search

wxdang / MSCRED

tensorflow implement the paper A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
60 stars 28 forks source link

Is the data really multivariate timeseries ? #8

Open IKetchup opened 2 years ago

IKetchup commented 2 years ago

From what I see in the data of the repository and the repository of the author the data have the following shape :

*(number of time series lenght of time series)**

However a multivatiate time serie should have the following shape :

(number of time series lenght of time series number of features)

Is it me who have missed something or a problem in the data?

agiannoul commented 1 year ago

The author uses the scheme (length of time series * number of features).

So think of it as one large time series, which is the result of multiple sources (sensors) which produce data in time.

Disclaimer, I am not any of the authors.