[R] Is there a time series resampling function ?
AltShift
allennugent at hotmail.com
Sun Sep 6 13:54:45 CEST 2015
I need a function for regularising the time base of electronically acquired
signals (i.e. vectors of samples with a nominally constant time base).
For example, the accelerometer in my smartphone can deliver data at about 50
Hz, but the sampling rate varies by about 5% throughout a recording. I have
developed signal processing functions that assume a constant sample rate, so
I need to modify my input data vectors so that this assumption becomes true.
Furthermore, if I want to combine signals from different sources that have
different sampling rates, I will be obliged to harmonise the time bases,
somehow.
I have written routines in other languages to interpolate (generate a larger
number of regularly spaced samples from the input series) or, what I call,
"intrapolate" (generate a smaller number of regularly spaced samples from
the input series), so it wouldn't be too hard form me to write a function
that covers both, but I prefer not to reinvent wheels (unless my wheel is
markedly better!)
Can anyone tell me if there is already a package that might cover what I
need?
--
View this message in context: http://r.789695.n4.nabble.com/Is-there-a-time-series-resampling-function-tp4711907.html
Sent from the R help mailing list archive at Nabble.com.
More information about the R-help
mailing list