Skip to main content
EURASIP Journal on Advances in Signal Processing

Table 9 Performance comparison between the proposed work (Lwin = 128, OP = 75%, SG feature) and state-of-the-art works as quadruple classifiers based on ICBHI 2017

From: Performance evaluation of lung sounds classification using deep learning under variable parameters

Works

Sen (%)

Spe (%)

Pre (%)

Acc (%)

F1_score (%)

Petmezas et al. [12]

52.78

84.26

–

76.39

68.52

Acharya et al. [28]

48.63

84.4

–

–

–

Jayalakshmy et al. [32]

–

–

–

92.5

–

Asatani et al. [33]

63

83

–

–

72

Rishabh et al. [38]

67.22

82.87

–

–

75.04

Jakovljević et al. [41]

–

–

–

–

39.56

proposed work

88.3

87.5

94.4

88.7

91.2

  1. The optimum values of performance criteria are highlighted in bold
  2. Acc accuracy, Sen sensitivity or recall, Pre precision, Spe specificity
Back to article page