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

Table 2

Validating RMSE and R² under varied feature preservation proportions.

proportion	0.20	0.25	0.30	0.35	0.40	0.45	0.50	0.55	0.60	0.65	0.70	1.00
RMSE	0.0423	0.0375	0.0336	0.0249	0.0327	0.0359	0.0391	0.0397	0.0423	0.0435	0.0468	0.0506
R^2	0.9692	0.9758	0.9805	0.9893	0.9816	0.9777	0.9736	0.9728	0.9691	0.9673	0.9621	0.9558

Best results are highlighted in bold font.