A Variational Auto-Encoder Enabled Multi-Band Channel Prediction Scheme for Indoor Localization

TL;DR

This paper introduces a multi-band channel prediction scheme using a variational auto-encoder to enhance indoor localization accuracy by predicting and combining CSI data across frequencies, tested on simulated and real WiFi data.

Contribution

The paper proposes a novel variational auto-encoder based method for multi-band CSI prediction to improve fingerprint-based indoor localization accuracy.

Findings

Improved localization accuracy with multi-band CSI prediction.

Effective on both simulated and real WiFi data.

Reduces computational overhead compared to traditional methods.

Abstract

Indoor localization is getting increasing demands for various cutting-edged technologies, like Virtual/Augmented reality and smart home. Traditional model-based localization suffers from significant computational overhead, so fingerprint localization is getting increasing attention, which needs lower computation cost after the fingerprint database is built. However, the accuracy of indoor localization is limited by the complicated indoor environment which brings the multipath signal refraction. In this paper, we provided a scheme to improve the accuracy of indoor fingerprint localization from the frequency domain by predicting the channel state information (CSI) values from another transmitting channel and spliced the multi-band information together to get more precise localization results. We tested our proposed scheme on COST 2100 simulation data and real time orthogonal frequency division multiplexing (OFDM) WiFi data collected from an office scenario.