Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Application in identifying event windows. #1097

Answered by seanlaw
aeroaks asked this question in Q&A
Discussion options

I am trying to find this pattern in my timeseries data which is aggregated and essentially noise free.
image

Is stumpy's Matrix profile useful in identifying the event windows? It can be that the signal spends longer time at 100 (in the graph above) that might create a broader window.

You must be logged in to vote

@aeroaks Thank you for your question and welcome to the STUMPY community. For nearly exact pattern matches (where you know the pattern ahead of time), I recommend taking a look at this tutorial. Instead of computing a matrix profile, you compute something called a "distance profile" instead. Having said that, your window size seems a bit short and so you may have better luck with a different approach.

Replies: 1 comment 1 reply

Comment options

@aeroaks Thank you for your question and welcome to the STUMPY community. For nearly exact pattern matches (where you know the pattern ahead of time), I recommend taking a look at this tutorial. Instead of computing a matrix profile, you compute something called a "distance profile" instead. Having said that, your window size seems a bit short and so you may have better luck with a different approach.

You must be logged in to vote
1 reply
Comment options

Thanks for the quick reply. Indeed, the type of data in my timeseries present opportunities to try more simpler analysis. I have given scipy.signal.correlate a try and it seems to perform good enough. I will look into the above mentioned tutorial too.

Answer selected by aeroaks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
2 participants

AltStyle によって変換されたページ (->オリジナル) /