Table 7 SVMR model parameters.

From: Estimating apple tree canopy chlorophyll content based on Sentinel-2A remote sensing imaging

Degree

Gamma

Coef0

Nu

Epsilon

Cashesize

Cost

Shrinking

Prob

P

3

0.5

0.001

0.5

0.001

100

1

1

1

0.01

  1. Note: Degree: set degree in kernel function; Gamma: set gamma in kernel function; Coef0: set coef0 in kernel function; Nu: set the parameter nu of nu-SVC, one-class SVM, and nu-SVR; Epsilon: set tolerance of termination criterion; Cashesize: set cache memory size in MB; Cost: set the parameter C of C-SVC, epsilon-SVR, and nu-SVR; Shrinking: whether to use the shrinking heuristics, 0 or 1; Prob: whether to train a SVR model for probability estimates, 0 or 1; P:set the epsilon in loss function of epsilon-SVR.
Back to article page