An Integrated Data Combination Method in Wireless Sensor Networks

An Integrated Data Combination Method in Wireless Sensor Networks

Yang Zhang (School of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing, China), Yun Liu (School of Electronic and Information Engineering, Key Laboratory of Communication and Information Systems, Beijing Municipal Commission of Education, Beijing Jiaotong University, Beijing, China), Qing-An Zeng (Department of Computer Systems Technology, North Carolina A&T State University, Greensboro, USA) and Qing Liu (China Electric Power Construction Limited by Share Ltd, Beijing, China)
DOI: 10.4018/IJITN.2018100104

Abstract

This article proposes an integrated information fusion approach in wireless sensor networks (WSNs) based on the Dempster-Shafer evidence theory, which includes four main aspects: the construction of basic probability assignment; a novel reliability coefficient function converting similarity to initial weight factors; an improved fusion approach by reassigning reliability coefficients; and the “Discount Rule.” Utilizing the integrated approach, conflicting data are fused more accurately and effectively than using the traditional fusion method. Experimental results show that the combined belief assignment of the proposed approach is in accordance with the real data observations. The integrated information combination rule for combining conflicting data can avoid the influence of imprecise information from sensors, and has the better performance than other conventional methods.
Article Preview
Top

1. Introduction

In recent years, multiple sensors data fusion as a rising cross-subject has been well studied in many literatures. Through fusing various data from several sensors, a unified result can be produced (Khaleghi & Khamis, 2013). Nowadays, data fusion is widely used in many fields, such as pattern recognition and classification, image processing, robotics, and expert systems (Shen & Liu, 2014), especially in the wireless sensor networks (Zhang & Lai, 2014). With the increasing application of target detection and classification, multiple sensors data fusion has emerged recently as an interesting technology (Zhang & Zhang, 2015). The raw data of each sensor are often harsh and imprecise, and cannot be used for target classification and decision making directly. As the further research of the community of multisensor data fusion in the past several years, decision fusion is developed which convert the raw data of each sensor into an individual decision. Fusion center collects the local decisions from sensors and combines them into a global one. By transmitting the decision instead of the raw data from an individual sensor, the energy and bandwidth consumption is reduced in WSNs (Zhang & Zhang, 2016). Compared with the detection and classification for a target using a single sensor, multisensor decision fusion achieves more accurate, comprehensive and reliable results. There are a number of theories which can be used during the fusion process, such as Bayesian fusion, evidential belief reasoning, fuzzy reasoning, rough set theory, and possibility theory (Khaleghi & Khamis, 2013; Zhang & Lai, 2014).

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 13: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2020): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing