Distributed Anomaly Detection and Estimation over Sensor Networks: Observational-Equivalence and Q-Redundant Observer Design

In this paper, we study stateless and stateful physics-based anomaly detection scenarios via distributed estimation over sensor networks. In the stateful case, the detector keeps track of the sensor residuals (i.e., the difference of estimated and true outputs) and reports an alarm if certain statistics of the recorded residuals deviate over a predefined threshold, e.g., χ^2 (Chi-square) detector. Instead, only instantaneous deviation of the residuals raises the alarm in the stateless case without considering the history of the sensor outputs and estimation data. Given (approximate) false-alarm rate for both cases, we propose a probabilistic threshold design based on the noise statistics. We show by simulation that increasing the window length in the stateful case may not necessarily reduce the false-alarm rate. On the other hand, it adds unwanted delay to raise the alarm. The distributed aspect of the proposed detection algorithm enables local isolation of the faulty sensors with possible recovery solutions by adding redundant observationally-equivalent sensors. We, then, offer a mechanism to design Q-redundant distributed observers, robust to failure (or removal) of up to Q sensors over the network.

READ FULL TEXT
research
12/12/2018

Distributed Anomaly Detection using Autoencoder Neural Networks in WSN for IoT

Wireless sensor networks (WSN) are fundamental to the Internet of Things...
research
09/12/2017

Distributed Estimation Recovery under Sensor Failure

Single time-scale distributed estimation of dynamic systems via a networ...
research
10/21/2019

Quickest Detection of Growing Dynamic Anomalies in Networks

The problem of quickest growing dynamic anomaly detection in sensor netw...
research
04/26/2022

Linear TDOA-based Measurements for Distributed Estimation and Localized Tracking

We propose a linear time-difference-of-arrival (TDOA) measurement model ...
research
09/28/2020

Anomaly Detection and Sampling Cost Control via Hierarchical GANs

Anomaly detection incurs certain sampling and sensing costs and therefor...
research
11/15/2021

Learning Graph Neural Networks for Multivariate Time Series Anomaly Detection

In this work, we propose GLUE (Graph Deviation Network with Local Uncert...
research
09/14/2022

A Temporal Anomaly Detection System for Vehicles utilizing Functional Working Groups and Sensor Channels

A modern vehicle fitted with sensors, actuators, and Electronic Control ...

Please sign up or login with your details

Forgot password? Click here to reset