Research Article
Automated Atrial Fibrillation Detection Based on Feature Fusion Using Discriminant Canonical Correlation Analysis
Table 3
Comparison of previous studies of ECG based on the PhysioNet/CinC challenge 2017 public dataset.
| Method | | | | | Acc | Spe | Sen |
| Convolutional recurrent neural network [23] | 92.4% | 81.4% | 80.9% | 84.9% | 87.5% | 94.6% | 82.9% | Decision tree ensemble [24] | 88.9% | 79.1% | 70.2% | 79.4% | —— | —— | —— | 16-layer 1D residual convolutional network [25] | 90.0% | 82.0% | 75.0% | 82.0% | 80.2% | —— | —— | 2D convolutional network with LSTM layer [26] | 88.8% | 76.4% | 72.6% | 79.2% | 82.3% | —— | —— | 1DCNN containing residual blocks and recurrent layers [27] | 91.9% | 85.8% | 81.6% | 86.4% | —— | —— | —— | Proposed in this paper | 93.1% | 88.3% | 84.0% | 88.3% | 91.7% | 93.2% | 90.4%% |
|
|