Table 1 The hyperparameters of classifiers.
Classifier | Hyperparameters |
|---|---|
kNN | Number of neighbors, distance metric (Euclidean, Mahalanobis, cubic, cosine), weighting scheme (equal, inverse, squared inverse) |
SVM | Kernel type (linear, quadratic, cubic, Gaussian), box constraint, kernel scale (only for Gaussian) |
Decision tree | Maximum number of splits |
Random forest | Minimum number of leaf sizes and number of predictors to sample |
