Skip to main content
. 2019 Jan 10;19(2):242. doi: 10.3390/s19020242

Table 10.

Global confusion matrix obtained using the different classifiers in the case of the Frenkel-Toledo et al. sub-dataset.

Obtained Classes
Supervised Unsueprvised
K-NN CART RF NB SVM K-Means GMM
Healthy PD Healthy PD Healthy PD Healthy PD Healthy PD Healthy PD Healthy PD
True Healthy 86.21% 13.79% 75.86% 24.14% 75.86% 24.14% 82.76% 17.24% 86.21% 13.79% 80.97% 19.03% 57.24% 42.76%
Classes PD 22.86% 77.14% 17.14% 82.86% 11.43% 88.57% 22.86% 77.14% 20.00% 80.00% 62.51% 37.49% 28.00% 72.00%