Robust Target Localization From Binary Decisions in Wireless Sensor Networks

Abstract

Wireless sensor networks (WSN) are becoming an important tool in a variety of tasks, including monitoring and tracking of spatially occurring phenomena. These networks offer the capability of densely covering a large area, but at the same time are constrained by the limiting sensing, processing and power capabilities of their sensors. In order to complete the task at hand, the information collected by the sensor nodes needs to be appropriately fused. In this paper, we study the problems of estimating the location of a target and estimating its signal intensity. The proposed algorithms are based on the local vote decision fusion (LVDF) mechanism, where sensors first correct their original decisions using decisions of neighboring sensors. These corrected decisions are more accurate, robust, and improve detection; however, they are correlated, which renders maximum likelihood estimation intractable. We adopt a pseudo-likelihood formulation and examine several variants of localization and signal estimation algorithms based on original and corrected decisions using direct optimization methods as well as an EM approach. Uncertainty assessments about the parameters of interest are provided using a parametric bootstrap technique. An extensive simulation study of the developed algorithms along with several benchmarks establishes the overall superior performance of the LVDF based algorithms, especially in low signal-to-noise ratio environments. Extensions to tracking moving targets and localizing multiple targets are also considered.

ftTRACK

“…Authors in Singh et al [2011] use geometric techniques that rely on the overlap of the sensing areas of sensors and employ a nonideal sensing model for localization. On a different line, authors in Katenka et al [2008aKatenka et al [ , 2008b achieve robust target localization by first using a local vote decision fusion (LVDF) scheme for correcting the original decisions based on the majority of the neighboring sensors' decisions followed by numerical optimization techniques.…”

Relocatable, Automated Cost-Benefit Analysis for Marine Sensor Network Design

“…There are existing techniques for designing networks for efficient communication [8,9] and these could be integrated at this stage.…”

“…We can also use more elaborate techniques such as k-median to ensure optimal spatial coverage of an area [7]. There are also methods for reducing the costs of communicating between nodes [8,9]. …”

Trackingwith binary sensors

“…The purpose is to analyze the best proportion of sensors in each class to tradeoff performance with cost. Some assume probabilistic models for object movement and/or for the received signal strength [5,8,11,13,15] and develop detection algorithms This work was partially supported by NSF CNS-1329657. based on these models.…”