Open AccessFast clustering‐based multidimensional scaling for mobile networks localisation
Author(s) -
Fan Yingsheng,
Qi Xiaogang,
Li Bo,
Liu Lifang
Publication year - 2020
Publication title -
iet communications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.355
H-Index - 62
eISSN - 1751-8636
pISSN - 1751-8628
DOI - 10.1049/iet-com.2019.0444
Subject(s) - multidimensional scaling , cluster analysis , computer science , algorithm , transformation (genetics) , iterative method , cluster (spacecraft) , scaling , mathematics , artificial intelligence , biochemistry , chemistry , gene , programming language , geometry , machine learning
This study considers the problem of localisation in mobile networks, a cooperative localisation algorithm based on fast clustering–multidimensional scaling (FC–MDS) is proposed. Firstly, a FC strategy suitable for mobile networks is given. In the inner‐cluster relative localisation stage, the authors combine the advantages of classical MDS with iterative MDS. In the inter‐cluster coordinate registration stage, the least squares based coordinate transformation method is used to reduce the registration error. Extensive simulation results show that the normalised root mean square error of the location estimates of FC–MDS close to Cramer–Rao lower bound, and the localisation accuracy of the irregular network is comparable to that of the regular network. The per‐time instant running time of FC–MDS is significantly lower than the iterative algorithm MDS–MAP (P, R).