Data Fusion Trees for Detection: Does Architecture Matter?

TL;DR

This paper analyzes how the architecture of tree-structured networks affects decentralized detection performance, showing that under certain conditions, simple 1-bit message strategies can nearly achieve optimal error decay rates.

Contribution

It characterizes the optimal error exponent in tree networks and identifies conditions where simple 1-bit message strategies are nearly optimal.

Findings

Type II error probability decays exponentially with number of nodes.

Optimal error exponent often matches that of parallel configurations.

Simple 1-bit message strategies can nearly achieve optimal performance under certain conditions.

Abstract

We consider the problem of decentralized detection in a network consisting of a large number of nodes arranged as a tree of bounded height, under the assumption of conditionally independent, identically distributed observations. We characterize the optimal error exponent under a Neyman-Pearson formulation. We show that the Type II error probability decays exponentially fast with the number of nodes, and the optimal error exponent is often the same as that corresponding to a parallel configuration. We provide sufficient, as well as necessary, conditions for this to happen. For those networks satisfying the sufficient conditions, we propose a simple strategy that nearly achieves the optimal error exponent, and in which all non-leaf nodes need only send 1-bit messages.