Table 4.

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

Ref	Prediction Model	Compared with	RMSE/MSE	MAXE	Best Performance
[43]	FNN Inverse System	PID control	-	-	FNN Inverse sys
[89]	GD-FNN		0.0064
		RBF-NN	0.0194		GD-FNN
[90]	MNN-KFCM		0.1963	-	MNN-MFKC
		Single NN	0.5441
[91]	FLS-SVM	LS-SVM	-	-	FLS-SVM
[92]	PSO-FNN		0.1141	0.6151	PSO-FNN
		FNN	1.3658	3.5640
[93]	Fuzzy LS-SVM		0.0097	-	Fuzzy LS-SVM
		LS-SVM	0.0244

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