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

Table 5

Testing prediction time consumed by three methods: CNN, CNN-L1, and mRMR-CNN.

Methods	CNN	CNN-L1	mRMR-CNN
Seconds per sample	6.0057 × 10^−5	6.0600 × 10^−5	6.0005 × 10^−5

Bold font indicates the best result, which indicates the shortest testing prediction time.