Giters

khundman / telemanom

A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.

Home Page:https://arxiv.org/abs/1802.04431

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

first letter represents nature of channel id

peerschuett opened this issue · comments

commented

Hi,
thanks for your work on anomaly detection and for providing the datasets!
For my own project I want to not only detect anomalies, but also learn which sensors correlate with each other. This correlations should then be investigated. For that I would like to have more information about the different sensors for the MSL dataset.

You stated "channel id: anonymized channel id - first letter represents nature of channel (P = power, R = radiation, etc.)". Could you explain the other letters as well?

Thanks a lot! :)