Table 3.

Result of the machine learning process of test and validation data.

Model	Error	GWC		CGC		CWC		SNR-CSF		SNR-GM		SNR-WM
		test	val	test	val	test	val	test	val	test	val	test	val
svm	rrse	0.45		0.8		0.77		0.28		0.47	0.49	0.53	0.52
	rmse	0.14		5.04		4.06		15.3		11.5	10.8	9.01	7.75
	rsle	0.06		0.39		0.42		0.17		0.55	0.53	0.51	0.46
knn	rrse	0.43	0.43	0.38	0.36	0.38	0.41	0.19	0.43	0.52		0.58
	rmse	0.13	0.13	2.38	2.5	2.01	2.48	10.7	22.3	12.8		9.88
	rsle	0.05	0.05	0.25	0.3	0.25	0.25	0.21	0.25	0.48		0.45
ranfor	rrse	0.80		0.76		0.72		0.76		0.87		0.88
	rmse	0.25		4.84		3.76		41.7		21.3		14.9
	rsle	0.1		0.46		0.44		0.48		0.80		0.7
		Ghost		Sharpness		Homogeneity		Motion		Distortion		Time
		test	val	test	val	test	val	test	val	test	val	test	val
svm	rrse	0.53		0.32	0.29	0.75	0.69	0.5	0.48	0.11	0.11	0.54
	rmse	0.05		0.02	0.02	0.01	0.01	0.03	0.03	0.00	0.01	5.5e6
	rsle	0.04		0.01	0.01	0.01	0.01	0.02		0.03	0.01	-
knn	rrse	0.45	0.61	0.52		0.76		0.73		0.18		0.58	0.46
	rmse	0.04	0.04	0.03		0.01		0.04		0.01		2.7e6	2.5e6
	rsle	0.02	0.04	0.18		0.01		0.04		0.01		1.21	-
ranfor	rrse	0.96		0.64		0.85		0.89		0.49		0.88
	rmse	0.08		0.04		0.01		0.49		0.03		4.1e6
	rsle	0.07		0.02		0.01		0.04		0.03		2.3

Bold values indicate hyperparameter sets and ML models chosen for training based on error metrics.