Model training for Device-Free Localization (DFL) and Radio-Frequency (RF) sensing systems heavily relies on large-scale datasets, which are costly and time-consuming to obtain through measurements across different environments and sensing configurations. Lightweight yet physically consistent propagation models are therefore critical for efficient generation of realistic RF sensing data. This paper presents an RF sensing prediction approach for indoor environments based on a Body of Revolution (BoR) human model. A fast 2.5-Dimensional Finite Element Method (2.5-D FEM) is proposed for computing the scattering fields of a human-like BoR model under the excitation of a vertical polarized dipole. Through comparisons, the proposed BoR model is shown to preserve scattering characteristics close to 3-D human bodies while yielding a smaller computational cost compared to a simple cylindrical model. A measurement-driven background-field modeling approach is further introduced for practical indoor applications, accounting for the complex propagation effects of indoor environments implicitly. Comparing with measurements of a typical indoor DFL scenario, the proposed approach achieves approximately 85

Model training for Device-Free Localization (DFL) and Radio-Frequency (RF) sensing heavily relies on large-scale datasets, which are difficult, expensive, and time-consuming to obtain through measurements. This paper proposes a fast 2.5-dimensional Finite Element Method (2.5-D FEM) for computing the scattering fields of a Body of Revolution (BoR) human model under the excitation of a z-directed dipole. The proposed method can evaluate the effect of human micro-movements through the statistical characteristics of the Received Signal Strength Indicator (RSSI). The numerical accuracy and the practical applicability of the proposed method are validated through comparisons with full-wave simulations and indoor RF sensing experiments. The simulation results show agreement with the experimental measurements, demonstrating that the method is a reliable tool for evaluating micro-movement-induced statistical variations. The proposed method provides a practical and efficient means for generating large-scale, labeled RF training datasets, thereby accelerating the development of indoor localization tools as well as the calibration and tuning of tomographic reconstruction methods.

Consensus algorithms are widely used in distributed optimization for large-scale problems such as sparse estimation, ridge regression, and optimal control. In these settings, regularization is employed to enforce task-specific structural constraints on the decision variables, with prior work focusing primarily on promoting sparsity or low-energy solutions. However, less attention has been devoted to achieving consensus on the regularization policy adopted across the network. This paper introduces a novel consensus-based algorithm with $\ell ^{1}$ and $\ell ^{2}$ regularization. The proposed mechanism adaptively controls the trade-off between sparsity and energy of the solution, by reaching a consensus on the weight-mixing parameter. We prove convergence of the dual-layer consensus process and link the distributed regularization dynamics to opinion formation in social learning. The effectiveness of the proposed Distributed Composite Regularization (DiCoR) algorithm is demonstrated on the Low Rank Matrix Completion problem (LRMC) using real image datasets under both centralized and decentralized architectures. The DiCoR approach is also compared against frameworks that employ distributed $\ell ^{1}$, $\ell ^{2}$ dynamic regularization and ElasticNet. We demonstrate that our approach achieves superior image-reconstruction quality measured in terms of Peak-Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Metric (SSIM), across multiple scenarios.

RF sensing exploits phase-sensitive measurements of stray electromagnetic (EM) fields from wireless devices across various frequency bands to detect EM blockage and to reconstruct and map the surrounding environment in 2D/3D. Although blockage effects caused by objects or human motion are well-studied in ISM bands and frequencies up to 60 GHz, there is a significant lack of research for frequencies above 100 GHz. The paper proposes a unified signal processing framework for RF sensing in the sub-THz D-band (105–175 GHz), explicitly integrating EM blockage and scattering as a single process through the birth-death dynamics of multipath components (MPCs). The framework extracts, associates, and classifies MPCs from angle-delay measurements using statistically grounded detection and classification, enabling human-scale sensing from a single radio link. The modeling and classification of MPCs, along with large-scale EM parameters, are demonstrated through an indoor measurement campaign using multiple test targets. Experimental results show that newly formed, attenuated, and suppressed MPCs can be reliably identified with millimeter-scale delay resolution. Static object localization achieves average positioning errors of 8-20 cm depending on range and material, while passive human localization yields errors of 12-17cm at 0.5m and 26-30cm at 2m, respectively. The proposed framework demonstrates that accurate sensing and localization are feasible at sub-THz frequencies using a single link.

Radio Frequency (RF) sensing is an emerging technology paradigm to utilize electromagnetic signals scattered off objects or subjects for sensing. The technology repurposes existing wireless communication networks for imaging and computer vision applications, namely ambient human sensing. For communication systems (i.e., cellular, Wi-Fi), this results in a ubiquitous sensing infrastructure, able to "photograph" an environment, connect stimuli to a larger local, national or global picture, and to track subjects seamlessly. The possible social and ethical implications may be surprising and drastic and are currently underexplored. The article showcases promising research directions in this new field and lays the groundwork for ethically compliant technology design, highlighting the challenges and potential solutions that can stimulate new research.

This paper proposes a 2.5-dimensional finite element method (2.5-D FEM) for computing human body scattering under plane-wave incidence from arbitrary directions. By modeling the body as a Body of Revolution (BoR) and applying azimuthal modal decomposition, the three-dimensional (3-D) problem is reduced to several independent two-dimensional (2-D) problems, significantly lowering computational cost while preserving key scattering features. The method provides an efficient tool for constructing human body scattering databases for wireless sensing and communication applications.

Radio Frequency (RF) sensing is attracting interest in research, standardization, and industry, especially for its potential in Internet of Things (IoT) applications. By leveraging the properties of the ElectroMagnetic (EM) waves used in wireless networks, RF sensing captures environmental information such as the presence and movement of people and objects, enabling passive localization and vision applications. This paper investigates the theoretical bounds on accuracy and resolution for RF sensing systems within dense networks. It employs an EM model to predict the effects of body blockage in various scenarios. To detect human movements, the paper proposes a deep graph neural network, trained on Received Signal Strength (RSS) samples generated from the EM model. These samples are structured as dense graphs, with nodes representing antennas and edges as radio links. Focusing on the problem of identifying the number of human subjects co-present in a monitored area over time, the paper analyzes the theoretical limits on the number of distinguishable subjects, exploring how these limits depend on factors such as the number of radio links, the size of the monitored area and the subjects physical dimensions. These bounds enable the prediction of the system performance during network pre-deployment stages. The paper also presents the results of an indoor case study, which demonstrate the effectiveness of the approach and confirm the model's predictive potential in the network design stages.

Human localization is gaining momentum in security, healthcare, logistics, and smart spaces applications. While global navigation systems are unreliable indoor, device-free (a.k.a. passive) localization methods that exploit human-induced perturbations of radio propagation can be effectively used. This paper investigates the use of a compact full-wave electromagnetic (EM) setup as a fast and reliable tool to simulate indoor Wi-Fi propagation for human sensing. The goal is to provide a practical baseline for validating simplified propagation models, such as diffraction-based descriptions, and to reduce the need for costly measurement campaigns. Two-dimensional attenuation maps from received signal strength are generated and compared in controlled environments, focusing on attenuation statistics and interference patterns. The simulations reproduce the main spatial features, though discrepancies remain due to simplified material characterization. Diffraction-aware refinements are proposed to mitigate these effects. Overall, the approach provides an efficient pre-measurement reference to support device-free system design and to guide experimental planning.

Federated Learning (FL) has emerged as a promising paradigm for preserving client data ownership and control over distributed Internet of Things (IoT) environments. While discriminative models dominate most FL use cases, recent advances in generative models – such as Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and Diffusion Models (DM) – offer new opportunities for unsupervised anomaly detection in time series analysis, with relevant applications in predictive maintenance (PdM) in critical industrial infrastructures. In this work, we present a comprehensive analysis of VAEs, GANs, and DMs in the context of federated PdM. We analyze their performance and communication overhead under both full and partial federation setups, where only subsets of model components are shared. Building on this analysis, the paper proposes a novel taxonomy for federated generative models that formalizes partial component sharing as a principled mechanism for model personalization. Our experiments over a real-world time series dataset reveal distinct trade-offs in model utility, stability, and scalability, especially in heterogeneous and bandwidth-constrained FL settings. For the evaluated GAN-based configurations, full federation improves training stability relative to independent local training, although the model remains less robust than the VAE- and DDPM-based alternatives. For DMs, however, partial federation – especially decoder sharing – can outperform full federation in bandwidth-constrained, non-IID settings.

Improving sensing performance in the 27.5 to 60 GHz frequency range remains challenging in integrated sensing and communication (ISAC) systems due to complex propagation conditions and signal variability. Smart reconfigurable environments, which allow control over the channel's propagation characteristics, offer a promising approach to enhance sensing accuracy. This paper emphasizes the key role of engineered surface in indoor environments with existing wireless infrastructure at 27.5–60 GHz, demonstrating their importance for practical passive localization in ISAC systems. Ray tracing simulations are performed to evaluate the power delay profile (PDP) and assess the influence of engineered surface on signal propagation in the presence of a human body. To achieve more intelligent and controllable coverage, smart electromagnetic surface (SES) is designed and characterized at these frequencies, and their functionalities are thoroughly analyzed. Building on these results, a clear direction for future work is the integration of SES tailored to specific environments and frequency ranges into ray tracing to further validate and prototype practical ISAC scenarios.

This letter proposes an approximate model based on electromagnetic scattering superposition for multi-target indoor passive Radio Frequency (RF) sensing scenarios, aiming to predict the influence of multiple human bodies on wireless network link signal strengths. A Line-of-Sight (LoS) condition is presented to simplify the compensation of shadowing effects. The scattering superposition model is validated numerically with a full-wave EM solver under different numbers of targets, separation distances, and occlusion conditions. The overall approximate framework is further validated against indoor measurements, showing good agreement in both Received Signal Strength Indicator (RSSI) and spatial variation trends across different link configurations. The proposed model provides a lightweight and computationally efficient solution for multi-target RF sensing, enabling low-cost yet accurate generation of large-scale synthetic databases for the training of machine-learning-based RF sensing networks with specific applications to people detection, people trajectory tracking, and RF tomography.

Smart Radio Environments (SREs) are a foundational paradigm for the Internet of Everything (IoE), in which dense, phase-coherent antenna arrays form a shared infrastructure for integrated sensing and communication (ISAC). Radio-Frequency (RF) holography is a core sensing building block for SREs: it reconstructs a volumetric map of the electromagnetic (EM) scattering scene from phase-sensitive field measurements, an infrastructural snapshot from stray RF radiation, without dedicated sensors. To make reconstructions accurate and rapidly adaptable, this paper adopts algorithm unrolling, in which the iterations of a classical holographic solver become the layers of a compact, trainable deep network that preserves the EM physical interpretation and learns only a few parameters from limited data. Building on the unrolled Iterative Shrinkage-Thresholding Algorithm (ISTA), namely Learned ISTA (LISTA), this paper first proposes a Weighted LISTA (W-LISTA) that preserves the EM forward model and learns a spatially-varying regularization that steers the sparsity prior towards target shapes consistent with the deployment. Second, the Low-Rank Weighted LISTA (LoRaW-LISTA) applies a low-rank adaptation (LoRa) of the holographic operator to compensate for model mismatch from linearized EM approximations. Both methods are validated on full-wave EM simulations and on a 2.45 GHz indoor campaign with human-body phantoms, improving accuracy and resolution over baselines. Combining the spatially-varying regularization of W-LISTA with the LoRa adaptation of the EM model yields superior reconstruction where classical iterative solvers fail. The proposed tools are rapidly adaptable building blocks for the SRE sensing layer, whose reconstructions, up to body-shape imaging, remain privacy-preserving by design.

The FedAdamPID algorithm resolves the overshoot problem suffered by the FedAdam algorithm under the framework of PID control. The research on FedAdamPID explores the connection between PID controllers and the process of federated learning algorithms, particularly applying it to the update rules on the server side. This study draws on the previous research of the research group, first establishing a connection between the local update process of the client and the PID controller, and then viewing the entire FL process involving both the client and the server as a multi-PID coupled system. On this basis, the minimum update difference and the dynamic adjustment strategy of the local learning rate are introduced, and an optimized algorithm, FedAdamPID-op, is proposed. Experiments on multiple standard datasets have verified that this optimized algorithm slightly outperforms FedAdamPID in terms of accuracy and the number of convergence rounds.

Federated learning (FL) can be used to distribute machine learning (ML) tasks across edge and Internet of Things (IoT) devices with limited resources. FL provides an alternative and much more practical solution to classical artificial intelligence (AI), which requires moving large data volumes to energy-hungry data centers. On the other hand, sustainability of FL processes should be accurately quantified as limiting energy consumption might require sacrificing accuracy. This article proposes a framework for real-time monitoring of energy and green house gas (GHG) emissions (carbon footprints) of FL systems. The framework is developed for both classical FL policies relying on the parameter server and emerging fully decentralized ones. The proposed approach considers, for the first time, the impact of ML model quantization and sparsification on the energy/carbon budget while also discussing novel gradient tracking (GT) FL strategies that are robust to data heterogeneity but require higher communication bandwidth. General guidelines for energy-efficient designs are discussed based on several case studies on real datasets. This article quantifies the energy footprint of continual FL processes that implement periodic adaptation on new data as foreseen by emerging IoT industry verticals. Results show that centralized FL is advantageous when strict carbon budgets are imposed or energy-inefficient (<50 Kbit/Joule) communication protocols are adopted. GT mechanisms are to be preferred in heterogeneous data environments and decentralized setups. Finally, using FL for continual model fine-tuning provides large energy savings (>80%), provided the ML model compression is properly tuned.

Recently, the development of techniques to capture and process wireless stray electromagnetic (EM) radiation from different radio sources is gaining increasing attention. RF sensing is, for example, an emerging paradigm that transforms existing wireless networks by adding sensing modalities to improve the perception of users and the environment. Stray fields of wireless devices in arbitrary frequency bands are recorded in a phase-sensitive manner and visualized in 3D to reconstruct or map the surrounding environment. These techniques can be generally exploited to transform radio networks into virtual radio sensors to allow mapping of objects, human-scale sensing, behavior recognition, and crowd density estimation. Ubiquitous perception through RF signals is a pivotal opportunity for future technology: it enables personalized services such as smart living, automated logistics or interaction through free-space gestures. However, it also challenges ethical and moral boundaries and threatens privacy. The workshop encourages authors from academia and industry to submit manuscripts on innovations on radio sensing, holography, networks, and computing techniques for privacy-selective human scale sensing. Analysis of social implications of the technology are also welcomed.

Bayesian Federated Learning (FL) policies enable multiple nodes to collaboratively train a shared Machine Learning (ML) model while accounting for the uncertainty of its predictions. This is accomplished by estimating the global posterior distribution in the model parameter space. Currently, Bayesian FL strategies are impaired by large communication costs that need to be reduced to provide more sustainable training platforms. This letter investigates the impact of compression strategies in centralized Bayesian FL setups, where a Parameter Sever (PS) is tasked to supervise the learning process. The goal is to study how compression affects the ability of Bayesian FL systems to provide high-quality, yet well-calibrated ML models. The analysis is carried out in the healthcare domain, where the prediction reliability is particularly critical, focusing on a medical imaging task. Numerical results show that applying aggressive compression policies highly reduces the ability of Bayesian FL systems to provide accurate and reliable ML models. On the contrary, light compression stages maximize accuracy and calibration at the cost of larger communication overheads.

Radio Frequency (RF) sensing is an emerging technology paradigm that repurposes existing wireless communication networks, such as WiFi, for imaging and computer vision applications, namely ambient and human sensing. Recent research has demonstrated that RF holography techniques can surpass human vision capabilities in several tasks such as identifying and resolving individuals within dense crowds, interpreting gestures and emotions, and capturing images through walls. The paper explores the use of pattern-reconfigurable antenna devices with unmodified WiFi signals for indoor people discrimination, namely counting the number of people co-present in the space. We discuss signal modeling, integration of beam-steering technology, and adaptation for this purpose. Initial case studies and analyses within a test-house environment are also presented.

As robots become increasingly prevalent in both homes and industrial settings, the demand for intuitive and efficient human-machine interaction continues to rise. Gesture recognition offers an intuitive control method that does not require physical contact with devices and can be implemented using various sensing technologies. Wireless solutions are particularly flexible and minimally invasive. While camera-based vision systems are commonly used, they often raise privacy concerns and can struggle in complex or poorly lit environments. In contrast, radar sensing preserves privacy, is robust to occlusions and lighting, and provides rich spatial data such as distance, relative velocity, and angle. We present a gesture-controlled robotic arm using mm-wave radar for reliable, contactless motion recognition. Nine gestures are recognized and mapped to real-time commands with precision. Case studies are conducted to demonstrate the system practicality, performance and reliability for gesture-based robotic manipulation. Unlike prior work that treats gesture recognition and robotic control separately, our system unifies both into a real-time pipeline for seamless, contactless human-robot interaction.

The adaptation of learning rate can significantly enhance the performance of deep neural networks, especially in intricate environment of federated learning (FL) with diverse client settings. Therefore, the hyperparameter optimization is a critical component in FL. Distributed iterative optimization algorithms for FL encounter issues such as slow convergence due to inter-node coupling, as well as diminished inference accuracy. Furthermore, the reliance on laborious empirical learning rate adjustment results in weak adaptability to changing environments and slow responsiveness to dynamic conditions. In this work, we propose Fed-PID, a novel PID controller based adaptive learning rate scheduler for FL. Fed-PID employs distributed feedback control and PID technique to re-express distributed iterative optimization algorithms as distributed PID controllers. By equivalently transforming multiple coupled control systems into an extended dimensional error system, it converts the federated aggregation convergence problem into a consensus control problem. We design Server Side Parameter Scheduler (SSPS) to automatically adjusts the P, I, and D parameters for all clients by minimizing the extended dimensional error system from a global perspective and design Client Side Parameter Schedulers (CSPS) to automatically tune hyperparameters during local training from a micro perspective. Extensive experimental results on three public datasets and our self-built cobot radar localization dataset demonstrate that Fed-PID consistently outperforms FedAvg and other baseline methods. In particular, Fed-PID outperforms its competitors by 3.6% accuracy on CIFAR-10 and 5.85% on Cobot dataset under the Non-IID setting.

Holographic imaging at Wi-Fi frequencies requires measurements of the scattered fields on large and densely sampled surfaces, e.g., the walls and ceiling of a room, enclosing a scenery of interest. Hardware realizations of the measurement instrumentation are complex, and data acquisition with moving probe antennas often requires acquisition times in the order of days. Thus, pre-deployment testing and development of imaging algorithms on the basis of synthetic data is desired. However, in the context of highly-echoic indoor scenarios such as domestic or office environments, it is unclear how detailed simulation models have to be in order to provide data of sufficient accuracy. We investigate scattering at low Wi-Fi frequencies of around 2.4 GHz and at a human phantom within an echoic office room. The quality of images generated from a simplistic simulation model and from real-world measurements are compared. The results indicate that similar images can be obtained from simulations without precise knowledge of the geometry of the scenery and of material properties.