Data clustering

[CdeMills]

Hello,

I would like to have some hints about the following problem. I test an
electrical system with a number of input levels. The system response consist
mainly of output steps, separated by short transition zones.

As the command and the recording are asynchronous, I would like to divide
the output data into zones where we are observing constant input level. The
hypothesis are:
1) the number of input steps is known;
2) the number of points in the stable zones is greater than the number of
points in the transition regions.

Is there some algorithm in Octave permitting to compute such a map between
points and level ? Basically the problem dimension is one.

Regards

Pascal



--
View this message in context: 
http://octave.1599824.n4.nabble.com/Data-clustering-tp4664909.html
Sent from the Octave - General mailing list archive at Nabble.com.