Table 6 Comparison of evaluation indexes of measuring point DB9 by four prediction models.

From: Monitoring and deformation of deep excavation engineering based on DFOS technology and hybrid deep learning

Prediction models

Determination coefficient \({\text{R}}^{2}\)

Root mean square error (RMSE)

Mean absolute error (MAE)

Mean bias error (MBE)

BP

0.7991

0.2598

0.2292

− 0.2258

LSTM

0.8253

0.2422

0.1958

− 0.1591

CNN–LSTM

0.8902

0.1920

0.1579

− 0.0601

CNN–LSTM–SAM

0.9461

0.1346

0.1062

0.0101

Back to article page