Indoor position system based on ultra-wideband technology was recognized recently as its great potential to guarantee accurate localization. Non-line-of-sight identification attracts lots of attention. Extracted from the different characters of channel impulse response using Machine Learning is proposed to reduce the localization error, caused by non-line-of-sight condition. In this paper, we proposed an efficient method using Generative Adversarial Network for data augmentation cooperating with autoencoder for enhancing the training model. The results show our framework obtained state-of-art identification performance.
Paper
Full text
GAN-based Data Augmentation for UWB NLOS Identification Using Machine Learning
Semantic Scholar · Computer Science · 2022
Abstract
Indoor position system based on ultra-wideband technology was recognized recently as its great potential to guarantee accurate localization. Non-line-of-sight identification attracts lots of attention. Extracted from the different characters of channel impulse response using Machine Learning is proposed to reduce the localization error, caused by non-line-of-sight condition. In this paper, we proposed an efficient method using Generative Adversarial Network for data augmentation cooperating with autoencoder for enhancing the training model. The results show our framework obtained state-of-art identification performance.