Skip to main content

Table 1 Breakdown of Training, Validation, and Test Sets for the PhysioNet/Computing in Cardiology 2017 Dataset

From: Deep learning for the classification of atrial fibrillation using wavelet transform-based visual images

Condition

PhysioNet 2017 Dataset

Training (64%)

Validation (16%)

Test (20%)

Total (100%)

AF

459

115

144

718

Normal

3,160

790

987

4,937

Other

1,666

416

521

2,603

Noisy

97

24

30

151

Total

5,382

1,345

1,682

8,409