Recognition of Mixture Control Chart Pattern Using Multiclass Support Vector Machine and Genetic Algorithm Based on Statistical and Shape Features

Table 7

Recognition accuracies with the BP model.

True pattern	Identified pattern (%)
	NOR	CYC	IT	DT	US	DS	CT	CS	TS	CTS
NOR	90	8	0	2	0	0	0	0	0	0
CYC	4	88	4	2	2	0	0	0	0	0
IT	0	0	56	32	10	2	0	0	0	0
DT	0	6	24	32	12	26	0	0	0	0
US	0	0	8	28	34	30	0	0	0	0
DS	0	0	0	2	10	74	10	2	2	0
CT	0	0	0	0	8	24	66	0	0	2
CS	0	0	0	0	0	0	22	78	0	0
TS	0	0	0	0	0	0	2	10	84	4
CTS	0	2	0	2	6	2	0	14	16	58
Average	65.2