Table 12 Impact of weight distribution on ensemble learning for bird species classification.

From: Enhancing occluded and standard bird object recognition using fuzzy-based ensembled computer vision approach with convolutional neural network

S.No

Ablation components

Standard bird objects

Occluded bird objects

DenseNet121

DenseNet169

ResNet101V2

A

(%)

FS

(%)

A

(%)

FS

(%)

1

Weight = 0.3

Weight = 0.3

Weight = 0.4

97.56

97.58

94.77

94.37

2

Weight = 0.2

Weight = 0.2

Weight = 0.6

96.88

96.84

93.41

92.89

3

Weight = 0.2

Weight = 0.3

Weight = 0.5

96.89

96.85

92.14

91.46

4

Weight = 0.3

Weight = 0.2

Weight = 0.5

96.96

96.92

93.41

92.72

  1. A: Accuracy, FS: F1-Score.