Time series/ sequential data study group

Part 1 (2019)
164

Hi @fl2o,
Sorry for the late reply!

I don’t have any personal experience with TS of different lengths, but the approach I’ve seen reflected more often in papers is padding TS before the transformation.

There are several approaches you could follow.
In all cases you would first transform each individual TS within a MTS into an image (array).
Some alternatives are:

  1. Tile images to build a larger image.
  2. Stack all images into a multichannel (3+) array.
  3. Fuse the images into a single image.
    To perform 2 & 3 you would need to modify the convnet to allow 3+ channels.

Edit: @hwasiti has pointed a 4th option: Concatenating multi CNN outputs (each CNN for each uni-variate spectrogram) into single dense NN (example).

2 Likes