0
$\begingroup$

My input is this picture
time series input

And I would like to put markers on it and use time series with markers as a label time series lable

Two picture are not scaled. Main point is I would like to train RNN classifier and let it be able to mark the starting points and stopping points.

More generalized examples More generalized example

Question
What is the best function to be marker encoding function?

$\endgroup$
4
  • $\begingroup$ Looks like a velocity trace. Why do you need a complicated network for this? You should be able to just set a threshold value based off of a sliding window, for example. $\endgroup$ Apr 7 at 15:05
  • $\begingroup$ Because size is not the same for each graph and I want to apply A.I. to this problem. Thank you for your attention ;) $\endgroup$
    – ii2
    Apr 8 at 1:40
  • $\begingroup$ Do you have a lot of them already manually marked to train on or do you want it to somehow learn these on its own? $\endgroup$ Apr 8 at 15:02
  • $\begingroup$ @neuroguy123 Thank you for you kind attentions. This question is solved by splitting my problem into 2 parts. First part is classification single pulse, multiple pulses, ... etc. Second starting point and stopping point detection. $\endgroup$
    – ii2
    Apr 8 at 15:38

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.