Machine and Deep Learning for Indoor UWB Jammer Localization

2025-11-03

AI Summary

To address the significant degradation in localization accuracy of indoor UWB jammer sources under varying room layouts, this paper proposes a domain-adversarial ConvNeXt autoencoder framework—the first robust transfer learning approach for cross-layout UWB jammer localization. By leveraging a gradient reversal layer to align channel impulse response (CIR) features across disparate environments, the model jointly optimizes classification and regression objectives. Compared to baselines including Random Forest and XGBoost, our method reduces the mean Euclidean localization error to 34.67 cm under reconstructed room layouts—a 83% improvement—and achieves a 56% proportion of samples with localization error ≤30 cm. The core contribution is the establishment of the first domain-adaptive deep learning paradigm specifically designed for UWB jammer source localization, substantially enhancing model generalizability and practical applicability in dynamic indoor environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Ultra-wideband (UWB) localization delivers centimeter-scale accuracy but is vulnerable to jamming attacks, creating security risks for asset tracking and intrusion detection in smart buildings. Although machine learning (ML) and deep learning (DL) methods have improved tag localization, localizing malicious jammers within a single room and across changing indoor layouts remains largely unexplored. Two novel UWB datasets, collected under original and modified room configurations, are introduced to establish comprehensive ML/DL baselines. Performance is rigorously evaluated using a variety of classification and regression metrics. On the source dataset with the collected UWB features, Random Forest achieves the highest F1-macro score of 0.95 and XGBoost achieves the lowest mean Euclidean error of 20.16 cm. However, deploying these source-trained models in the modified room layout led to severe performance degradation, with XGBoost's mean Euclidean error increasing tenfold to 207.99 cm, demonstrating significant domain shift. To mitigate this degradation, a domain-adversarial ConvNeXt autoencoder (A-CNT) is proposed that leverages a gradient-reversal layer to align CIR-derived features across domains. The A-CNT framework restores localization performance by reducing the mean Euclidean error to 34.67 cm. This represents a 77 percent improvement over non-adversarial transfer learning and an 83 percent improvement over the best baseline, restoring the fraction of samples within 30 cm to 0.56. Overall, the results demonstrate that adversarial feature alignment enables robust and transferable indoor jammer localization despite environmental changes. Code and dataset available at https://github.com/afbf4c8996f/Jammer-Loc

Problem

• Localizing indoor UWB jammers under layout changes
• Mitigating performance degradation from domain shifts
• Achieving robust jammer localization with adversarial feature alignment

Innovation

• Domain-adversarial autoencoder aligns cross-domain CIR features
• Gradient-reversal layer enables robust jammer localization transfer
• ConvNeXt architecture mitigates performance degradation from layout changes