Ñ Patience: The patience value of 20 epochs means we are willing to tolerate a fair number of epochs without improve- ment before stopping training. This avoids stopping too early and allows temporary plateaus in validation loss, but ulti- mately stops before severe overfitting occurs. In the Impact dataset, the CNN and MLP models, with and without transfer learning, achieved comparative perfor- mance in terms of accuracy, precision, and recall, with slight enhancements observed in models using transfer learning. Conversely, FCNN underperformed, showing negligible improvement from transfer learning unlike CNN and MLP, which recorded accuracies above 0.8, FCNN yielded a mere 0.2. Transfer learning substantially increased ResNet’s performance variance regarding recall, precision, and accuracy. Inception showed a similar trend to CNN and MLP, where transfer learning resulted in minor enhancements. The Encoder model Training loss Epoch 20 15 10 5 0 0 100 200 300 400 500 Mean loss model Loss range modell Mean loss model with TL Loss range model with TL L de 20 15 10 5 0 0 100 200 300 400 500 Mean loss model Loss range modell Mean model with TL Loss range model with TL Validation loss Epoch e lloss del th del th Training loss Epoch 14 12 10 8 6 4 2 0 0 100 200 300 400 500 Mean loss modell Loss range modell Mean loss model with TL Loss range model with TL M L M L 14 12 10 8 6 4 2 0 0 100 200 300 400 500 Mean loss Loss range modelled Mean model with TL Loss range model with TL Validation loss Epoch an mmodel L M lloss del th L del th Training loss Epoch 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0 25 50 75 100 125 150 175 200 Mean modell Loss range modell Mean model with TL Loss range model with TL M lloss de L de an lloss s m el L del th 3.5 3.0 2.5 2.0 1.5 1.0 0.5 0 25 50 75 100 125 150 175 200 Mean modell Loss range modell Mean loss model with TL Loss range model with TL Validation loss Epoch M lloss de L de M l w L del th Training loss Epoch 4 3 2 1 0 0 25 50 75 100 125 150 175 200 Mean modelled Loss range modelled Mean model with TL Loss range model with TL M lloss L an lloss s m el L del th 4 3 2 1 0 0 25 50 75 100 125 150 175 200 Mean modelled Loss range modelled Mean loss model with TL Loss range model with TL Validation loss Epoch M lloss L M L del th Figure 9. Comparative analysis of mean loss and range with and without the implementation of transfer learning for: (a) Inception model applied to the impact test dataset (b) Inception model applied to the PLB test dataset (c) ResNet model applied to the impact test dataset and (d) ResNet model applied to the PLB test dataset. J U L Y 2 0 2 3 • M A T E R I A L S E V A L U A T I O N 81 2307 ME July dup.indd 81 6/19/23 3:41 PM

CNN 0.8 0.6 0.4 0.2 MLP FCNN RESNET INCEPTION ENCODER CNN 1.0 0.8 0.6 0.4 0.2 0.0 MLP FCNN RESNET INCEPTION ENCODER CNN 1.0 0.8 0.6 0.4 0.2 MLP FCNN RESNET INCEPTION ENCODER Figure 10. The distribution of: (a) accuracy (b) precision and (c) recall from a tenfold cross-validation for six classifiers on the impact test dataset. Models without transfer learning are indicated by red bars, while those with transfer learning are shown in blue. 0.8 0.6 0.4 0.2 0.0 CNN MLP FCNN RESNET INCEPTION ENCODER CNN 0.8 0.6 0.4 0.2 0.0 MLP FCNN RESNET INCEPTION ENCODER CNN 0.8 0.6 0.4 0.2 MLP FCNN RESNET INCEPTION ENCODER Figure 11. The distribution of: (a) accuracy (b) precision and (c) recall from a tenfold cross-validation for six classifiers on the PLB test dataset. Models without transfer learning are indicated by red bars, while those with transfer learning are shown in blue. ME |AI/ML 82 M A T E R I A L S E V A L U A T I O N • J U L Y 2 0 2 3 2307 ME July dup.indd 82 6/19/23 3:41 PM Accuracy Precision Recall Accuracy Precision Recall