Table 11 Training and prediction times of ML-DRSNet, ML-DCNN, and MT-DCNN at optimal step and window sizes
Method | Window size (data point) | Step size (data point) | Training time (s/epoch) | Prediction time (ms/window) |
|---|---|---|---|---|
ML-DRSNet | 20 | 50 | 88.59 | 15.15 |
ML-DCNN | 140 | 50 | 18.03 | 69.36 |
MT-DCNN | 140 | 10 | 180.64 | 76.96 |