A Novel Cross-band CSI Prediction Scheme for Multi-band Fingerprint based Localization

TL;DR

This paper introduces a new multi-band fingerprint localization method that leverages channel reconstruction and deep learning to improve accuracy in mobile environments, addressing the limitations of traditional fingerprinting techniques.

Contribution

It proposes a novel system combining SAGE algorithm and VAE for cross-band CSI prediction, enhancing localization accuracy in dynamic scenarios.

Findings

Effective channel reconstruction using VAE improves localization accuracy.

System tested on deep-MIMO channel data shows promising results.

Mathematical analysis supports the system's viability.

Abstract

Because of the advantages of computation complexity compared with traditional localization algorithms, fingerprint based localization is getting increasing demand. Expanding the fingerprint database from the frequency domain by channel reconstruction can improve localization accuracy. However, in a mobility environment, the channel reconstruction accuracy is limited by the time-varying parameters. In this paper, we proposed a system to extract the time-varying parameters based on space-alternating generalized expectation maximization (SAGE) algorithm, then used variational auto-encoder (VAE) to reconstruct the channel state information on another channel. The proposed scheme is tested on the data generated by the deep-MIMO channel model. Mathematical analysis for the viability of our system is also shown in this paper.