Label-Efficient School Detection from Aerial Imagery via Weakly Supervised Pretraining and Fine-Tuning

Accurate school detection is essential for supporting education initiatives, including infrastructure planning and expanding internet connectivity to underserved areas. However, many regions around the world face challenges due to outdated, incomplete, or unavailable official records. Manual mapping efforts, while valuable, are labor-intensive and lack scalability across large geographic areas. To address this, we propose a weakly supervised framework for school detection from aerial imagery that minimizes the need for human annotations while supporting global mapping efforts. Our method is specifically designed for low-data regimes, where manual annotations are extremely scarce. We introduce an automatic labeling pipeline that leverages sparse location points and semantic segmentation to generate infrastructure masks from which we generate bounding boxes. Using these automatically labeled images, we train our detectors on a first training stage to learn a representation of what schools look like, then using a small set of manually labeled images, we fine-tune the previously trained models on this clean dataset. This two stage training pipeline enables large-scale and strong detection in low-data setting of school infrastructure with minimal supervision. Our results demonstrate strong object detection performance, particularly in the low-data regime, where the models achieve promising results using only 50 manually labeled images, significantly reducing the need for costly annotations. This framework supports education and connectivity initiatives worldwide by providing an efficient and extensible approach to mapping schools from space. All models, training code and auto-labeled data will be publicly released to foster future research and real-world impact.

Frequency Diverse Arrays: Fundamentals, Key Insights, and Future Directions

Frequency diverse arrays (FDA) have attracted sustained interest as a promising architecture for introducing range-dependent responses into array systems. Unlike conventional phased arrays (PA), whose transmit behavior is primarily angle-dependent, FDA employs inter-element frequency offsets to generate time-and range-dependent phase structures, thereby producing a joint time-range-angle array response. Despite extensive research, the physical meaning of FDA-induced degrees of freedom remains debated, particularly in relation to range-angle coupling, the feasibility of time-invariant focusing, and the distinction between frequency-driven and waveform-driven range selectivity. This paper reexamines FDA from a structural and manifold-based perspective. A central contribution is the introduction of an irreducibility criterion, which distinguishes genuine range-domain physical degrees of freedom from effects that can be reproduced by equivalent signal-processing transformations. Based on this perspective, PA, multiple-input multiple-output (MIMO), FDA, and FDA-MIMO are comparatively interpreted according to the physical origin of their effective degrees of freedom, including spatial phase, waveform orthogonality, frequency gradients, and their interaction. The paper further clarifies the role of frequency across different array paradigms, contrasts FDA with time-coding-based architectures, and explains how key FDA properties such as manifold expansion, range--angle coupling, time variation, and multi-frequency diversity translate into system capabilities. Building on these structural insights, the paper connects FDA to a broad range of radar and communication functionalities, including parameter estimation, target detection, imaging, physical-layer security, and integrated sensing and communication.

Geometry-Aware Networking for Low-Altitude Economy: Movable Antennas in Space-Air-Ground Integrated Systems

Space--air--ground integrated networks (SAGINs) are emerging as a key foundation for future non-terrestrial networks (NTNs) and low-altitude economy services. However, their performance is increasingly limited not only by communication resources, but by the inability to adapt to rapidly changing spatial geometry. Here, spatial geometry refers to the relative configuration among network nodes, obstacles, and targets, which directly determines propagation conditions, blockage states, interference patterns, and sensing observability.This trend becomes more pronounced as low-altitude operations grow in density and complexity, causing the dominant bottleneck to shift from static resource allocation toward real-time maintenance of favorable spatial geometry across layers.In this article, we argue that movable antenna (MA) technology provides a fundamentally new perspective for SAGIN design. By enabling controlled antenna displacement, MA introduces a spatial degree of freedom that allows the network to directly adapt local spatial geometry at fine granularity, rather than passively reacting to it through beamforming or platform mobility.We present a geometry-aware, layered SAGIN architecture, where Low-Earth-Orbit (LEO) provides macro-scale coverage and coordination, High-Altitude Platform Stations (HAPS) enables regional continuity and backhaul support, and MA is incorporated into the layered design to enable fine-grained geometry adaptation, particularly at unmanned aerial vehicles (UAVs) and terrestrial layers where local channel dynamics are most pronounced. We further discuss how such geometry control enhances robustness, supports multi-functional operation spanning communication, sensing, control, and navigation, and enables more flexible spatial cooperation across layers.

Toward Environment-Aware LAE: SAR as a Shared Sensing Infrastructure

The rapid growth of the low-altitude economy (LAE) is making aerial systems an important part of future digital infrastructure. Although major advances have been achieved in unmanned aerial vehicle (UAV) platforms, communications, and autonomous control, environmental perception remains a key bottleneck to reliable and scalable LAE operations. Existing sensing modalities, such as optical, LiDAR, and millimeter-wave radar, are limited by visibility, sensing range, and environmental conditions, resulting in fragmented situational awareness. This article argues that addressing these limitations requires a shift from platform-centric sensing to a shared, environment-aware sensing infrastructure. In this context, synthetic aperture radar (SAR) offers a distinct advantage by enabling all-weather, wide-area perception. We show that SAR can support UAV operations through global environmental awareness, enhance task-level sensing, and enable cooperative sensing across satellites, high-altitude platforms, UAVs, and ground systems. Building on this perspective, we present a system-level view of SAR-enabled LAE, highlighting key transformations from fragmented to infrastructure-centric sensing, from reactive to predictive operation, and from device-centric to environment-aware networking. We further discuss enabling architectures, including multi-platform sensing hierarchies, integration with integrated sensing and communication (ISAC), and the role of artificial intelligence and digital twins, along with the key challenges toward real-world deployment. By positioning SAR as a shared sensing foundation rather than a standalone modality, this article provides new insights into the design of scalable, reliable, and intelligent LAE systems.

Activity Recognition Using mm-Wave Radar and Deep Learning: Prayer Tracker Case Study

The issue of privacy has gained significant attention in recent times. Many real-world applications increasingly require the use of sensitive data, such as in surveillance or tracking and assistance systems. To address these concerns, we propose a framework based on mm-wave radar technology that not only meets privacy requirements but also provides the necessary capabilities for these systems, including reliable current position tracking, sequence tracking, and feedback to the user. While the use of radar technology for surveillance purposes is gaining momentum, there has been no research to date on its application for prayer tracking and assistance systems. Furthermore, there is a lack of comprehensive research that covers all aspects of implementing such a system. Proposed approach offers a versatile solution that can be applied to a broad range of scenarios. Instead of utilizing raw I-Q data, we addressed the challenge of classification based on point cloud information generated by the conventional processing chain of the frequency-modulated continuous wave radar. This information contains corresponding range, reflection amplitude, Doppler and angular values. We have developed and compared different machine-learning classification algorithms to identify the most effective one. Our findings reveal that the convolutional neural network ResNet achieves the best results, with accuracy rates reaching up to 95.4 percent when applied to unknown data. The demonstration video of the developed system can be viewed at the following link: https://youtu.be/PnpGQZWqCr4.

Simultaneous Unicast and Multicast Transmissions in Stacked Intelligent Metasurfaces-assisted HAPS Wireless Networks: Performance Analysis and Optimization

In this paper, we investigate high-altitude platform station (HAPS) wireless networks for simultaneous non-orthogonal unicast and multicast transmissions. Specifically, stacked intelligent metasurface (SIM)-based wave-domain beamforming is proposed to enable efficient HAPS-to-ground communications. Also, the system performance is investigated from an energy-efficiency (EE) perspective, which is a crucial for HAPS operations. For performance analysis, we derive approximate closed-form expressions for the outage probability over Rician fading channels. For EE optimization, we jointly optimize the transmit power and the SIM phase-shifts for the maximal EE. Two methods are proposed to solve this non-convex optimization problem. The first method develops an efficient alternating optimization (AO) framework based on golden-section search and projected gradient ascent (PGA) for transmit power and phase-shift optimization, respectively. The second method uses unsupervised deep neural network (DNN) that does not require labeling. Performance comparison between the two methods, as well as with other benchmarks schemes are examined. Additionally, the impacts of the number of SIM elements per layers, the number of SIM layers, the maximum transmit power on the EE performance are evaluated. Simulation results are provided to demonstrate the performance of the proposed systems.

Wireless Energy Transfer from Space to Ground via Satellite Constellation Grids

This letter presents a framework for space-to-ground wireless energy transfer (WET) for wirelessly chargeable devices (WCD) located in remote areas or disaster situations. We consider a grid of multi-antenna satellites that charge a WCD within line-of-sight. Closed-form expressions for harvested energy are derived considering maximum ratio transmission (MRT) ensuring that the WCD meets its circuit charging threshold $P_{th}$. Simulations elucidate that milli-joule-level energy can be harvested during satellite grid visibility, with charging efficiency influenced by the number of satellites, their altitude, charging frequency, and grid inclination.

Movable-Antenna Index Modulation (MA-IM): System Framework and Performance Analysis

This paper proposes a movable-antenna-based index modulation (MA-IM) framework that exploits the spatial mobility of a single reconfigurable antenna to create additional information-bearing dimensions for next-generation wireless systems. By discretizing the continuous movable region into a dense set of candidate sampling points and selecting representative anchors for indexing, the proposed framework converts spatial degrees of freedom into a practical modulation resource. Building on this framework, we develop a family of anchor-selection strategies with different levels of channel awareness, including geometry-based, SNR-based, max--min channel-domain, and joint constellation-aware designs. For the resulting MA-IM schemes, joint maximum-likelihood (ML) detectors are derived, along with a low-complexity two-stage detector, and unified analytical upper bounds on the average bit error probability (ABEP) are established based on the joint index--modulation constellation. The results reveal that directly indexing all sampling points is generally unreliable, highlighting the necessity of anchor optimization. The performance of MA-IM is shown to depend on key system parameters, including channel richness, spatial correlation, the number of index states, and the modulation order. In particular, increasing the number of index states and increasing the QAM order affect MA-IM in fundamentally different ways, even under the same transmission rate. Among the proposed schemes, the joint constellation-aware anchor design achieves the best error performance, demonstrating that optimizing channel-domain separation alone is insufficient and that effective MA-IM design must account for the geometry of the joint signal constellation. Simulation results further show that, with properly designed anchors, MA-IM can approach or even outperform same-spectral-efficiency QAM baselines.

CRB-Based Resource Allocation in Multi-User Uplink Transmissions

In this work, we study the design of receivers for uplink multi-user systems, aiming to estimate both the channel and the transmitted symbols. We consider two estimation strategies: (i) a joint estimation approach, where the channel and symbols are estimated simultaneously, and (ii) a sequential estimation approach, where the channel is first estimated and then used for symbol detection. For both strategies, we derive the Cramér-Rao Bound (CRB) for symbol estimation to characterize fundamental performance limits. When efficient receivers achieving the CRB exist, these bounds provide accurate lower bounds on the mutual information. In general, however, such receivers may not be available, and we instead use these same CRB-based metrics as practical proxies for achievable throughput. Leveraging tools from random matrix theory (RMT), we analyze the asymptotic behavior of these lower bounds under various asymptotic regimes for both estimation strategies. This analysis enables the derivation of generic power allocation guidelines that asymptotically maximize the proxy metrics. Simulation results confirm the accuracy of the asymptotic expressions and their effectiveness in guiding resource allocation decisions.

Transformer-based Hybrid Beamforming with Dynamic Subarray for Near-Space Airship-Borne Communications

This paper proposes a hybrid beamforming framework for massive multiple-input multiple-output (MIMO) in near-space airship-borne communications. To achieve high energy efficiency (EE) in energy-constraint airships, a dynamic subarray structure is introduced, where each radio frequency chain (RFC) is connected to a disjoint subset of the antennas according to channel state information (CSI). The proposed joint dynamic hybrid beamforming network (DyHBFNet) comprises three key components: 1) An analog beamforming network (ABFNet) that optimizes the analog beamforming matrices and provides auxiliary information for the antenna selection network (ASNet) design, 2) an ASNet that dynamically optimizes the connections between antennas and RFCs, and 3) a digital beamforming network (DBFNet) that optimizes digital beamforming matrices by employing a model-driven weighted minimum mean square error algorithm for improving beamforming performance and convergence speed. The proposed ABFNet, ASNet, and DBFNet are all designed based on advanced Transformer encoders. Simulation results demonstrate that the proposed framework significantly enhances spectral efficiency and EE compared to baseline schemes. Additionally, its robust performance under imperfect CSI makes it a scalable solution for practical implementations.