Broad Learning System with Locality Sensitive Discriminant Analysis for Hyperspectral Image Classification

Table 1

Parameter settings of the proposed method for each dataset.

Dataset parameter	Indian pines	Pavia University	Salinas
H	3	3	3
C	5	5	5
S	10	10	10
N1	200	200	200
N2	30	30	30
N3	1000	1000	1000
	0.1	0.1	0.1
D	30	50	60
	5, 7, 9, 11, 13	5, 7, 9, 11, 13	5, 7, 9, 11, 13
f	5, 7, 9, 11, 13	5, 7, 9, 11, 13	5, 7, 9, 11, 13

h is the convolution depth of Gabor and AWF filters, and f are the neighborhood’s sizes of Gabor and AWF, respectively, is the weight of the spatial information in equation (15), d is the number of dimensions of reduced subspace in LSDA algorithm, C and s are penalty parameters and enhanced node scaling in BLS, and N1, N2, and N3 are the number of feature node groups, feature nodes per group, and enhanced nodes in BLS, respectively.