SMOTE

The Synthetic Minority Over-sampling Technique(SMOTE) to balance the data prior to feeding them into the network.10 Keras’ Adam optimizer was chosen with default parameters, i.e., learning rate 0.001, and dropout with a value of 0.1 was used to prevent overfitting ¹⁾. Cross-validation on a 0.33 split was used on the class-balanced datasets during fitting the model.

¹⁾

Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014;15:1929-1958.