BUPNN: Manifold Learning Regularizer-Based Blood Usage Prediction Neural Network for Blood Centers

Table 5

Median classification ACC comparison with the baseline methods for different hospitals’ all data, the best result are shown in bold. The second result is italicised. The brackets at the right end show how much BUPNN exceeds the optimal metrics in the other methods.

	KNN	RF	ET	MLP	GB	LGBM	SVMVC	ADB	BUPNN
DYang	1.000	1.000	0.571	0.723	0.786	0.714	0.857	0.929	1.000 (0.000)
SYi	1.000	0.667	1.000	1.000	1.000	0.667	1.000	1.000	1.000 (0.000)
SYiFu	0.796	0.778	0.815	0.735	0.556	0.593	0.630	0.778	0.926 (0.111)
WLing	0.500	1.000	0.750	0.250	1.000	1.000	1.000	1.000	1.000 (0.000)
ZEr	0.748	0.800	0.743	0.786	0.707	0.833	0.828	0.801	0.834 (0.001)
Average	0.765	0.834	0.764	0.698	0.775	0.750	0.833	0.854	0.909 (0.055)