Features Extraction of Flotation Froth Images and BP Neural Network Soft-Sensor Model of Concentrate Grade Optimized by Shuffled Cuckoo Searching Algorithm

Table 2

Performance comparison under different training methods.

Predictive method	MSE	RMSE	NMSE	SSE	MAPE
MO-BP	0.5245	0.7242	0.0328	26.2236	0.8617
VL-BP	0.4987	0.7062	0.0320	24.9357	0.8232
LM-BP	0.0558	0.2362	0.0107	2.7897	0.2570
CSA-BP	0.0390	0.1976	0.0004	1.9521	0.1897
SCSA-BP	0.0146	0.1207	0.0003	0.7282	0.0993