Research Article
Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants
Table 2
Performance comparison of various classifiers with and without feature selection.
| Feature selection | Performance metrics | Machine learning algorithms | SVM | NB | MLP | RF | KNN |
| Yes | Accuracy (%) | 81.11 | 77.78 | 78 | 80 | 77.78 | Kappa statistics | 0.72 | 0.62 | 0.65 | 0.66 | 0.61 | Root mean square error | 0.17 | 0.26 | 0.27 | 0.25 | 0.26 |
| No | Accuracy (%) | 64.40 | 75.50 | 73.00 | 72.22 | 62.22 | Kappa statistics | 0.52 | 0.58 | 0.47 | 0.47 | 0.21 | Root mean square error | 0.22 | 0.19 | 0.18 | 0.18 | 0.20 |
|
|