Skip to main content

Advertisement

Table 3 Results of the different numbers of convolution layers in 1D CNNs

From: Feature extraction and classification of heart sound using 1D convolutional neural networks

Different layersConvolutional kernel shapeAccuracy rate (%)F-score (%)
3 layers1×1394.3296.02
5 layers 95.2197.31
3 layers1×2695.1296.87
5 layers 96.3398.65
3 layers1×3996.0196.54
5 layers 99.0199.10
3 layers1×5293.3194.26
5 layers 94.2494.89
3 layers1×6592.0394.01
5 layers 94.3295.23