An Efficient Feature Selection Method for Video-Based Activity Recognition Systems

Table 2

Accuracy of the designed approach with the wrapper method on depth database.

Activities	BD	JK	PJU	RUN	SMO	SKI	WAK	1HW	2HW	JU	CL	BOX	SS
BD	80	0	2	1	0	2	0	2	0	1	0	2	0
JK	2	77	1	2	2	2	4	1	2	2	2	1	2
PJU	1	2	81	2	1	1	2	1	2	2	1	2	2
RUN	2	2	1	78	4	2	1	2	1	1	1	4	1
SMO	1	1	3	2	76	3	2	2	4	2	1	1	2
SKI	0	2	2	1	2	83	1	2	1	2	1	2	1
WAK	2	1	0	2	1	2	85	1	2	0	2	1	1
1HW	2	2	1	2	1	2	3	79	1	2	1	2	2
2HW	1	2	2	1	2	1	1	2	82	1	2	1	2
JU	2	1	1	2	1	2	2	1	2	83	1	2	0
CL	1	2	2	1	2	1	1	0	2	2	85	0	1
BOX	2	2	3	1	2	2	1	2	4	1	2	77	1
SS	1	2	2	4	1	2	3	1	2	2	3	2	75
Average	80.1%