Table 1.

Original optimal weights of each classifier used for the training datasets at different time steps, namely, ${\beta }_i^j$.

Classifier/fi	Batch ID (The Mean Measurement Time in Months)/j (wj)
	1 (1.5)	2 (6.5)	3 (12)	4 (14.5)	5 (16)
f1	0.50	0.05	0.05	0.15	0.35
f2	0.10	0.55	0	0.05	0
f3	0.25	0.15	0.90	0.20	0
f4	0.15	0.10	0.05	0.50	0
f5	0	0.15	0	0.1	0.65