RNN/LSTM deep learning model?

Question

I am trying to build an RNN/LSTM model for binary classification 0 or 1

a sample of my dataset (patient number, time in mill/sec., normalization of X Y and Z, kurtos

Answer 1

The LSTM layer takes a 3 dimensional input, corresponding to (batch_size, timesteps, features). In your case you have only a 2 dimensional input, which is (batch_size, features).

The LSTM layer is adapted to sequences formats (sentences, stocks prices ...). You need to reshape your data so that it can be used this way. More specificaly, you need to reshape your data to have one line per patient (Or you can choose to have multiple sequences per patient, but let's say we want one line per patient for now), and each line needs to contain multiple arrays, each array corresponding to an observation of your patient.