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

Table 5

Accuracy of the designed approach with greedy forward selection on depth database.

Activities	BD	JK	PJU	RUN	SMO	SKI	WAK	1HW	2HW	JU	CL	BOX	SS
BD	75	2	1	2	4	2	1	6	2	1	2	2	0
JK	2	77	1	2	2	2	4	1	2	2	1	2	2
PJU	1	2	80	1	0	2	2	1	1	2	2	4	2
RUN	2	1	2	78	2	1	1	4	2	1	3	2	1
SMO	0	2	1	2	85	2	2	0	1	2	0	2	1
SKI	4	1	1	2	4	75	1	2	1	2	1	3	3
WAK	1	2	6	1	3	2	73	2	2	1	4	2	1
1HW	2	4	2	2	1	2	3	77	1	2	1	1	2
2HW	1	2	1	2	2	1	2	2	83	1	2	1	0
JU	2	1	1	3	1	2	0	1	2	82	2	2	1
CL	0	2	2	1	2	1	2	2	1	2	84	0	1
BOX	2	2	1	1	6	2	1	4	2	1	0	76	2
SS	1	1	2	4	1	3	2	2	1	2	1	1	79
Average	78.8%