Research on a reference signal optimisation algorithm for indoor Bluetooth positioning
GPS has a sharp performance decline in terms of accuracy indoors due to the complex building structure. A combined algorithm, targeting at received signal strength indication (RSSI) calibration optimisation, depending on deep neural network training via input vector Γ and the target output vector ψ, termed reference signal optimisation algorithm (RSOA) is proposed to improve the positioning accuracy in the indoor Bluetooth positioning networks. Experimental results show that the relative error of the proposed RSOA between the estimated results and the measured ones can reach as low as 0.2%, and the absolute errors can be reduced to 0.13 m at most within 10 m. © 2021 Heng Luo et al., published by Sciendo 2021.
This article is not available at CUD collection. The version of scholarly record of this article paper is published in Applied Mathematics and Nonlinear Sciences (2021), available online at: https://doi.org/10.2478/amns.2021.2.00111
Bluetooth, deep learning, Gaussian filter, indoor positioning, supervised learning
Luo, H., Hu, X., Zou, Y., Jing, X., Song, C. & Ni, Q. (2021). Research on a reference signal optimisation algorithm for indoor Bluetooth positioning. Applied Mathematics and Nonlinear Sciences,6(2) 525-534. https://doi.org/10.2478/amns.2021.2.00111