QUANTILE-LSTM: A ROBUST LSTM FOR ANOMALY DETECTION
Keywords: Anomaly, Quantile, LSTM, Activation Function
Abstract: Anomalies refer to departure of systems and devices from their normal behaviour in standard operating conditions. An anomaly in an industrial device can indicate an upcoming failure, often in the temporal direction. In this paper, we make two contributions: 1) we estimate conditional quantiles, and consider three different ways to define anomalies based on the estimated quantiles and 2) use a new
learnable activation function in the popular Long Short Term Memory (LSTM) architecture to model temporal long-range dependency. In particular, we propose Parametrized Elliot Function (Parametric Elliot Function (PEF)) as an activation function inside LSTM, which saturates lately compared to sigmoid and tanh. The proposed algorithms are compared with other well known anomaly detection algorithms, such as Isolation Forest (iForest), Elliptic Envelope, Autoencoder,and modern Deep Learning models such as Deep Autoencoding Gaussian Mixture Model (DAGMM), Generative Adversarial Networks (GAN) etc. The algorithms are evaluated in terms of various performance metrics, such as precision and recall. The algorithms are experimented on multiple industrial timeseries datasets such as Yahoo, AWS, GE, and machine sensor. We have found the LSTM based quantile algorithms are very effective and outperformed the existing algorithms in identifying the anomalies.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
5 Replies
Loading