Including Sparse Production Knowledge into Variational Autoencoders to Increase Anomaly Detection Reliability

03/24/2021
by   Tom Hammerbacher, et al.
0

Digitalization leads to data transparency for production systems that we can benefit from with data-driven analysis methods like neural networks. For example, automated anomaly detection enables saving resources and optimizing the production. We study using rarely occurring information about labeled anomalies into Variational Autoencoder neural network structures to overcome information deficits of supervised and unsupervised approaches. This method outperforms all other models in terms of accuracy, precision, and recall. We evaluate the following methods: Principal Component Analysis, Isolation Forest, Classifying Neural Networks, and Variational Autoencoders on seven time series datasets to find the best performing detection methods. We extend this idea to include more infrequently occurring meta information about production processes. This use of sparse labels, both of anomalies or production data, allows to harness any additional information available for increasing anomaly detection performance.

READ FULL TEXT

page 3

page 5

research
01/12/2021

Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators

Anomaly detection is a challenging task for machine learning algorithms ...
research
04/09/2020

Anomaly Detection with SDAE

Anomaly detection is a prominent data preprocessing step in learning app...
research
09/29/2020

A comparison of classical and variational autoencoders for anomaly detection

This paper analyzes and compares a classical and a variational autoencod...
research
08/06/2023

Detection of Anomalies in Multivariate Time Series Using Ensemble Techniques

Anomaly Detection in multivariate time series is a major problem in many...
research
09/27/2019

Anomaly Detection in DevOps Toolchain

The tools employed in the DevOps Toolchain generates a large quantity of...
research
03/03/2018

Analyzing Business Process Anomalies Using Autoencoders

Businesses are naturally interested in detecting anomalies in their inte...
research
06/12/2014

Event and Anomaly Detection Using Tucker3 Decomposition

Failure detection in telecommunication networks is a vital task. So far,...

Please sign up or login with your details

Forgot password? Click here to reset