Table 18.

Precision, recall and F1 scores for classifiers trained on data with different values of the cutoff c. Set A of features was used. All results are rounded to three decimal digits. For each data set, the support of the testing set is 12,000 trajectories per diffusion mode, giving 36,000 in total.

c Value	Measure	Normal Diffusion	Subdiffusion	Superdiffusion	Total/Average
	Precision	0.835	0.972	0.974	0.927
$c=0$	Recall	0.950	0.910	0.900	0.920
	F1	0.889	0.940	0.936	0.921
	Precision	0.842	0.975	0.972	0.930
$c=0.001$	Recall	0.952	0.915	0.906	0.924
	F1	0.894	0.944	0.938	0.925
	Precision	0.850	0.976	0.976	0.934
$c=0.01$	Recall	0.955	0.918	0.913	0.929
	F1	0.900	0.946	0.943	0.930
	Precision	0.929	0.973	0.970	0.957
$c=0.1$	Recall	0.944	0.966	0.962	0.957
	F1	0.936	0.969	0.966	0.957