Model-based Neural Data Augmentation for sub-wavelength Radio Localization
- URL: http://arxiv.org/abs/2506.06387v1
- Date: Thu, 05 Jun 2025 08:20:51 GMT
- Title: Model-based Neural Data Augmentation for sub-wavelength Radio Localization
- Authors: Baptiste Chatelier, Vincent Corlay, Musa Furkan Keskin, Matthieu Crussière, Henk Wymeersch, Luc Le Magoarou,
- Abstract summary: This work extends the well-established fingerprinting-based localization framework by simultaneously reducing its memory requirements and improving its accuracy.<n>A model-based neural network is used to learn the location-to-channel mapping, and then serves as a generative neural channel model.<n>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.
- Score: 19.966727480424794
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Radio Foundation Models: Pre-training Transformers for 5G-based Indoor Localization [3.2805385616712677]
We propose a self-supervised learning framework that pre-trains a general transformer (TF) neural network on 5G channel measurements without expensive equipment.
Our novel pretext task randomly masks and drops input information to learn to reconstruct it.
It implicitly learnstemporal patterns and information of the propagation environment that enable FP-based localization.
arXiv Detail & Related papers (2024-10-01T12:03:32Z) - A Novel Cross-band CSI Prediction Scheme for Multi-band Fingerprint based Localization [0.0]
We propose a system to extract the time-varying parameters based on space-alternating generalized expectation (SAGE) algorithm.
We then used variational auto-encoder (VAE) to reconstruct channel state information on another channel.
arXiv Detail & Related papers (2024-05-06T20:44:58Z) - A Variational Auto-Encoder Enabled Multi-Band Channel Prediction Scheme
for Indoor Localization [11.222977249913411]
We provide a scheme to improve the accuracy of indoor fingerprint localization from the frequency domain.
We tested our proposed scheme on COST 2100 simulation data and real time frequency division multiplexing (OFDM) WiFi data collected from an office scenario.
arXiv Detail & Related papers (2023-09-19T08:19:34Z) - Adaptive Local-Component-aware Graph Convolutional Network for One-shot
Skeleton-based Action Recognition [54.23513799338309]
We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition.
Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
arXiv Detail & Related papers (2022-09-21T02:33:07Z) - Inducing Gaussian Process Networks [80.40892394020797]
We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points.
The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains.
We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
arXiv Detail & Related papers (2022-04-21T05:27:09Z) - Bayesian Optimisation-Assisted Neural Network Training Technique for
Radio Localisation [3.0981875303080804]
Radio signal-based (indoor) localisation technique is important for IoT applications such as smart factory and warehouse.
Different radio protocols have different features in the transmitted signals that can be exploited for localisation.
Neural networks methods often rely on carefully configured models and extensive training processes to obtain satisfactory performance.
arXiv Detail & Related papers (2022-03-08T11:46:41Z) - LocUNet: Fast Urban Positioning Using Radio Maps and Deep Learning [59.17191114000146]
LocUNet: A deep learning method for localization, based merely on Received Signal Strength (RSS) from Base Stations (BSs)
In the proposed method, the user to be localized reports the RSS from BSs to a Central Processing Unit ( CPU) which may be located in the cloud.
Using estimated pathloss radio maps of the BSs, LocUNet can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the radio maps.
arXiv Detail & Related papers (2022-02-01T20:27:46Z) - Three-Way Deep Neural Network for Radio Frequency Map Generation and
Source Localization [67.93423427193055]
Monitoring wireless spectrum over spatial, temporal, and frequency domains will become a critical feature in beyond-5G and 6G communication technologies.
In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain.
arXiv Detail & Related papers (2021-11-23T22:25:10Z) - Real-time Outdoor Localization Using Radio Maps: A Deep Learning
Approach [59.17191114000146]
LocUNet: A convolutional, end-to-end trained neural network (NN) for the localization task.
We show that LocUNet can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the estimations of radio maps.
arXiv Detail & Related papers (2021-06-23T17:27:04Z) - SignalNet: A Low Resolution Sinusoid Decomposition and Estimation
Network [79.04274563889548]
We propose SignalNet, a neural network architecture that detects the number of sinusoids and estimates their parameters from quantized in-phase and quadrature samples.
We introduce a worst-case learning threshold for comparing the results of our network relative to the underlying data distributions.
In simulation, we find that our algorithm is always able to surpass the threshold for three-bit data but often cannot exceed the threshold for one-bit data.
arXiv Detail & Related papers (2021-06-10T04:21:20Z) - PILOT: Introducing Transformers for Probabilistic Sound Event
Localization [107.78964411642401]
This paper introduces a novel transformer-based sound event localization framework, where temporal dependencies in the received multi-channel audio signals are captured via self-attention mechanisms.
The framework is evaluated on three publicly available multi-source sound event localization datasets and compared against state-of-the-art methods in terms of localization error and event detection accuracy.
arXiv Detail & Related papers (2021-06-07T18:29:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.