Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization

Add code
Jul 19, 2018
Dmitry Shalyga, Pavel Filonov, Andrey Lavrentyev

Figure 1 for Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
Figure 2 for Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
Figure 3 for Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
Figure 4 for Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We continue to develop our neural network (NN) based forecasting approach to anomaly detection (AD) using the Secure Water Treatment (SWaT) industrial control system (ICS) testbed dataset. We propose genetic algorithms (GA) to find the best NN architecture for a given dataset, using the NAB metric to assess the quality of different architectures. The drawbacks of the F1-metric are analyzed. Several techniques are proposed to improve the quality of AD: exponentially weighted smoothing, mean p-powered error measure, individual error weight for each variable, disjoint prediction windows. Based on the techniques used, an approach to anomaly interpretation is introduced.

* 9 pages  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon