The weight [lambda] is used to balance the effect of the spectral radial kernel (SPRBF) and the textural weighted radial basis function kernel (WRBF) in CRBF. When [lambda] is close to 1, SPRBF is dominant in CRBF; otherwise, WRBF is dominant.
Thus the parameter optimization strategy for CRBF is of great importance.
In this work, GA was first used to obtain the kernel parameters of SRBF (including parameters C and [delta]) and CRBF (including parameters C, [lambda], [[delta].sub.s], and [[delta].sub.w]).
In addition, CRBF has the fastest training speed second only to SRBF and the fastest test speed.
To more intuitively show the benefit of CRBF for classification of [C.sub.3], [C.sub.5], [C.sub.8], and [C.sub.10], 4 instances are selected, respectively, from the two zones for verification.
In order to improve the accuracy and efficiency of the classification of hyperspectral fused images, a new combined radial basis kernel function (CRBF) is proposed by combining spectral and textural features in a weighted manner.
CRBF, or Co-Operation Retirement Benefit Fund, made an irrevocable undertaking which could not be withdrawn if a higher offer was made, nevada said.
Nevada added that CRBF would own around 84 pecent of Stentor's share capital if convertible preferred shares were converted and all warrants exercised.