Skip to main content

Table 4 Interaction results on the hyperparameters of the encoder transformer model with its combinations

From: A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure

Algorithms

Numheads

Accuracy [%]

Layers

Accuracy [%]

CNN+Tf+Capsule-Net

1

85.26

1

86.74

 

2

84.43

2

84.91

 

4

84.78

4

86.26

 

8

86.91

8

85.70

 

16

85.74

16

85.04

CNN+Tf

1

86.30

1

86.00

 

2

87.22

2

82.30

 

4

84.96

4

87.30

 

8

87.13

8

86.35

 

16

87.57

16

85.39

CNN+Tf+Fully

1

86.30

1

87.09

 

2

86.57

2

85.43

 

4

85.61

4

86.22

 

8

85.57

8

84.48

 

16

86.74

16

86.22

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us