Research Article
Feature Selection for Interpatient Supervised Heart Beat Classification
Table 4
Classification performances of the two feature selection methods compared to previously reported feature choices.
| Model | Feature selection | Features | BCR | | | | |
| wLDA | [4] | 50 | 73.83% | 88.63% | 44.66% | 80.58% | 81.44% | wLDA | Wrapper wLDA | 2 | 73.00% | 81.88% | 70.53% | 70.77% | 68.81% | wSVM | Ranking MI | 6 | 82.99% | 75.88% | 82.63% | 85.06% | 88.40% | wSVM | [1] | 36 | 71.55% | 77.54% | 42.86% | 79.19% | 86.60% |
|
|