Research Article
Deep Denoising Autoencoding Method for Feature Extraction and Recognition of Vehicle Adhesion Status
Table 3
Effect of different types of noises on classification accuracy (OA%).
| Sample set 3000 | 0.2 | 0.3 | 0.4 | 0.5 | 0.6 | 0.7 | 0.8 |
| Gaussian noise | 94.53 | 94.60 | 94.83 | 94.87 | 94.38 | 94.40 | 94.32 | Random noise | 91.13 | 90.87 | 91.00 | 91.60 | 90.03 | 90.63 | 90.97 | Salt-and-pepper noise | 93.30 | 93.07 | 92.90 | 93.37 | 92.50 | 92.83 | 92.70 |
|
|