Jul 2026· IEEE Transactions on Wireless Communications· Vol 25, pp. 21105-21118· 0 citations· 25 references
EngineeringComputer Science
TL;DR
RadioTrace is proposed, a novel RM estimation framework without deployment-time fine-tuning that tightly integrates sparse RSS measurements with a frozen pre-trained diffusion prior and achieves competitive performance with state-of-the-art learning-based methods under random sampling, and maintains strong reconstruction quality under restricted-area sampling.
Abstract
Radio map (RM) estimation aims to reconstruct the spatial distribution of wireless signal characteristics, such as received signal strength (RSS), from sparse measurements, a task that is critical for spectrum management, interference mitigation, and localization in modern wireless networks. Traditional approaches, including interpolation and deep learning, either struggle to capture complex propagation effects or require large-scale retraining for each new sampling pattern, which limits their generalization. More recently, prior-based methods have combined pre-trained generative models with measurements to reduce the need for deployment-time model fine-tuning, but they typically treat the prior as a simple regularizer and lack explicit transmitter-aware integration. In this paper, we propose RadioTrace, a novel RM estimation framework without deployment-time fine-tuning that tightly integrates sparse RSS measurements with a frozen pre-trained diffusion prior. RadioTrace incorporates transmitter (Tx) location estimation directly into the denoising loop, iteratively refining Tx coordinates based on reconstruction quality to guide the generative process. To further enhance robustness, we introduce a propagation-guided K-means initialization that mitigates poor local minima in the Tx update and provides a geometry-consistent starting point. Moreover, we provide a stochastic stability analysis for the Tx-coordinate refinement component, showing that the Tx update remains stable under perturbations induced by diffusion sampling and Tx-map relaxation. Extensive experiments demonstrate that RadioTrace achieves competitive performance with state-of-the-art learning-based methods under random sampling, and maintains strong reconstruction quality under restricted-area sampling, highlighting its adaptability, robustness, and practical relevance.
Radio maps provide spatially resolved received signal strength information for coverage assessment, gateway placement, interference awareness, and adaptive power management in Internet of Things (IoT) environments. However, dense radio maps are expensive to measure, and simple path-loss models are often inaccurate in indoor spaces with walls, shadowing, and non-line-of-sight propagation. This paper proposes a propagation-prior-guided model-aided learning framework for sparse received signal strength indicator (RSSI) radio map prediction. Unlike conventional deep learning approaches that expect a network to infer both propagation behavior and local signal variations directly from sparse measurements, the proposed framework explicitly separates these two roles. Coarse propagation knowledge is first encoded into structured physical-prior channels, while the neural network focuses on learning the remaining spatial variations that cannot be captured by analytical propagation models. The input representation combines sampled RSSI values with transmitter location, distance, free-space path-loss prior, wall-loss prior, line-of-sight prior, carrier frequency, and transmit-power channels. A compact encoder–decoder with channel and spatial attention is used as one dense reconstruction implementation of this formulation. A multi-band IoT-style indoor simulation dataset is generated to evaluate sparse radio-map reconstruction under different sampling ratios, frequencies, transmit powers, and indoor layouts. The model is further checked on a real-world indoor Bluetooth Low Energy (BLE) RSSI dataset to examine real-data handling and floor-value sensitivity. A public CampusRSSI dense site-survey experiment is additionally included to evaluate sparse reconstruction against measured indoor WiFi RSSI radio maps under path-constrained sampling. The results show that the proposed method consistently outperforms classical path-loss modeling, interpolation, Kriging, and encoder–decoder baselines, especially when only a small fraction of measurement locations is available. Robustness and generalization analyses further examine imperfect propagation priors, clustered sparse measurements, structured measurement noise, and more challenging unseen evaluation settings. These findings support propagation-prior-guided model-aided learning as a practical approach for low-cost IoT radio-map construction and wireless signal management.
Ming-Kun Lu, A. Taparugssanagorn· IEEE Access· 0 citations
A channel knowledge map (CKM) provides location-specific channel priors and can reduce the overhead of real-time channel state information (CSI) acquisition for 6G environment-aware communications. In practice, CKM generation is often constrained by sparse and noisy measurements due to the high cost of wireless data collection. In this paper, we propose PDiff, a physics-informed conditional diffusion framework for CKM generation under sparse observations. Specifically, PDiff incorporates an analytical free-space propagation prior to capture the dominant distance-dependent attenuation trend, and combines it with environmental geometry, observation masks, and sparse observations as structured conditions. These conditional inputs guide the generation process with explicit propagation-aware, environmental, and measurement constraints. To improve inference efficiency, we further develop Prop-Cache, a training-free acceleration mechanism that reuses slowly varying intermediate features across denoising steps to reduce redundant computation during sampling. Experiments on RadioMapSeer demonstrate that PDiff outperforms a wide range of baseline methods for CKM generation.
Yu Chen, Jiao Chen, Jian Tang et al.· IEEE Transactions on Network...· 0 citations
Radio map construction aims to infer dense received-power fields from environmental layouts, sparse observations, and physical priors. While crucial for environment-aware wireless systems, it remains challenging in complex urban scenes with building-induced non-line-of-sight (NLOS) shadows and dynamic blockages. Non-iterative methods, such as interpolation techniques, RadioUNet, and RME-GAN, often struggle to accurately model these complex obstruction effects. Conversely, iterative generative methods tend to produce physically implausible hallucinations in shadowed or strongly obstructed areas. To address these issues, we propose LSK-RM, a physics-guided Large Selective Kernel U-Net for one-stage dense radio map reconstruction. Specifically, an LSK-based encoder-decoder is introduced to adaptively aggregate local shadow-boundary details and long-range attenuation context within a single forward pass. Furthermore, we develop a multi-source physical prior representation that fuses environmental geometry, sparse measurements, and fast ray-tracing visibility cues. To suppress physically implausible energy leakage, we design a novel logarithmic physics-guided objective combining pixel-wise supervision with Laplacian and obstacle-boundary consistency. Experiments on the RadioMapSeer dynamic blockage dataset demonstrate that LSK-RM outperforms representative baselines, including RadioUNet, RME-GAN, RMDM, and RadioFlow. Notably, it achieves higher accuracy across quantitative metrics such as NMSE, and exhibits significantly better modeling performance in diffraction transitions and shadow regions.
Zhengyan Liao, Weidong Zou, Chunlei Wang et al.· 2026 8th International Confe...· 0 citations
Wireless localization in complex propagation environments remains challenging due to the heterogeneous channel-location relationships induced by varying propagation conditions. Conventional unified localization models often fail to adequately capture such condition-dependent characteristics, leading to degraded positioning accuracy and limited robustness. To address this issue, this letter proposes a probabilistic condition-aware dual-branch localization framework that explicitly incorporates propagation uncertainty into the localization process. By modeling the location posterior as a mixture of LOS- and NLOS-conditioned predictors and adaptively fusing their outputs via a learned probabilistic router, the proposed approach enables propagation-aware localization without requiring explicit state observation at inference. A two-stage training strategy ensures stable learning of state-specialized representations and routing weights. Experiments demonstrate that the proposed method consistently outperforms both unified regression and hard-decision baselines, particularly in challenging NLOS scenarios. Source code is available at https://github.com/jzengust/Res-SR.
Yaping Zhu, Yilong Chen, Jin Zeng et al.· IEEE Communications Letters· 0 citations
Radio maps, which estimate spatial radio-frequency characteristics from spectrum measurements, are essential for applications such as spectrum management and network planning. With the continuous arrival of spectrum measurements, conventional batch processing methods for radio map reconstruction become computationally prohibitive, as they require reprocessing all accumulated measurements for each radio map update. To address this, we propose a memory-based online sparse variational Gaussian process (M-OSVGP) method that efficiently updates radio maps from streaming spectrum measurements. Our method employs sparse variational inference and updates the posterior online by minimizing a hybrid objective that integrates newly received measurements and a memory subset of previous ones to mitigate catastrophic forgetting. To further improve posterior approximation as measurements accumulate over spatially diverse regions, we extend M-OSVGP with a grid-assisted online inducing point selection (GOIPS) algorithm. GOIPS dynamically adapts the number and locations of inducing points based on measurement density and spatial correlation, providing a more informative inducing set while maintaining computational efficiency. Extensive simulations demonstrate the effectiveness of our proposed methods in reconstruction accuracy, computational efficiency, and uncertainty quantification, compared to existing batch and online baselines across various scenarios.
Yuanyuan Deng, Bo Zhou, Tianjun Chen et al.· 0 citations
This work introduces a physics- and tail-informed VAE-EVT (variational autoencoder-extreme value theory) framework that distinctly models both the bulk and tail distribution of SNR, and significantly outperforms the state-of-the-art GAN-based model.
A. Gamage, Niloofar Mehrnia, James Gross· 0 citations
