Accesso libero

AtanK-A New SVM Kernel for Classification

 e   
31 dic 2021
INFORMAZIONI SU QUESTO ARTICOLO

Cita
Scarica la copertina

Fig. 1

Trends near the zero for AtanK kernel with different σ values.
Trends near the zero for AtanK kernel with different σ values.

Fig. 2

The trends near and far from the zero for Gauss, ERBF, UKF and AtanK kernels with different σ values.
The trends near and far from the zero for Gauss, ERBF, UKF and AtanK kernels with different σ values.

Fig. 3

Two-dimensional Checkerboard dataset and classification boundaries of 5 sets of kernels on Checkerboard dataset.
Two-dimensional Checkerboard dataset and classification boundaries of 5 sets of kernels on Checkerboard dataset.

Fig. 4

Boundary between domains of positive and negative samples corresponding to Cosexp dataset and the classification boundaries of 5 sets of kernels on Cosexp dataset.
Boundary between domains of positive and negative samples corresponding to Cosexp dataset and the classification boundaries of 5 sets of kernels on Cosexp dataset.

Fig. 5

Result of Friedman’s test of the testing accuracy.
Result of Friedman’s test of the testing accuracy.
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Scienze biologiche, Scienze della vita, altro, Matematica, Matematica applicata, Matematica generale, Fisica, Fisica, altro