Skip to main content

Table 4 Performance outcome of the k-nn Classifier for bipolar-normalised data

From: A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals

K value

Validation method

Classification accuracy (%)

Validation method

Classification accuracy (%)

1

Conventional validation

97.53 ± 0.29

Ten-fold-cross validation

98.26 ± 0.32

2

97.62 ± 0.58

97.11 ± 0.75

3

97.56 ± 1.25

97.52 ± 0.97

4

96. 23 ± 1.36

97.67 ± 0.46

5

96.92 ± 2.54

97.53 ± 0.48

6

95.25 ± 1.27

97.82 ± 0.62

7

95.51 ± 1.58

96.65 ± 0.96

8

95.88 ± 1.69

96.41 ± 1.19

9

95.88 ± 0.58

96.65 ± 1.36

10

95.14 ± 1.69

96.25 ± 0.85