L2-norm multiple kernel learning and its application to biomedical data fusion

Table 9 Results of experiment 4 data set II: classification of miscarriage patients using multiple kernels derived from clinical data

Classifier	Mean - error of AUC	Std. - error of AUC	pvalue
SVM L ₂ MKL	0.1975	0.0037	-
LSSVM L ₂ MKL	0.2002	0.0049	0.0712
LSSVM L_∞ (0.5) MKL	0.2027	0.0045	9.77 · 10^-4
SVM L_∞ MKL	0.2109	0.0040	9.55 · 10^-12
SVM L_∞ (0.5) MKL	0.2168	0.0040	1.79 · 10^-12
LSSVM L₁ MKL	0.2132	0.0029	1.11 · 10^-13
SVM L₁ MKL	0.2297	0.0038	1.10 · 10^-15
LSSVM L_∞ MKL	0.2319	0.0015	3.42 · 10^-21

Results of experiment 4 data set II: classification of miscarriage patients using multiple kernels derived from clinical data. The classifier with the best performance is shown in bold. The p-values are compared with the best performance using a paired t-test. The performance of classifiers is sorted from high to low according to the p-values.