On Mitigation of Ranging Errors for Through-the-Body NLOS Conditions using Convolutional Neural Networks

Abstract

A UWB-based indoor localization is highly useful in various location-aware applications due to its high-precision and robustness in obstacles. However, it is still a challenging issue to mitigate ranging errors caused by non-line-of-sight(NLOS) conditions. In recent years, various approaches have been attempted using deep learning, but this is mostly the study of NLOS conditions by indoor obstacles. In this paper, we proposed a solution of ranging error mitigation for through-the-human body NLOS conditions using Convolutional Neural Networks.