Table 1 Classification results for 52 sound types using the TensorFlowLite model.

From: Animal-borne soundscape logger as a system for edge classification of sound sources and data transmission for monitoring near-real-time underwater soundscape

Top1

 

Recall (%)

Precision (%)

F-measure (%)

 

Level 1

85.8

82.1

82.2

 

Level 2

73.1

75

65.1

 

Level 3

43.7

52.7

41.8

Top5

 

Recall (%)

Precision (%)

F-measure (%)

 

Level 1

95.4

92.5

93.7

Level 2

95

89.6

91.4

Level 3

74.5

85.4

75.0

  1. Refer to Supplementary Table 1 for classes at each level.
Back to article page