Table 1.
Confusion Matrix.
Table 2.
Performance measures.
Figure 1.
Feature vector length versus accuracy, specificity and sensitivity.
The figure shows for different feature vector lengths, selected through the feature selection algorithm explained above, the average accuracy, sensitivity and specificity of the 10-fold CV. The model that uses 97 features (red dashed line) achieves the best accuracy of 82.04% while having a sensitivity of 76.45% and a specificity of 88.61%.
Table 3.
Cross-validation results.