Table 4 Comparison with other methods.

From: Underwater vessel sound recognition based on multi-layer feature and attention mechanism

Number

Methods

Accuracy

Precision

Recall

F1-score

1

Baseline22

0.754

–

–

–

2

ResNet18 with 3-D future12

0.943

0.943

0.943

0.943

3

CRNN-9 with 3-D Mel15

0.946

–

–

–

4

3DSNet16

0.935

0.935

0.935

0.930

5

ResNet_cDCGAN26

0.963

0.965

0.963

0.964

6

Our method

0.982

0.980

0.979

0.980

  1. Bold font represents the best performance among various evaluation indicators.
Back to article page