Applying Adaptive Neural Fuzzy Inference System to Improve Concrete Strength Estimation in Ultrasonic Pulse Velocity Tests

Table 6

Comparison of ANFIS, ANN, linear, and nonlinear regression model prediction accuracy.

Forecasting model		Prediction formula and parameter setting	Standard deviation	Single entry (MAPE %)
Linear regression			16.80	11.17
Nonlinear regression			23.13	17.66
AI	ANN test	Network type (1-3-1)	16.42	10.94
	ANFIS test	The number of functions: 5	13.90	9.86
		Function type: Gbellmf

is the compressive strength and is the average wave speed.