Research Article

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

Table 4

Adaptive neuro-fuzzy inference system (ANFIS) model.

Attribution functionMAPE (%)MAPE (%)
One-input: number of functionsTwo-input: number of functions
[2][3][4][5][2 2][3 3][4 4][5 5]

Trimf10.049.809.669.809.989.9410.0510.46
Trapmf10.2610.949.4810.0010.5210.9410.439.18
Gbellmf9.739.899.469.379.689.8910.409.56
Gaussmf9.7610.019.419.769.7710.8510.289.94
Gauss2mf9.7810.019.499.8810.1810.5410.2610.98
Pimf10.4810.5010.5010.5010.7310.6610.3110.49
Dsigmf10.159.979.469.6910.1110.5610.6710.58
Psigmf10.159.919.469.4310.1110.5710.6710.56
Trimf10.049.809.669.809.989.9410.0510.46
Trapmf10.2610.949.4810.0010.5210.9410.439.18