Research Article
A Two-Level Sound Classification Platform for Environmental Monitoring
Table 3
Summary of classification performance of neural network with selected features: second-level classification, one-step Implementation.
| | Scalar features | MFCCs | Spectrogram coefficients | Scalar features + MFCCs | Scalar features + spectrogram coefficients | MFCCs + spectrogram coefficients | Scalar features + MFCCs + spectrogram coefficients |
| Average correct classifications | 80.07% | 79.55% | 66.99% | 85.34% | 85.67% | 75.77% | 85.98% | Standard deviation of correct classifications | 26.45% | 23.77% | 26.00% | 23.38% | 21.69% | 23.42% | 22.74% | Number of features/hidden layer nodes | 12/24 | 26/40 | 64/95 | 38/60 | 76/110 | 90/100 | 102/140 |
|
|