Combined Kernel-Based BDT-SMO Classification of Hyperspectral Fused Images

Table 5

Comparison of classification results under different SMO multiclass classification approaches (zone 2).

Classification approaches	Overall accuracy (%)	Average accuracy (%)	Kappa coefficient	Training time (s)	Test time (s)	Standard deviation	Optimized parameters
OAO-SMO	81.57	81.79	0.7994	32.33	24.74	1.11	,
OAA-SMO	81.21	80.75	0.7837	31.64	26.75	1.21	,
DAG-SMO	82.31	80.79	0.8106	40.12	16.84	1.32	,
ECC-SMO	82.52	81.32	0.8153	43.35	16.01	1.33	,
BDT-SMO	84.05	83.37	0.8254	42.11	14.59	0.59	,