Likelihood ratio based communication for distributed detection

This paper is concerned with a detection framework under scheduled communication for a binary hypothesis testing problem. A scheduler is designed to smartly select useful sensor measurements for transmission and leave non-useful ones, which results in that only a subset of measurements is sent to the testing agency. To this purpose, a likelihood ratio based scheduler is implemented to decide the transmission of measurements from sensor to the tester. For comparison, a random scheduler which randomly selects measurements for transmission is also included. The Neyman-Pearson tests under the above two schedulers is provided. Given a moderate communication cost constraint, it is shown that the likelihood ratio based scheduler achieves a comparable asymptotic testing performance to the optimal test using the full set of measurements, and is strictly better than the random scheduler. The theoretical results are verified by simulations.