Multi-sample clustering decision fusion for distributed target detection in wireless sensor networks

In this paper, we revisit the problem of target detection in wireless sensor networks (WSNs). Because that the practical environment of WSNs is very complex, and usually the target signal is mixed with a lot of random noises, the phenomenon impacts the performance of target detection experiment. This paper set forth a new way to improve the system performance. We introduce gather multiple sample when we get the observation signals. After obtaining the samples, we calculate the judgments of each sensor by fusion rule. At last local sensors transfer their judgments to the fusion center. We prove that the method is better than single sample through Monte Carlo experiments because of the full use of the observation signals.