Networked and Embedded Systems Laboratory

Tryear

Trmonth

Trnumber

Title

Abstract

With their increasing capabilities, research efforts in sensor network have been spreading on a variety of aspects. In this paper, we present a system-oriented, layered approach for evaluating their application-related performance. Focusing on sensor-enabled detection systems, an application planner’s point of view of the system is considered and a hypothesis-testing-based analysis framework for evaluating the quality of information (QoI) supported by a sensor network deployment is explored. The QoI properties of centralized, distributed and hybrid decision topologies are investigated and trade-offs explored at the sensor, cluster, and system-level. In the process, the computationally powerful concept of a QoI equivalent sensor is presented and applied in the aforementioned explorations. Finite size networks are considered and limiting behavior and dominance properties are also investigated. Finally, extensions of the analysis framework to faulty sensor and the impact of calibration are also investigated.

Filename

File

Urlpdfpaper

Urlsrcpaper

Urlpdfpresentation

Urlsrcpresentation

Urlavmedia

Urldoi

Urlpublisher

Urlgooglescholar

Urlciteseer

Pubin

Pubvol

Pubnum

Pubnum end

Pubpagefirst

Pubpagelast

Pubpagecount

Pubdate

Pubdate end

Pubplace

Publisher

Ispublic

Islabdocument

Miscattributes

Document category

Main research area

Editing document