# DNN-based Localization from Channel Estimates: Feature Design and Experimental Results

arXiv: https://arxiv.org/abs/2004.00363 · HTML: https://mlsanity.com/paper/2004.00363/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Communication-Efficient Large-Scale Distributed Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2404.06114/) (2024)
- [Federated Distillation based Indoor Localization for IoT Networks](https://mlsanity.com/paper/2205.11440/) (2022)
- [Optimizing Multicarrier Multiantenna Systems for LoS Channel Charting](https://mlsanity.com/paper/2310.03762/) (2023)
- [DyLoc: Dynamic Localization for Massive MIMO Using Predictive Recurrent Neural Networks](https://mlsanity.com/paper/2101.07848/) (2021)
- [Attention Aided CSI Wireless Localization](https://mlsanity.com/paper/2203.10506/) (2022)
- [Supervised Contrastive CSI Representation Learning for Massive MIMO Positioning](https://mlsanity.com/paper/2204.12796/) (2022)
- [Resource Allocation and Workload Scheduling for Large-Scale Distributed Deep Learning: A Survey](https://mlsanity.com/paper/2406.08115/) (2024)
- [High-Precision Machine-Learning Based Indoor Localization with Massive MIMO System](https://mlsanity.com/paper/2303.03743/) (2023)
- [CSI Obfuscation: Single-Antenna Transmitters Can Not Hide from Adversarial Multi-Antenna Radio Localization Systems](https://mlsanity.com/paper/2508.02553/) (2025)
- [DNN-Enabled Multi-User Beamforming for Throughput Maximization under Adjustable Fairness](https://mlsanity.com/paper/2602.15617/) (2026)

## Abstract (arXiv)

We consider the use of deep neural networks (DNNs) in the context of channel state information (CSI)-based localization for Massive MIMO cellular systems. We discuss the practical impairments that are likely to be present in practical CSI estimates, and introduce a principled approach to feature design for CSI-based DNN applications based on the objective of making the features invariant to the considered impairments. We demonstrate the efficiency of this approach by applying it to a dataset constituted of geo-tagged CSI measured in an outdoors campus environment, and training a DNN to estimate the position of the UE on the basis of the CSI. We provide an experimental evaluation of several aspects of that learning approach, including localization accuracy, generalization capability, and data aging.