A Combination of Vision- and Sensor-Based Defect Classifications in Extrusion-Based Additive Manufacturing

Table 5

Performance metrics on vision-based machine learning model test sets.

Experiments	Model	Confusion matrix						Accuracy	Macro avg precision	Macro avg recall	Macro avg -score
Image classification	SW	15	0	0	0	0	0	0.899	0.794	0.833	0.811
		0	0	0	0	0	0
		0	0	25	0	0	0
		0	15	0	48	0	0
		0	0	0	0	30	0
		0	0	0	0	0	15
	SVM	12	0	0	0	0	3	0.899	0.794	0.833	0.811
		1	7	0	7	0	0
		0	0	24	1	0	0
		0	4	3	41	0	0
		0	0	0	0	30	0
		4	1	0	0	0	10
	DT	15	0	0	0	0	0	0.75	0.704	0.707	0.402
		1	6	1	6	0	1
		0	0	23	2	0	0
		0	7	3	36	0	2
		0	0	0	0	30	0
		2	0	0	10	0	3
	KNN	13	0	0	0	0	2	0.777	0.723	0.746	0.706
		3	3	5	4	0	0
		1	0	22	2	0	0
		3	2	5	38	0	0
		0	0	0	0	30	0
		4	0	0	2	0	9
	NB	1	0	3	11	0	0	0.635	0.484	0.678	0.429
		0	1	5	9	0	0
		0	0	25	0	0	0
		0	0	11	37	0	0
		0	0	0	0	30	0
		0	0	3	12	0	0