Table 2.

Performance of the proposed algorithm under different values of $\gamma$.

Dataset	Metric	0.1	0.15	0.2	0.25	0.3
Tawsifur	Noise number	21	21	38	56	118
	RE (%)	89.18	89.18	80.41	71.13	39.18
	OA (%)	99.36	99.50	97.86	96.79	91.86
Skytells	Noise number	20	26	36	53	108
	RE (%)	90.70	87.91	83.26	75.35	49.77
	OA (%)	99.48	98.82	97.25	95.41	94.36
CXRs	Noise number	91	70	60	58	120
	RE (%)	47.09	59.30	65.12	66.28	30.23
	OA (%)	80.57	82.86	85.14	89.55	76.57

Note: bold numbers represent the best results. Experimental results of NLA are as follows: Noise number = 194, OA = 71.36 % (Tawsifur dataset); Noise number = 215, OA = 68.66 % (Skytells dataset); Noise number = 172, OA = 60.82 % (CXRs dataset).