Table 7 Model hyperparameters.
From: Multi-level feature encoding algorithm based on FBPSI for heart sound classification
Modules | Hyperparameters |
|---|---|
DT | Fine Tree: A decision tree with detailed branching. Maximum Splits: 100. Splitting Criterion: Gini Diversity Index |
SVM | Quadratic Kernel Function: The kernel used is a quadratic. polynomial. Kernel Scale: Automatic. Box Constraint Level: 1. Multiclass Method: One-vs-One. Standardize Data: Yes |
KNN | Weighted KNN. Number of Neighbors: 10. Distance Metric: Euclidean. Distance Weight: Inverse Distance Squared. Standardize Data: Yes |
MNN | Wide Neural Network. Number of Fully Connected Layers: 1. First Layer Size: 100. Activation Function: ReLU. Iteration Limit: 1000. Regularization Strength (Lambda): 0. Standardize Data: Yes |
EBTC | Learner Type: Decision Tree. Number of Learners: 10 |
