2

I understand that the question I am asking seem the be somewhat related to another question which has been asked already here and here.

But I feel that this is an entirely different question. (I have also submitted this question on the dsp.stackexchange)

I have a huge (over 100K data points) time series data of the position (x, y coordinates) of an element in space. This element is vibrating randomly, and both amplitude and the frequency of vibration is random. I want to look at the events which are similar and see if there is any pattern in those events, are they periodic or related somehow.

I am working on a biological problem and have very little knowledge about signal processing. I can provide more details. Any help would be really appreciated.

Community
  • 1
  • 1
C.M
  • 87
  • 8
  • if you're looking for patterns of anomaly check this [article](https://blog.twitter.com/2015/introducing-practical-and-robust-anomaly-detection-in-a-time-series) – bachr Jan 08 '15 at 14:01
  • Thanks! but I am not looking for anomalies, in fact I do not know what I am looking for! I am trying to establish a pattern, and thus am fishing for one. – C.M Jan 08 '15 at 14:11
  • so there is no direct answer, you should proceed scientifically, check how people in the same field used to process these data (e.g. visualization first) – bachr Jan 08 '15 at 14:17
  • I was wondering if I can find a way where I can plot for each type of vibration event (amplitude and frequency is comparable) separately? If this makes any sense? – C.M Jan 08 '15 at 14:44
  • I suggest that you will define more clearly what do you mean by an "event" in your problem. Is that a single instance of the time series? a sequence of a fixed length? a sequence of variable length? A sequence where there is a non-negligible change of position? – nojka_kruva Jan 20 '15 at 14:11
  • Another thing is what exactly do you mean by your data being random, in respect to your desire to look for patterns in it. The very definition of randomness is the absence of a pattern between different data instances. – nojka_kruva Jan 20 '15 at 14:16

1 Answers1

0

One of the areas of the research on time series patterns is called Motif Detection or Discovey, some use association strategies, other are probabilistic.

Some links here http://dl.acm.org/results.cfm?query=motif+discovery&Go.x=5&Go.y=12

jcarlos
  • 425
  • 7
  • 17