.png){kind=icon}
.png){kind=icon}
Return
Indoor positioning system based on particle swarm optimization algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.measurement.2018.12.038.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In recent years, wireless sensor networks localization becomes a crucial method in the indoor positioning. Following the frontiers of technology, we studied on ZigBee wireless sensor network. Since the parameters of the path loss model are difficult to be estimated by the ordinary methods, the Particle swarm optimization (PSO) method is proposed in this paper to simulate the parameter estimation in the indoor environment. The Texas Instruments CC2530 chip was also taken to build a ZigBee wireless sensor network. The data collected from ZigBee wireless sensor network experiment could be used to estimate the model parameters. PSO algorithm for fitting the signal attenuation curve removed the poor experimental data, and the output model fit well with the signal attenuation curve. Experimental results demonstrate that the PSO algorithm works well, clear, easy to understand, and has a high reliability. Using the parametric model to locate the user's position, and with the weighted K-Nearest Neighbor algorithm, the two-dimensional (2D) positioning was improved effectively. The standard deviation of 2D positioning is 1.15 m, so the model has practical value. Through the experiment and analyzing the data, it is verified that the proposed PSO algorithm in this paper is better than the previous methods we presented. (C) 2018 Elsevier Ltd. All rights reserved.
Keywords:
ZigBee
Path loss model
Particle swarm optimization algorithm
Parameter estimation
K-Nearest Neighbor algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.6
Papers:
1.9W
Citations:
5.4W