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.
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?
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! :)