Table 1 Results of Pearson’s correlations (R) and root mean squared errors (RMSE) comparing predictions under the machine learning approaches proposed and the experimentally measured RWC values
Number of ultrasonic signals | Method | R | RMSE |
|---|---|---|---|
1960 | Random forest | 0.8400 | 0.0591 |
1960 | Convolutional neural network | 0.9225 | 0.0407 |
280 | Random forest | 0.8453 | 0.0585 |
280 | Convolutional neural network | 0.9228 | 0.0406 |