Smoothing data with Filtering

3 visualizaciones (últimos 30 días)
SS
SS el 9 de Feb. de 2017
Editada: Image Analyst el 10 de Feb. de 2017
Hi, Please check the attached image. So, I was trying to smoothing the data with filtering. But, in some cases, the value doesn't go up to mark (black circles). Please let me know, how can I fix this problem?
Here is the code I am using now:
FOrd = 400;
fitleredData = filter(ones(1,FOrd)/FOrd,1,inputData);

Respuestas (2)

Image Analyst
Image Analyst el 9 de Feb. de 2017
Obviously if you smooth the data, the smoothed data will never get as high as the peak - otherwise it wouldn't be smoothed now, would it?
Your FOrd should be an odd number, or else you will get a lateral shift in your array, as you are seeing.
  2 comentarios
SS
SS el 9 de Feb. de 2017
Hi, I know that. However, for this problem, I want the peaks to be same. Is there any way I can do it while filtering? That was my question. If not, what is the best way to matching those peaks (such as using if else)?
Image Analyst
Image Analyst el 10 de Feb. de 2017
Editada: Image Analyst el 10 de Feb. de 2017
You can detect the peaks and save their values. Then smooth the whole array. Then replace only the peak locations with the peak values, leaving everything else as it is (smoothed).
Also, can you put back your graph to help people understand what we're talking about?

Iniciar sesión para comentar.


John D'Errico
John D'Errico el 9 de Feb. de 2017
A characteristic of virtually any smoothing scheme is it will tend to round over the peaks and valleys. So what do you expect?
  1 comentario
SS
SS el 9 de Feb. de 2017
Hi, I know that. However, for this problem, I want the peaks to be same. Is there any way I can do it while filtering? That was my question. If not, what is the best way to matching those peaks (such as using if else)?

Iniciar sesión para comentar.

Etiquetas

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by