Premium
Track fusion based on threshold factor classification algorithm in wireless sensor networks
Author(s) -
Wang Xiang,
Wang Tao,
Chen Shiyang,
Fan Renhao,
Xu Yang,
Wang Weike,
Li Hongge,
Xia Tongsheng
Publication year - 2016
Publication title -
international journal of communication systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.344
H-Index - 49
eISSN - 1099-1131
pISSN - 1074-5351
DOI - 10.1002/dac.3164
Subject(s) - computer science , algorithm , wireless sensor network , euclidean distance , tracking (education) , track (disk drive) , wireless , computation , function (biology) , fusion center , artificial intelligence , telecommunications , cognitive radio , psychology , computer network , pedagogy , evolutionary biology , biology , operating system
Summary Traditional tracking classification algorithm has been widely applied to target tracking in wireless sensor networks. In this paper, focusing on the accuracy of target tracking in wireless sensor networks, we propose an improved threshold factor track classification algorithm. The algorithm extracts the motion model according to the intrinsic properties of the target. It updates the iterative center according to the real‐time motion state of the moving target and timely filters out the weak correlated or uncorrelated data. In order to show the improved threshold factor classification algorithm is more effective, we compare the proposed algorithm with the classification algorithm based on the Euclidean distance comprehensive function. Experimental results show that through the proposed algorithm, the mean error and variance in the direction of x / y / z have been reduced to a certain extent, and the computation time consumed is also reduced. Copyright © 2016 John Wiley & Sons, Ltd.