A method for indoor Wi-Fi location based on improved back propagation neural network

Jinghui Chen,Chen Dong,Xiaoyu Zhang,Guorong He

doi:10.3906/elk-1812-13

Jinghui Chen, Chen Dong + Show 2 more

Open Access

https://doi.org/10.3906/elk-1812-13

Copy DOI

Abstract

A method for indoor Wi-Fi location based on improved back propagation neural network

Highlights

With the rapid development of the wireless network, the accuracy of location is concerned
Momentum term To solve the problem that slow convergence speed and easy to fall into the local minimum value of the classical back propagation (BP) algorithm, the momentum term has been introduced to speed up the updating rate of the weight value and promote the accuracy rate of neural network prediction [16]
Aiming at solving the problem that BP neural network is easy to fall into the local minimum value and slow convergence speed, which affects the accuracy of the Wi-Fi signal feature location method, this paper proposes a Wi-Fi indoor location method based on improved BP neural network

Summary

Introduction

With the rapid development of the wireless network, the accuracy of location is concerned. The indoor area location technology is given more attention. As an example of RFID-based indoor location technologies, He Xu et al [3] used the weighted path length and support vector regression algorithm to solve the problem that the accuracy of the LANDMARC location algorithm relies on the density of reference tags and the performance of RFID readers. He Xu et al [4] proposed a

Objectives

Methods

Findings

Conclusion