Data-Driven Quality Prediction of Batch Processes Based on Minimal-Redundancy-Maximal-Relevance Integrated Convolutional Neural Network

Table 4

Testing RMSE and R² of different methods.

Methods	SVR	BP	AE	SAE	CNN	CNN-L1	mRMR-CNN
RMSE	0.0735	0.0495	0.0407	0.0614	0.0506	0.0359	0.0249
R^2	0.9071	0.9579	0.9716	0.9351	0.9558	0.9778	0.9893

Bold indicates the lowest RMSE value and highest R² value.