Robust Sequential Detection in Distributed Sensor Networks

TL;DR

This paper develops robust sequential detection algorithms for distributed sensor networks operating in non-Gaussian noise, enhancing reliability in binary hypothesis testing through novel consensus-based methods.

Contribution

It introduces a general CISPRT framework and four new robust algorithms tailored for non-Gaussian environments, with analysis and evaluation of their performance.

Findings

The proposed algorithms perform well in shift-in-mean scenarios.

The methods are effective in shift-in-variance scenarios.

Robustness is improved compared to traditional methods.

Abstract

We consider the problem of sequential binary hypothesis testing with a distributed sensor network in a non-Gaussian noise environment. To this end, we present a general formulation of the Consensus + Innovations Sequential Probability Ratio Test (CISPRT). Furthermore, we introduce two different concepts for robustifying the CISPRT and propose four different algorithms, namely, the Least-Favorable-Density-CISPRT, the Median-CISPRT, the M-CISPRT, and the Myriad-CISPRT. Subsequently, we analyze their suitability for different binary hypothesis tests before verifying and evaluating their performance in a shift-in-mean and a shift-in-variance scenario.