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.