Table 3 Hyperparameter tuning experiment for classification task model.

From: A machine learning approach for vocal fold segmentation and disorder classification based on ensemble method

Serial number

Parameter

Search space

Selected value

1

Kernel

[\(3 \times 3, 5 \times 5\)]

\(3 \times 3\)

2

Padding

[Same, valid]

Same

3

Pool

[Max]

Max

4

Num_layer

[3, 31, 42]

3

5

Max_depth

[7, 11, 5, 3]

7

6

n_estimators

[12, 13]

12

7

Learning rate

[0.1, 0.2, 0.3]

0.2

8

Objective

[Multiclass]

Multiclass

9

Min_child_weight

[0.0001, 0.0002]

0.0001

10

Min_split_gain

[0.1, 0.2, 0.3]

0.3

11

Random_state

[42, 69]

42

Back to article page