Skip to main content
Earth, Planets and Space

Table 5 The accuracy of CNN-SVM system (RBF kernel) with various filter sizes

From: Classification of the equatorial plasma bubbles using convolutional neural network and support vector machine techniques

 

Number of convolutional layers

Filter size

1

3

5

7

\(3\times 3\)

91.37

92.02

92.64

93.67

\(5\times 5\)

90.11

90.73

91.08

91.53

\(7\times 7\)

89.33

89.92

90.24

90.67

  1. The value in bold signifies the highest accuracy value achieved by using the RBF kernel
Back to article page