Owing to its ability to offer collaborative data utilization while ensuring data privacy, federated learning (FL) provides a promising paradigm to enable cooperative intelligent tasks across multiple low-earth orbit (LEO) satellites, such as carbon estimation, traffic surveillance, and forest fire detection. Although the advantages of pushing intelligence to satellites are multi-fold, limited communication channels along with the rigid global model aggregation conditions result in dramatic convergence delays. In order to reduce the convergence time, we propose an asynchronous FL framework in LEO satellite networks by exploiting multiple high-altitude platforms for model aggregation, where the advanced over-the-air computation (AirComp) transmission scheme is utilized for the sake of further reducing energy consumption. Considering the practical constraint of AirComp signal distortion, the objective function of optimizing FL performance is carefully formulated and solved by the proposed quantity-quality jointed linkage search algorithm. Simulation results demonstrate that our proposed asynchronous FL framework outperforms the conventional synchronous FL framework by a decline of 30.07% in convergence time at most. It also provides an average increase of 110% and 580%, respectively, in terms of throughput and energy efficiency in all scenarios considered. Overall, our study presents a beneficial asynchronous FL framework and a fast aggregation scheduling algorithm in LEO satellite networks, accelerating the convergence of global model with reduced energy expenditure.

Unmanned Aerial Vehicle (UAV) swarms are key enablers for cooperative intelligent tasks in Internet of Everything (IoE) environments, like environmental monitoring and disaster response. Meanwhile, Digital Twin (DT) technology is rapidly advancing in academia and industry due to its potential to design, test, and optimize evolving IoE networks. While DT-empowered UAV swarms provide a compelling solution for complex tasks, challenges remain in jointly designing swarm control and service provision strategies, especially in dynamic IoE environments. To harness the potential of UAV swarm intelligence, we propose a DT-empowered cluster formation technique employing the Over-the-Air Computation (AirComp) transmission scheme for energy-efficient IoE data aggregation, where UAV and IoE device clusters are dynamically constructed and adjusted. Furthermore, we consider the limited power resources by maximizing energy efficiency, which leads to a joint cluster formation, multi-UAV trajectory design, and power allocation problem under the constraint of AirComp signal distortion. To efficiently solve this mixed-integer nonlinear fractional programming problem, we develop a low-complexity iterative algorithm based on the block coordinate descent method. Simulation results show that the proposed DT-empowered AirComp cluster formation technique achieves up to 42% higher energy efficiency and 34% greater throughput than the baselines, validating its potential for efficient data aggregation tasks.

Federated learning (FL) is a promising paradigm for collaborative intelligence in low-altitude economy, enabling unmanned aerial vehicle (UAV) swarms to perform deep learning tasks (e.g., logistics, emergency rescue) while preserving data sovereignty. However, limited communication channels and heterogeneous computation capabilities among UAVs cause significant FL aggregation delays. To reduce convergence time, we propose an asynchronous FL (AFL) framework for UAV swarms, integrating over-the-air computation (AirComp) to boost communication efficiency via simultaneous transmission. To address signal distortion in AirComp, we design an objective function solved via an aggregation scheduling algorithm, which transforms the nonconvex problem into two convex subproblems tackled via alternating optimization, to derive optimal aggregation strategies and beamforming vectors. Besides, to mitigate model staleness in AFL, which causes gradient divergence and slow convergence, we propose a self-adaptive aggregation scheme with staleness awareness, enabling UAVs to adjust local models autonomously without information from other UAVs. Simulation results show that our scheme not only reduces staleness impact but also leverages stale parameters, helping AFL outperform synchronous FL in convergence speed and accuracy. Overall, our study presents an effective AFL framework, a fast aggregation scheduling algorithm, and a self-adaptive aggregation scheme for UAV swarms, accelerating global model convergence while reducing energy expenditure.

Prolonged +Gz acceleration during high-performance flight exposes pilots to the risk of G-induced loss of consciousness (G-LOC), a dangerous condition that compromises operational safety. To enable early detection without intrusive sensors, we present a vision-based warning system that analyzes facial action units (AUs) as physiological indicators of impending G-LOC. Our approach combines computer vision with physiological modeling to capture subtle facial microexpressions associated with cerebral hypoxia using widely available RGB cameras. We propose a novel Graph Convolution-Augmented Vision Transformer (GC-ViT) network architecture that effectively captures dynamic AU variations in pilots under G-LOC conditions by integrating global context modeling with vision Transformer. The proposed framework integrates a vision–semantics collaborative Transformer for robust AU feature extraction, where EfficientNet-based spatiotemporal modeling is enhanced by Transformer attention mechanisms to maintain recognition accuracy under high-G stress. Building upon this, we develop a graph-based physiological model that dynamically tracks interactions between critical AUs during G-LOC progression by learning the characteristic patterns of AU co-activation during centrifugal training. Experimental validation on centrifuge training datasets demonstrates strong performance, achieving an AUC-ROC of 0.898 and an AP score of 0.96, confirming the system’s ability to reliably identify characteristic patterns of AU co-activation during G-LOC events. Overall, this contact-free system offers an interpretable solution for rapid G-LOC detection, or as a complementary enhancement to existing aeromedical monitoring technologies. The non-invasive design demonstrates significant potential for improving safety in aerospace physiology applications without requiring modifications to current cockpit or centrifuge setups.

Prolonged +Gz acceleration during high-performance flight exposes pilots to the risk of G-induced loss of consciousness (G-LOC), a dangerous condition that compromises operational safety. To enable early detection without intrusive sensors, we present a vision-based warning system that analyzes facial action units (AUs) as physiological indicators of impending G-LOC. Our approach combines computer vision with physiological modeling to capture subtle facial microexpressions associated with cerebral hypoxia using widely available RGB cameras. We propose a novel Graph Convolution-Augmented Vision Transformer (GC-ViT) network architecture that effectively captures dynamic AU variations in pilots under G-LOC conditions by integrating global context modeling with vision Transformer. The proposed framework integrates a vision-semantics collaborative Transformer for robust AU feature extraction, where EfficientNet-based spatiotemporal modeling is enhanced by Transformer attention mechanisms to maintain recognition accuracy under high-G stress. Building upon this, we develop a graph-based physiological model that dynamically tracks interactions between critical AUs during G-LOC progression. By learning the characteristic patterns of AU co-activation during centrifugal training. Experimental validation on centrifuge training datasets demonstrates strong performance, achieving an AUC-ROC of 0.898 and an AP score of 0.96, confirming the system’s ability to reliably identify characteristic patterns of AU co-activation during G-LOC events. Overall,this contact-free system offers an interpretable solution for rapid G-LOC detection, or as a complementary enhancement to existing aeromedical monitoring technologies. The non-invasive design demonstrates significant potential for improving safety in aerospace physiology applications without requiring modifications to current cockpit or centrifuge setups.