Prediction of Compressive Strength of Concrete Using the Spearman and PCA-Based BP Neural Network

Table 6

Comparison of the prediction errors of the two models.

Compare indicators	Spearman and PCA optimized BP model	Nonoptimized BP model
Mean value error	0.29 MPa	1.60 MPa
Variance	3.16 MPa	8.48 MPa
Standard deviation	1.77 MPa	2.91 MPa
Mean square error (MSE)	2.77	8.5
Root mean-squared errors (RMSE)	1.66 MPa	2.92 MPa
Mean absolute error (MAE)	1.30 MPa	2.30 MPa
Mean absolute percentage error (MAPE)	2.78%	4.82%
Root mean square (RMS)	48.66 MPa	50.01 MPa
Mean observation	48.30 MPa	48.30 MPa