Semi-supervised t-SNE for Millimeter-wave Wireless Localization

TL;DR

This paper introduces a semi-supervised t-SNE method for millimeter-wave wireless localization that effectively embeds high-dimensional channel data into 2D maps, achieving accurate positioning with minimal labeled data.

Contribution

The paper presents a novel semi-supervised t-SNE algorithm tailored for millimeter-wave localization, reducing the need for extensive labeled samples and synchronization among base stations.

Findings

Achieves 6.8 m localization error with only 5% labeled data

Operates effectively in simulated urban millimeter-wave environments

Does not require precise synchronization among base stations

Abstract

We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI). For this problem, we propose a Semi-supervised tdistributed Stochastic Neighbor Embedding (St-SNE) algorithm to directly embed the high-dimensional CSI samples into the 2D geographical map. We evaluate the performance of St-SNE in a simulated urban outdoor millimeter-wave radio access network. Our results show that St-SNE achieves a mean localization error of 6.8 m with only 5% of labeled CSI samples in a 200*200 m^2 area with a ray-tracing channel model. St-SNE does not require accurate synchronization among multiple BSs, and is promising for future large-scale millimeter-wave localization.