Distributed sequential detection for Gaussian binary hypothesis testing: Heterogeneous networks

This paper studies the problem of sequential Gaussian binary hypothesis testing in a distributed multi-agent heterogeneous network. A distributed sequential detection algorithm of the consensus+innovations form is proposed, in which the agents update their decision statistics by simultaneously processing latest observation samples (innovations) and neighborhood information. For each pre-specified set of error probabilities, algorithm parameters are derived which ensure that the algorithm achieves the desired error performance and finite time termination almost surely. The expected stopping time for the proposed algorithm is evaluated and its dependance on network connectivity quantified. Finally, simulation studies are presented which illustrate the analytical findings.