A Flexible and Interpretable Framework for Predicting Anomalous Behavior in Industry 4.0 Environments.

2020 
A method called interpretable anomaly prediction is introduced in this paper. The proposed methodology allows us to handle prediction issues in industry 4.0 settings by using regularized logistic regression as core model. In particular, in contrast to anomaly detection algorithms which permits to identify if the current data are anomalous or not, the proposed technique is able to predict the probability that future data will be abnormal. Furthermore, feature extraction and selection mechanisms give insights on the possible root causes leading to failures.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    31
    References
    2
    Citations
    NaN
    KQI
    []