Table 6.

Precision, recall and F1 scores of the classifiers trained on base synthetic data with Set A of features. For each classifier, the testing set consists of 12,000 trajectories per diffusion mode—that is, 36,000 in total. All classifiers were built on base data set with Set A of features.

Method	Variant	Measure	Normal Diffusion	Subdiffusion	Superdiffusion	Total/Average
RF		Precision	0.929	0.973	0.970	0.957
	with D	Recall	0.944	0.966	0.962	0.957
		F1	0.936	0.969	0.966	0.957
		Precision	0.922	0.971	0.971	0.955
	no D	Recall	0.943	0.963	0.958	0.955
		F1	0.933	0.967	0.964	0.955
GB		Precision	0.928	0.972	0.970	0.956
	with D	Recall	0.942	0.966	0.961	0.956
		F1	0.935	0.969	0.965	0.956
		Precision	0.925	0.970	0.969	0.955
	no D	Recall	0.940	0.964	0.960	0.955
		F1	0.932	0.967	0.965	0.955