Table 3.

Comprehensive analysis of soft sensor models based on NN/ANN (for the list of abbreviations see Table A1).

Ref	Prediction model	Compared with	RMSE/MSE	MAXE	Best Performance
[31]	NN-MIV		27.512	-	NN-MIV
		NN	37.943
[61]	GPR-NN MIV		0.0436	0.1440	GPR-NN-MIV
		GPR	0.1082	0.4373
[23]	RBF-NN	BP	-	-	RBF-NN
[62]	PSO-NN	BPNN	-	-	PSO-NN
[65]	Novel SS ANN	General SS-ANN	-	-	Novel SS-ANN
[66]	GRNN	RBF-NN	-	-	GRNN
[67]	KPCA-RBF-NN	PCA	-	-	KPCA-RBF-NN

Ref - References, RMSE – Root Mean Square Error, MAXE –Maximum Absolute Error, MSE – Mean Square Error.