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.
I would like to know if Telemanom has parameters for sliding window size similar to that in Matrix Profile, and if so, which parameter should I adjust?
I found these parameters in the 'config.yaml' file that might be related to the sliding window size:
l_s: 250
batch_size: 70
window_size: 30
Could you please explain the distinctions between these parameters and their respective usages?
For my use case, I am aiming to detect anomalies of length 132. Could you please advise me on how to set the relevant Telemanom parameters accordingly?
Thank you for your help, and I look forward to your response.
Hello,
I would like to know if Telemanom has parameters for sliding window size similar to that in Matrix Profile, and if so, which parameter should I adjust?
I found these parameters in the 'config.yaml' file that might be related to the sliding window size: l_s: 250 batch_size: 70 window_size: 30 Could you please explain the distinctions between these parameters and their respective usages?
For my use case, I am aiming to detect anomalies of length 132. Could you please advise me on how to set the relevant Telemanom parameters accordingly?
Thank you for your help, and I look forward to your response.
Best regards, Yue Lu