Model-Aided Learning for Sparse Received Signal Strength Indicator Radio Map Prediction and Wireless Signal Management in Internet of Things Environments
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, support propagation-prior-guided model-aided learning as a practical approach for low-cost IoT radio-map construction and wireless signal management.
Abstract
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.
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.
Liu Yang, Qiang Li, Zhuo Cao et al.· IEEE Transactions on Wireles...· 0 citations
Wireless localization is expected to play a key role in future communication systems by providing location-aware services and supporting efficient network operation. However, existing deep learning (DL)-based localization methods often suffer from limited generalization when the deployment environment changes, since they tend to learn environment-specific propagation patterns. To address this issue, this article proposes an environment-aware generalized wireless localization framework that jointly exploits wireless channel, base station (BS) geometric information, and environmental information. Irregular city structures are represented by voxel-based occupancy maps, enabling explicit modeling of environmental factors that affect radio propagation. A transformer-based architecture is developed to comprehensively process wireless channel, geometric information of network nodes, and environmental information, thereby capturing the interaction between channel observations and surrounding urban structures. In addition, the proposed framework estimates a confidence map instead of directly regressing user equipment (UE) coordinates, which improves robustness under ambiguous propagation conditions. To support training and evaluation, we also develop an urban environment generator and a ray tracing-based channel simulator that produce large-scale datasets with physically consistent alignment between channels and 3-D environments. This framework enables systematic evaluation and robust localization in previously unseen urban environments.
Y. Noh, Kae Won Choi· IEEE Internet of Things Jour...· 0 citations
Automated spectrum management systems such as radio dynamic zones must infer where transmitters are and what the spatial spectrum usage looks like within a frequency band from only a handful of monitoring sensors. This paper presents an iterative likelihood-ratio detection pipeline that first performs localization from sparse power measurements without training data and subsequently reconstructs the radio-map. The region is discretized into candidate cells, and the sensor powers follow a linear model whose sparse support is the set of active transmitters. The pipeline detects transmitters one at a time by scoring every cell with a single-source generalized likelihood ratio test (GLRT), uses beam search and physics-based filters to avoid committing early to a wrong cell, and reconstructs the power field from the recovered sources. Because the channel enters only through a precomputed propagation matrix, log-distance, terrain-integrated rough earth model (TIREM), and Sionna ray-tracing models are interchangeable inputs. The pipeline is evaluated on real POWDER-testbed measurements of five fixed transmitters in a semi-urban environment spanning roughly 2.6 km by 2.9 km, discretized into a 5 m grid of about 305,000 candidate cells, at two sparse sensor densities of 10 and 30 sensors that sample on the order of 0.01% of the grid. The pipeline reconstructs the power field to 13.8 dB RMSE at 30 sensors, and per-transmitter detection probability ranges from 0.95 for the best-positioned source down to near zero for spatially distant ones. Substituting an environment-aware propagation matrix recovers a distant transmitter’s detection probability to 0.67 with no added sensors. Since the detector consumes only received-power readings, it transfers directly to emerging low-cost sensing technologies such as RFID and backscatter sensor networks, a practical way to achieve denser monitoring that would improve the detection rates further.
Serhat Tadik, Gregory D. Durgin· IEEE Journal of Radio Freque...· 0 citations
A deep learning-based approach is presented that optimizes environmental input construction for accurate channel path loss prediction and validate that the input feature construction improves channel prediction accuracy and provides guidance for future intelligent channel prediction.
Zhicheng Qiu, Rui-Si He, Bo Ai et al.· npj Wireless Technology· 0 citations
Wireless signal reconstruction is essential for RF-based positioning in GPS-denied environments. However, multipath propagation, shadowing, and non-Gaussian noise complicate this, and traditional methods require extensive site-specific calibration that precludes rapid deployment. We present In-Context Signal Completion (ICSC), demonstrating that small language models fine-tuned with Group Relative Policy Optimization and physics-informed rewards can reconstruct RSSI across sequential extrapolation and spatial interpolation tasks. Our 0.5B-parameter model attains 55% recall within 2 dB and a 2.85 dB mean absolute error on sequential prediction. This achieves a 49% error reduction over the untrained baseline, performing on par with GPT-4o (51%) with fewer parameters. Successful zero-shot transfer to spatial interpolation indicates the model acquires transferable physical reasoning rather than task-specific memorization. Operating at 3 ms latency for real-time edge inference, ICSC reduces deployment from weeks of per-site data collection to immediate inference using sequential context.
Indoor positioning using commodity Wi-Fi infrastructure is attractive for smart buildings and Internet of Things applications, but the practical accuracy of Wi-Fi Fine Timing Measurement (FTM) remains limited by non-line-of-sight propagation, multipath delay, access-point-dependent ranging bias, and unstable anchor geometry. This paper proposes a measurement-reliability learning and geometry-constrained fusion framework, termed MRL-GCF, for robust horizontal Wi-Fi FTM indoor localization. MRL-GCF learns the reliability of each access-point observation from a multi-factor representation that includes Received Signal Strength Indicator (RSSI), logarithmic FTM range, short-window range stability, RSSI fluctuation, access-point visibility, abnormal-range tendency, and coarse anchor geometry. A lightweight heteroscedastic neural calibrator estimates both range bias and observation uncertainty. A supervised reliability-regime head is further trained from residual-regime soft targets, and its entropy is used as a propagation-ambiguity measure. The learned uncertainty is fused with propagation ambiguity, map obstruction, material-aware obstruction cues, and anchor geometry to select reliable anchors and construct a trust-weighted nonlinear least-squares localization objective. To avoid overestimating performance from repeated scans at identical survey points, both scan-level and point-held-out protocols were adopted. Experiments were conducted in a lobby, a classroom, and a dormitory using 4410 synchronized RSSI-FTM scans. On 882 scan-level test queries, MRL-GCF achieved mean absolute errors of 0.88 m, 0.55 m, and 1.20 m, with sub-3 m success rates of 98.0%, 99.0%, and 96.5%, respectively. Additional replay-based dynamic, temporal, cross-device, AP-density, uncertainty-calibration, map-availability, and coefficient-sensitivity analyses were included to examine deployment-oriented robustness. These results indicate that learning measurement reliability while preserving geometric constraints provides a practical and interpretable solution for robust Wi-Fi FTM indoor positioning.
