2
$\begingroup$

I have a following signal, and I want to correct the part which has a sharp jump, based on the value of the signal sometimes before the jump and its future values.

Instead of that jump I want something like a red line or green line, or something in between (sth that is most likely to be the signal instead of that noise based on the behavior of the signal in the pas and in the future.) Any suggestions? enter image description here

$\endgroup$
  • $\begingroup$ Please explain what a "correction" would be. It sounds like you have in mind some idealized behavior to which your data do not conform, but exactly how do they depart from it? (In many contexts the circled points would be considered an important part of the "signal.") $\endgroup$ – whuber Sep 20 '16 at 17:54
  • $\begingroup$ Does the procedure need to identify the jump as well as smooth it over, or will you identify the jump? $\endgroup$ – whuber Sep 20 '16 at 18:20
  • 1
    $\begingroup$ I have already found the maximum of the jump which in this case is the dot which is at lfp=8000 But I don't know how far I should go left and right and remove those "noise" and put some other values instead. $\endgroup$ – Mina Sep 20 '16 at 18:43
  • $\begingroup$ It night help to have an idea of what you want to do with the "corrected" signal. The entire character of the signal seems to perhaps change after the jump (e.g. acquiring a strong periodic component). $\endgroup$ – GeoMatt22 Sep 20 '16 at 19:04
  • 1
    $\begingroup$ Why don't you share your data ? $\endgroup$ – IrishStat Sep 20 '16 at 20:33

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.