Table 2 Calinski-Harabasz index for all subjects’ Fusion features before and after Fusion Dimensionality reduction with t-SNE, PCA and KPCA.

From: Method for EEG signal recognition based on multi-domain feature fusion and optimization of multi-kernel extreme learning machine

Subject

Calinski-Harabasz index

 

Before

After t-SNE

After PCA

After KPCA

S1

13.56

18.45

17.79

25.56

S2

15.06

21.63

20.58

35.95

S3

6.87

10.39

12.86

15.29

S4

15.93

21.76

23.32

28.04

S5

6.85

9.89

9.16

15.82

S6

6.72

11.67

11.42

16.61

Mean

10.83

15.63

15.85

22.88

Back to article page