Table 1 Parameter ranges for hybrid classifier optimization.
From: Detection of kidney bean leaf spot disease based on a hybrid deep learning model
Classifier | Parameter optimization | Values |
|---|---|---|
LR | Maximum number of iterations (m) | 1–100 |
penalty coefficient (\(\rho \)) | L2, None | |
RF | Number of trees (\(\gamma \)) | 2–500 |
Maximum depth (\(d\)) | 1–50 | |
Criterion (\(c\)) | Gini, entropy | |
ADB | Number of trees (\((\gamma \)) | 10–1000 |
Maximum depth (d) | 1–50 | |
Learning rate (c) | 0.0001–1 | |
Criterion (\(\gamma \)) | Gini, entropy | |
SGB | Number of trees (\(Y\)) | 10–1000 |
Maximum depth (\(d\)) | 1–20 | |
Learning rate (l) | 0.0001–1E | |
Subsample () | 0.1–1 |
