Substitute of CUSUM algorithm for point-change detection and curve fitting..

Hi, I am using CUSUM (cumulative sum) algorithm to detect points of sudden changes in my neural signal data. This algorithm is working fine, but I want to try some other algorithm. Can anyone suggest some other algorithm that can be used to detect changes?

[H. Sh. G.]

Hi

Use findchangpts.m

https://www.mathworks.com/help/signal/ref/findchangepts.html

Answer 1

[Greg Heath]

Just compare the new point with the old mean before updating the mean

   check(n+1) = abs( x(n+1)- meanx(n) )
   meanx(n+1) = ( x(n+1) + n*meanx(n))/(n+1)

Hope this helps

Thank you for formally accepting my answer

Greg

Answer 2

[jyoti mundra]

Hi, is there any matlab function available for CUSUM also?

[Tommy]

In the signal processing toolbox:

https://www.mathworks.com/help/signal/ref/cusum.html