Combining Dissimilarities in a Hyper Reproducing Kernel Hilbert Space for Complex Human Cancer Prediction

Table 2

Accuracy for the 𝜈-SVM using a linear combination of non-Euclidean dissimilarities in an HRKHS. The 𝜈-SVM based on the best distance and coordinates and the Lanckriet formalism have been taken as a reference.

Technique	Limphoma	Limphoma cell B	Breast LN	Brain
𝜈-SVM (coordinates)	6.66%	7.14%	8.16%	16.6%
𝜈-SVM (best distance)	6.66%	5.71%	8.16%	13.3%
𝜈-SVM (nonlinear kernel)	6.25%	5.71%	8.16%	11.6%
Lanckriet (finite family)	5%	7.62%	8.16%	11.67%
Finite family of distances	5%	7.14%	10%	10%
Infinite family of distances	5%	5.71%	8%	8.33%