The task at hand is to predict the future lab values for a patient (1 if abnormal and 0 if normal) using the previous numerical data. It is a multi-label, multi-class time series classification task. I want to improve the training using data augmentation. What are the best ways of doing this? maybe SMOTE or GANs?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.