Table 4.

Sample confusion matrices of the classification results of MLR classifier using selected features with tolerance value = 0.01 and a sampling rate of (a) $\alpha =0.1$, (b) $\alpha =0.2$, and (c) $\alpha =0.3$.

	NO	NW	IR	OR	RE	CA
NO	80	0	0	0	0	0
NW	0	80	0	0	0	0
IR	0	0	80	0	0	0
OR	0	0	0	80	0	0
RE	0	0	1	0	79	0
CA	0	0	0	0	0	80
(a)
	NO	NW	IR	OR	RE	CA
NO	80	0	0	0	0	0
NW	0	78	0	0	0	2
IR	0	0	80	0	0	0
OR	0	0	0	80	0	0
RE	0	0	0	0	80	0
CA	0	0	0	0	0	80
(b)
	NO	NW	IR	OR	RE	CA
NO	80	0	0	0	0	0
NW	0	80	0	0	0	0
IR	0	0	80	0	0	0
OR	0	0	0	80	0	0
RE	0	0	0	0	80	0
CA	0	0	0	0	0	80
(c)