Research Article
Seismic Events Prediction Using Deep Temporal Convolution Networks
Table 2
Seven compared methods performance on UCI seismic bumps dataset.
| | Category | Methods | RMSE | MAE | Running time (s) |
| | Traditional time series prediction | ARIMA | 0.918 | 0.419 | 172.2 | | Classic machine learning method | SVR | 0.213 | 0.076 | 37.2 | | RF | 0.108 | 0.048 | 17.8 | | Normal recurrent network | LSTM | 0.010 | 0.026 | 46.3 | | Normal temporal CNN network | TCNN | 0.006 | 0.009 | 26.1 | | The proposed method | DCTCNN | | | 79.2 | | CNN-LSTM | | | 60.5 |
|
|