Score: 1

Model-based Neural Data Augmentation for sub-wavelength Radio Localization

Published: June 5, 2025 | arXiv ID: 2506.06387v1

By: Baptiste Chatelier , Vincent Corlay , Musa Furkan Keskin and more

Potential Business Impact:

Finds exact spots even with blocked signals.

Business Areas:
Natural Language Processing Artificial Intelligence, Data and Analytics, Software

The increasing deployment of large antenna arrays at base stations has significantly improved the spatial resolution and localization accuracy of radio-localization methods. However, traditional signal processing techniques struggle in complex radio environments, particularly in scenarios dominated by non line of sight (NLoS) propagation paths, resulting in degraded localization accuracy. Recent developments in machine learning have facilitated the development of machine learning-assisted localization techniques, enhancing localization accuracy in complex radio environments. However, these methods often involve substantial computational complexity during both the training and inference phases. This work extends the well-established fingerprinting-based localization framework by simultaneously reducing its memory requirements and improving its accuracy. Specifically, a model-based neural network is used to learn the location-to-channel mapping, and then serves as a generative neural channel model. This generative model augments the fingerprinting comparison dictionary while reducing the memory requirements. The proposed method outperforms fingerprinting baselines by achieving sub-wavelength localization accuracy, even in NLoS environments. Remarkably, it offers an improvement by several orders of magnitude in localization accuracy, while simultaneously reducing memory requirements by an order of magnitude compared to classical fingerprinting methods.

Country of Origin
🇸🇪 🇫🇷 France, Sweden

Page Count
13 pages

Category
Electrical Engineering and Systems Science:
Signal Processing