Research on Indoor Positioning Algorithm of Single Reader Based on Gated Recurrent Unit

Authors

  • Jintao Tang School of Informatics, Xiamen University, Xiamen 361005, China
  • Lvqing Yang School of Informatics, Xiamen University, Xiamen 361005, China
  • Jiangsheng Zhao School of Informatics, Xiamen University, Xiamen 361005, China
  • Yishu Qiu School of Informatics, Xiamen University, Xiamen 361005, China
  • Yihui Deng School of Informatics, Xiamen University, Xiamen 361005, China

DOI:

https://doi.org/10.37256/aie.212021663

Keywords:

indoor positioning, GRU, RFID, signal collision

Abstract

With the development of the Internet of Things and Radio Frequency Identification (RFID), indoor positioning technology as an important part of positioning technology, has been attracting much attention in recent years. In order to solve the problems of low precision, high cost and signal collision between readers, a new indoor positioning algorithm based on a single RFID reader combined with a Double-order Gated Recurrent Unit (GRU) are proposed in this paper. Firstly, the reader is moved along the specified direction to collect the sequential tag data. Then, the tag’s coordinate is taken as the target value to train models and compare them with existing algorithms. Finally, the best Gated Recurrent Unit positioning model is used to estimate the position of the tags. Experiment results show that the proposed algorithm can effectively improve positioning accuracy, reduce the number of readers, cut down the cost and eliminate the collisions of reader signals.

Downloads

Published

2021-02-07

How to Cite

1.
Jintao Tang, Lvqing Yang, Jiangsheng Zhao, Yishu Qiu, Yihui Deng. Research on Indoor Positioning Algorithm of Single Reader Based on Gated Recurrent Unit. Artificial Intelligence Evolution [Internet]. 2021 Feb. 7 [cited 2024 Mar. 29];2(1):1-10. Available from: https://ojs.wiserpub.com/index.php/AIE/article/view/663