Dynamic Indoor Fingerprinting Localization based on Few-Shot Meta-Learning with CSI Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiao, Jiyu, Wang, Xiaojun, Han, Chenpei, Huang, Yuhua, Zhang, Yizhuo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917563873624064
author Jiao, Jiyu
Wang, Xiaojun
Han, Chenpei
Huang, Yuhua
Zhang, Yizhuo
author_facet Jiao, Jiyu
Wang, Xiaojun
Han, Chenpei
Huang, Yuhua
Zhang, Yizhuo
contents While fingerprinting localization is favored for its effectiveness, it is hindered by high data acquisition costs and the inaccuracy of static database-based estimates. Addressing these issues, this letter presents an innovative indoor localization method using a data-efficient meta-learning algorithm. This approach, grounded in the ``Learning to Learn'' paradigm of meta-learning, utilizes historical localization tasks to improve adaptability and learning efficiency in dynamic indoor environments. We introduce a task-weighted loss to enhance knowledge transfer within this framework. Our comprehensive experiments confirm the method's robustness and superiority over current benchmarks, achieving a notable 23.13\% average gain in Mean Euclidean Distance, particularly effective in scenarios with limited CSI data.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05711
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic Indoor Fingerprinting Localization based on Few-Shot Meta-Learning with CSI Images
Jiao, Jiyu
Wang, Xiaojun
Han, Chenpei
Huang, Yuhua
Zhang, Yizhuo
Machine Learning
Signal Processing
While fingerprinting localization is favored for its effectiveness, it is hindered by high data acquisition costs and the inaccuracy of static database-based estimates. Addressing these issues, this letter presents an innovative indoor localization method using a data-efficient meta-learning algorithm. This approach, grounded in the ``Learning to Learn'' paradigm of meta-learning, utilizes historical localization tasks to improve adaptability and learning efficiency in dynamic indoor environments. We introduce a task-weighted loss to enhance knowledge transfer within this framework. Our comprehensive experiments confirm the method's robustness and superiority over current benchmarks, achieving a notable 23.13\% average gain in Mean Euclidean Distance, particularly effective in scenarios with limited CSI data.
title Dynamic Indoor Fingerprinting Localization based on Few-Shot Meta-Learning with CSI Images
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2401.05711