Table 4 The performance comparison of the SVM and MLP classifiers for the MIT-BIH and SPH databases using the features PR, RT, age, and sex.
From: ECG-based machine-learning algorithms for heartbeat classification
MIT-BIH | SVM | MLP | ||||
|---|---|---|---|---|---|---|
Diseases | Precision | Recall | f1-Score | Precision | Recall | f1-Score |
Normal | 0.524 | 0.985 | 0.684 | 0.815 | 0.746 | 0.779 |
LBBB | 1.000 | 1.000 | 1.000 | 0.681 | 0.871 | 0.765 |
RBBB | 0.818 | 0.070 | 0.130 | 0.749 | 0.746 | 0.748 |
PACE | 1.000 | 1.000 | 1.000 | 0.868 | 0.833 | 0.851 |
PVC | 1.000 | 1.000 | 1.000 | 1.000 | 0.844 | 0.916 |
APC | 1.000 | 1.000 | 1.000 | 0.845 | 0.748 | 0.793 |
SPH | ||||||
AFIB | 0.666 | 0.580 | 0.620 | 0.883 | 0.782 | 0.830 |
SB | 0.746 | 0.818 | 0.780 | 0.879 | 0.898 | 0.889 |
SR | 0.957 | 0.992 | 0.974 | 0.941 | 0.988 | 0.964 |
GSVT | 0.842 | 0.818 | 0.830 | 0.895 | 0.899 | 0.897 |
