Semi-supervised t-SNE for Millimeter-wave Wireless Localization
This addresses localization for future millimeter-wave wireless networks, offering a practical solution with reduced labeled data requirements, but it is incremental as it adapts an existing method to a specific domain.
The paper tackles mobile localization in millimeter-wave networks by proposing a semi-supervised t-SNE algorithm to embed high-dimensional channel state information into a 2D map, achieving a mean localization error of 6.8 m with only 5% labeled samples in a 200*200 m² area.
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.