0.748	0.0259	6.11	20.922	367
MLR2	0.82	0.1566	4.39	52.3229	222
MLR3	0.829	0.1423	17.5	59.212	220

MLR1: compressive strength; MLR2: water permeability; MLR3: concrete porosity.