Research Article
Ensemble Classification Based on Feature Selection for Environmental Sound Recognition
Table 4
Accuracy of different feature selection methods at k = 1/2 of subsets on five classes.
| Methods | Bird | Wind | Rain | Frog | Thunder |
| Correlation | 0.607 | 0.7028 | 0.5915 | 0.5808 | 0.6705 | GainRatio | 0.6124 | 0.7206 | 0.5313 | 0.6646 | 0.703 | InfoGain | 0.6169 | 0.7606 | 0.5936 | 0.6458 | 0.705 | OneR | 0.6418 | 0.6923 | 0.5769 | 0.6433 | 0.7236 | ReliefF | 0.5743 | 0.7321 | 0.5604 | 0.5758 | 0.587 | SymmetricalUncert | 0.6119 | 0.7634 | 0.5909 | 0.6458 | 0.7015 | csFs | 0.6419 | 0.7012 | 0.5676 | 0.5914 | 0.7005 | MmEnFs1 | 0.765 | 0.79 | 0.695 | 0.655 | 0.765 | MmEnFs2 | 0.785 | 0.805 | 0.77 | 0.635 | 0.785 |
|
|