Table 3.

Table of test set predictions given by classifier trained on Scenario A using class availability labelling technique and class weighting (cf. Figure 7–Table 2 fourth row–Figure 11).

Id	Total labels	Unique label	Predictions
			PVI	FIBRO	ROTOR
P10_scenarioA	PVI	PVI	0.3201	0.2381	0.4418
P02_scenarioA	FIBRO,ROTOR	FIBRO	0.3596	0.5352	0.1052
OIR_scenarioA	PVI,FIBRO,ROTOR	PVI	0.2839	0.4492	0.2668
38C_scenarioA	FIBRO	FIBRO	0.1917	0.4070	0.4014
s_26F_scenarioA	PVI	PVI	0.3997	0.4124	0.1879
s_11F_scenarioA	ROTOR	ROTOR	0.2628	0.0759	0.6613
s_9F_scenarioA	PVI,FIBRO,ROTOR	PVI	0.3552	0.4212	0.2236
s_3I_scenarioA	PVI,FIBRO,ROTOR	PVI	0.4284	0.4216	0.1500
s_10F_scenarioA	FIBRO,ROTOR	FIBRO	0.3968	0.4015	0.2017
s_9G_scenarioA	FIBRO,ROTOR	FIBRO	0.3691	0.4409	0.1899
s_4I_scenarioA	FIBRO,ROTOR	FIBRO	0.4020	0.4162	0.1818
s_19F_scenarioA	PVI	PVI	0.4334	0.2922	0.2745

The Total Labels column contains all the successful strategies identified through the simulations, the Unique Label column shows the final ground truth label assigned based on class availability technique.

The Predictions column contains the classification output for each class.