SwinFi: a CSI Compression Method based on Swin Transformer for Wi-Fi Sensing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Bian, Jichen
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910436714086400
author Bian, Jichen
author_facet Bian, Jichen
contents Wi-Fi sensing is a transformative approach that enables a large of applications through CSI analysis. The challenge lies in the high computational and communication costs with the increasing granularity of CSI data. In this letter, we propose SwinFi, a pioneering solution that compresses CSI at the edge into a succinct feature image and reconstructs at the cloud for further processing. SwinFi employs a Swin Transformer-based autoencoder-decoder architecture that ensures SOTA performance in both CSI reconstruction and sensing tasks. We utilize a dataset for PIR task and conduct extensive experiments to evaluate SwinFi. The results show that SwinFi achieves the reconstruction quality with the NMSE of -37.74dB and the classification accuracy of 95.3% at the same time.
format Preprint
id arxiv_https___arxiv_org_abs_2405_03957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SwinFi: a CSI Compression Method based on Swin Transformer for Wi-Fi Sensing
Bian, Jichen
Signal Processing
Wi-Fi sensing is a transformative approach that enables a large of applications through CSI analysis. The challenge lies in the high computational and communication costs with the increasing granularity of CSI data. In this letter, we propose SwinFi, a pioneering solution that compresses CSI at the edge into a succinct feature image and reconstructs at the cloud for further processing. SwinFi employs a Swin Transformer-based autoencoder-decoder architecture that ensures SOTA performance in both CSI reconstruction and sensing tasks. We utilize a dataset for PIR task and conduct extensive experiments to evaluate SwinFi. The results show that SwinFi achieves the reconstruction quality with the NMSE of -37.74dB and the classification accuracy of 95.3% at the same time.
title SwinFi: a CSI Compression Method based on Swin Transformer for Wi-Fi Sensing
topic Signal Processing
url https://arxiv.org/abs/2405.03957