Papers

Integrated sensing and communication (ISAC) is a new paradigm for efficiently combining sensing and communication functionalities by leveraging shared hardware and radio resources. Despite its promise, ISAC yields conflicting beamforming goals and competition over the same resources. Movable antennas enable effective exploitation of spatial degrees of freedom through dynamic position/orientation control, thereby enhancing the performance of ISAC systems. This paper proposes a movable antenna framework for ISAC in air sea ground networks. A multi-objective optimization problem is formulated with the objectives of maximizing the communication rate of a set of aerial, sea, and ground devices and the sensing rate of a set of targets. The location and orientation of the antenna sub-arrays, as well as the transmit/receive beamforming, are optimized under practical constraints on the movable antennas' location and orientation. A solution is developed based on a $K$-means clustering approach to optimize the sub-arrays' orientation and a particle swarm optimization to place the sub-arrays in optimized locations. The transmit and receive beamforming are designed using a successive convex approximation and a generalized eigenvector method, respectively. Simulation results illustrate that the developed movable antenna framework improves the ISAC objective and provides a remarkable trade-off between the communication data rate and the targets' sensing rate when compared with the conventional stationary antenna array scenario.

This paper investigates the optimal safety control problem of nonlinear control systems by proposing novel high-order control barrier functions (HOCBFs). Different from zeroing HOCBFs, two novel HOCBFs are derived and the safety controllers are designed in an explicit way. Next, we implement vector Lyapunov function approach to propose a novel high-order control Lyapunov function (HOCLF) for the stabilization control problem. The relations between the proposed and existing HOCBFs are discussed. Afterwards, the compatibility of the proposed HOCLF and HOCBF is addressed to guarantee the stabilization and safety control objectives simultaneously, and thus the optimal controller is established. Finally, a numerical example from the navigation problem of quadrotors is presented to illustrate the efficacy of the derived results.

Security-constrained unit commitment (SCUC) couples binary commitment, economic dispatch, reserves, and network security over a multiperiod horizon, making an exact solution computationally expensive for realistic system sizes. This paper proposes a three-layer hybrid framework in which a Bernoulli hybrid soft actor-critic (HSAC) policy proposes hourly commitments, a quantum-sampled auxiliary channel augments the state, and a native SCUC mixed-integer linear program recovers dispatch and security variables after only a limited subset of commitment binaries is enforced. The method is therefore solver-compatible rather than an end-to-end replacement for exact optimization. We formalize the SCUC-to-reinforcement-learning interface, derive the temporal coverage induced by the fixed cap, and evaluate the 14- 57- and 118-bus benchmark cases. The results show stable, low-cost recovery in the 14-bus case, where the best recovered schedule attains the full-horizon optimum; a very low screen-rejection rate in the 57-bus case; and a clear coverage bottleneck in the 118-bus case once the enforcement cap no longer spans a complete commitment period. The study, therefore, identifies the amount of useful commitment information that reaches the recovery model, under an exploratory Bernoulli actor and a small enforcement cap, as the dominant limitation that governs scalability

Brain-computer interface neurofeedback (BCI-NFT) has shown promise for neuromotor rehabilitation, but its clinical adoption – particularly in pediatric populations – remains limited in part by the lengthy calibration required before each therapy session. This study developed and evaluated a deep-learning framework to reduce calibration requirements for movement-related cortical potential (MRCP)-based movement-intention detection in children with cerebral palsy (CP). Electroencephalography (EEG) was collected during repeated ankle dorsiflexion tasks across 27 sessions in four children with CP. A bidirectional long short-term memory (Bi-LSTM) network was evaluated using seven training strategies, ranging from conventional within-session calibration to cumulative cross-subject learning and transfer learning. Cross-subject cumulative learning achieved 91% accuracy without within-session calibration, while the addition of transfer learning increased accuracy to 93% with minimal within-session calibration. Both approaches significantly outperformed conventional calibration strategies and achieved the highest F1-scores and receiver operating characteristic (ROC) performance, demonstrating robust generalization across sessions and participants. These findings show that cumulative learning and transfer learning can substantially reduce calibration requirements while maintaining high decoding performance, supporting the development of clinically practical MRCP-based pediatric BCI systems

In many cases, the outage of one transmission line in a system can be localized by monitoring the power flow of another line, and machine learning methods can be used to distinguish the cases under uncertainty. In this study, we examine the improvements in line outage localization performance achieved by various ensemble classifiers compared to single-model methods. In the case studies, we compared the classification results with measurement data collected at observed transmission lines (OTLs) selected using three algorithms, i.e, greedy maximum coverage problem (MCP), high-eta, and random selection, based on two sensitivity factors, i.e., line outage distribution factors (LODFs) and line outage impact factors (LOIFs). We found that the OTLs selected by the greedy MCP algorithm yielded the highest F1 score and the ensemble classifiers significantly outperformed a base kNN classifier. The extra-trees bagging technique achieved the highest F1 score in many instances. All the findings were statistically significant.

This letter proposes an off-grid variational Bayesian (OVB) method for fractional delay-Doppler (DD) estimation in OTFS-based integrated sensing and communication (ISAC) systems. To enable off-grid parameter estimation, the OTFS channel is reformulated using separable delay and Doppler steering vectors, and the corresponding phase variables are modeled by von Mises distributions. Closed-form variational updates provide posterior statistics for identifying significant paths and pruning redundant candidates, enabling automatic path-number estimation. Simulation results demonstrate that the proposed method achieves higher channel and parameter estimation accuracy than conventional fractional DD estimation approaches.

Large-scale power networks are often organized by geography, ownership, or control authority, making stability certificates that require a fully assembled global model challenging. This paper develops a time-domain small-signal stability certification framework for grid-forming inverter networks with selectable clustering resolution. The objective is to certify stability at the same scale at which the network is organized and operated: each cluster verifies conditions using intra-cluster and limited boundary information, and these checks collectively yield a network-level stability certificate without requiring a global eigenvalue computation. After linearization about a phase-cohesive synchronized operating point, a small-angle approximation decomposes the model into a voltage subsystem and an angle-frequency subsystem, where the latter is certified by an energy argument using the symmetric weighted-Laplacian network structure. For the voltage subsystem, node-to-node gains are introduced and a cyclic small-gain argument yields a family of sufficient exponential stability certificates ranging from fully decentralized to cluster-based and centralized. For an arbitrary network partition, each cluster verifies intra-cluster directed-cycle conditions and inter-cluster path conditions. The singleton- and single-cluster limits recover the decentralized and centralized certificates, respectively. The resulting stability indices provide diagnostic information beyond a pass/fail verdict by localizing the limiting margin to individual nodes, internal feedback loops, and inter-cluster channels.

Over-the-air (OTA) computation has recently gained significant attentions as an effective approach to enhance the communication efficiency of wireless federated learning (FL). By enabling simultaneous transmission and aggregation of local model updates, OTA-FL can substantially reduce both latency and bandwidth consumption. However, a key challenge lies in the imperfect aggregation of global models caused by channel state information (CSI) uncertainty, which introduces distortion to the final learning performance. To address this issue, we study the long-term mean squared error (MSE) minimization problem for OTA-FL under imperfect CSI conditions. Through convergence analysis, we establish an upper bound for the time-averaged MSE, thereby revealing the effect of aggregation errors accumulated throughout multiple communication rounds on the overall training performances. Based on this analysis, an optimization framework is developed to minimize the long-term MSE via the joint design of (i) transmit coefficients at the local devices and (ii) receive combining vectors at the parameter server (PS). Since this alternating optimization approach requires non-causal CSI, a Lyapunov-based optimization method is further introduced to handle causal CSI scenarios. By incorporating virtual queues to characterize long-term energy consumption, the proposed method effectively decouples temporal dependencies and allows transmit coefficients to be optimized based on the causal CSI of each aggregation round. Comprehensive evaluations on Fashion-MNIST, CIFAR-10 and CIFAR-100 datasets have demonstrated that the proposed algorithms can significantly reduce the degradation of test accuracy caused by imperfect CSI. Comparisons with other benchmark schemes further verify the superiority of our proposed algorithms.

Audio-visual event recognition (AVER) has achieved significant performance improvements through transformer-based multimodal architectures. However, the high computational complexity, large memory footprint, and inference cost of these models hinder their deployment on edge and resource-constrained devices. This paper presents an efficient compression framework for hybrid cross-attention-based audiovisual event recognition by combining architectural model compression, knowledge distillation, and dynamic INT8 quantization. A high-capacity teacher model integrates VideoMAE for visual representation learning, the Audio Spectrogram Transformer (AST) for audio feature extraction, and a hybrid cross-attention fusion network for multimodal feature integration. A lightweight student model is constructed by reducing the hidden feature dimension, the number of attention heads, and the feedforward network size while preserving the overall network architecture. The student model is trained using knowledge distillation to effectively transfer discriminative knowledge from the teacher. Finally, dynamic INT8 post-training quantization is applied to further reduce the model size for efficient deployment. Experimental results on the Audio-Visual Event (AVE) dataset show that the proposed framework reduces the number of trainable parameters in the multimodal fusion module by 59.06%, with only a 2.14% decrease in classification accuracy compared with the teacher model. Furthermore, dynamic INT8 quantization reduces the model size from 10.71 MB to 2.04 MB while maintaining competitive recognition performance. These results demonstrate that the proposed framework provides an effective trade-off between recognition accuracy and computational efficiency, making it a promising solution for deployment on resource-constrained edge AI platforms.

Under stated assumptions, a static surface-code patch that adds no fold or \mbox{self-dual} structure cannot perform the magic-axis check that magic-state cultivation relies on while still accepting often. This is a conditional no-go. Fault-tolerant machines spend much of their cost making magic states, and cultivation makes them in place by measuring the magic axis, which every known construction does through a fold or \mbox{self-dual} patch that it is folklore to call necessary. We test the folklore. The no-go says that a useful check must pay for the magic axis somewhere. It can add a charge-converting resource, it can leave the dilute regime of its accepted history, or it can accept only exponentially rarely. For a single stabilizer-measurement transcript this is proved outright, from a topological reading of the accepted outcome. For adaptive, post-selected protocols in a bounded-depth (polynomial spacetime-volume) model, it holds under two structural assumptions plus a subcriticality assumption. We isolate the one open assumption, show that protection alone does not force it, and give the threshold any resolution must address. What remains is a single conjecture.

Interpretability is critical in clinical decision support. Concept bottleneck frameworks improve it by representing inputs as human-understandable concepts and restricting predictions solely on them. However, research on their use for voice-based health assessment remains limited. In this study, we propose a voice concept bottleneck framework for interpretable health assessment using an audio language model (ALM). The ALM is fine-tuned on a voice quality assessment dataset to enhance its understanding of voice concepts and serves as an independent concept extractor, producing discrete, interpretable scores for a lightweight downstream classifier. The discrete concept scores provide intuitive interpretation, while the lightweight classifier facilitates post-hoc interpretability analyses. Results on depression and dysarthria assessment tasks demonstrate that the proposed framework can flexibly adapt voice concepts to different health conditions and consistently outperforms openSMILE-based and self-supervised speech model-based baselines.

The tuned mass damper inerter (TMDI) is a passive vibration absorber that suppresses structural vibrations by leveraging the inertance property of inerter devices. Previous studies have demonstrated TMDI effectiveness in wind turbines, but relied on simplified structural models. To date, no study has implemented multi-directional TMDIs within aero-hydro-servo-elastic tools such as OpenFAST to enable independent vibration control across multiple turbine components, including the tower, blades, and substructure. This paper addresses this gap by implementing the TMDI in OpenFAST. The governing equations of motion are derived and implemented within the Structural Control (StC) Module, supporting arbitrary TMDI connectivity and independent multi-directional configurations across turbine components. Verification against independent numerical models confirms the implementation's accuracy across all supported configurations. An application study examines the IEA 15MW reference wind turbine equipped with a tower-top TMDI under combined wind-wave loading. Optimal tuning is performed using a simplified two-degree-of-freedom model, with modal properties extracted from an OpenSeesPy finite element model of the IEA 15MW. Results show that TMDIs with secondary mass up to 100 times smaller than a conventional TMD achieve matching or superior vibration suppression in the fore-aft and side-side directions, in terms of peak and standard deviation of tower-top displacement and acceleration. Notably, TMDI stroke is markedly reduced compared to the TMD, better suiting the spatially constrained wind turbine environment. These results support the practical merit of lightweight TMDIs for wind turbine vibration control, with the OpenFAST implementation enabling performance-driven design under realistic loading conditions.

Throughput prediction is foundational for artificial intelligence-driven 6G resource orchestration. Conventional monolithic machine learning models struggle to generalize across diverse operators, mobility modes, and traffic types, leaving a critical stochasticity gap between signal conditions and achievable throughput. To overcome these constraints in heterogeneous urban environments, we propose a Tiered Multi-Agent System (TMAS) that dynamically routes edge telemetry to context-aware Domain Micro-Agents, validated on a dataset of 48,618 samples collected in Sunway City, Malaysia, with Nemo Handy drive test software, spanning three Tier-1 mobile network operators, three mobility modes, namely (i) elevated pedestrian walkway, (ii) ground-level shuttle bus, and (iii) elevated bus rapid transit; and three traffic profiles, namely (i) persistent download, (ii) persistent upload, and (iii) adaptive video streaming. Our evaluations reveal that TMAS overcomes predictability bottlenecks, achieving a coefficient of determination (R2) of up to 0.931 and a Mean Absolute Error (MAE) as low as 0.53 Mbps. The system demonstrates high operational efficiency, with rapid micro-agent training times, low inference latencies, and agentic routing overhead of 0.004 to 0.126 ms. These latency characteristics indicate the architecture is a promising candidate for the response times required by next-generation wireless networks.

We develop the Cloud 3-Dimensional Imager Retrieval (C3DIR), a deep learning model that estimates 3-D cloud properties for multiple passive satellite imagers trained to match retrievals from the Earth Cloud Aerosol and Radiation Explorer(EarthCARE) ACM-CAP product. This work is aimed towards moving AI/ML 3-D cloud algorithms closer towards operational use. C3DIR predicts the occurrence water content of ice, cloud liquid, and rain along the imager line-of-sight and uses a voxel-level collocation approach to account for the misaligned viewing geometries of passive imagers and active profiling instruments. This precise collocation methodology allows for constructing vertical profiles using voxels contained by multiple imager pixels to facilitate comparisons with active profiling instruments. Qualitative case studies show that C3DIR can accurately depict multiple distinct overlapping cloud layers, albeit with some smoothing. Quantitative evaluations illustrate that C3DIR overall excels at hydrometeor detection which intuitively tends to be a function of water content. However, detection of voxels classified as liquid cloud remains difficult due to the their small geometric thickness, finer horizontal scale, and frequent tendency to be obscured or embedded within ice clouds. In general, water content estimation is reasonably accurate, yielding the best results in ice clouds but uncertainties remain for liquid and rain water content. Column-integrated water paths are in tighter agreement with EarthCARE. Comparisons with the algorithms underpinning current NOAA operational products highlight several areas where C3DIR may offer improvement. Overall, these results demonstrate the potential for C3DIR to provide flexible 3-D output depicting vertically resolved cloud structure which can offer broader utility for aviation applications, numerical weather modeling, and climate research.

This paper presents a novel intelligent chaotic-based code-division multiple access (CDMA) scheme for underwater optical wireless communication (UOWC), addressing critical performance degradation caused by severe scattering and multipath dispersion in underwater environments. Unlike conventional modulation techniques such as on-off keying, which depend on precise pulse timing and show high sensitivity to channel distortions, the proposed approach leverages unpredictable deterministic chaotic sequences generated by the logistic map to enhance robustness against scattering-induced impairments. A Multi-Agent Reinforcement Learning (MARL) framework enables distributed agents to dynamically adapt chaotic map parameters, including initial conditions and bifurcation parameters, based on real-time environmental feedback, optimizing sequence generation to maintain low cross-correlation properties and improve resilience to multipath effects. Experimental validation using a 2-meter water tank testbed with controlled turbidity demonstrates superior performance compared to conventional schemes. The adaptive framework exhibits rapid convergence and relaxed synchronization requirements, making it highly suitable for distributed underwater networks where centralized coordination is impractical.

This paper presents an analytical framework for evaluating the outage probability of ambient Internet of Things (A-IoT) device classes communicating directly with a base station. Device 1 is a passive backscatter device with minimal storage, while Device 2 is equipped with a supercapacitor that enables energy buffering and optional amplification. The proposed framework jointly accounts for carrier-detection sensitivity, energy harvesting constraints, supercapacitor energy dynamics, and an energy-aware amplification policy, while the energy evolution of buffered devices is modeled using a discrete-time Markov chain (DTMC). The results highlight the interplay between energy availability and communication reliability. Device 2 achieves superior performance in energy-rich regimes due to buffering and amplification gains, whereas Device 1 becomes more robust in energy-constrained regimes, particularly at larger distances or under high payload requirements. These findings highlight that the optimal device choice depends critically on the operating regime and application demands.

Covariance steering provides an efficient framework for designing linear stochastic feedback policies, but its extension to nonlinear systems relies on a Gaussian surrogate obtained through local linearization. Because this surrogate may differ substantially from the true nonlinear state distribution, risk-sensitive quantities such as collision probability and mean-squared error may be inaccurately estimated. This work develops a distributionally robust covariance-steering framework based on the relative entropy, also known as the Kullback-Leibler divergence (KLD), to account for ambiguity in the propagated probability density function. Using a variational representation of exponential integrals, we derive computable upper bounds on risk-sensitive quantities over a KLD ambiguity set. We then formulate an upper bound on the time rate of change of the KLD between the true nonlinear distribution and a Gaussian reference surrogate. Under some assumptions, this bound is controlled by decision variables within a covariance-steering formulation. The resulting constraints are incorporated into a sequential convex programming algorithm to design stochastic guidance policies that keep the true distribution close to its Gaussian surrogate while enforcing bounds on risk-sensitive performance measures. The proposed approach is demonstrated on a challenging nonlinear spacecraft transfer between two near-rectilinear halo orbits.

The emerging paradigm of Non-Conventional Internet of Things (NC IoT), which focuses on the usefulness of information rather than high-volume data collection and transmission, will be a dominant paradigm in the next generation of wireless systems. On the downside, the absence of standardized protocols and the heterogeneity of underwater nodes, coupled with the unique constraints of acoustic communication (e.g., propagation delays and bandwidth limitations), pose significant interoperability challenges for Underwater Internet of Things (UIoT) networks. In this paper, we introduce a pioneering self-learning semantic framework that addresses these issues by leveraging a three-layer architecture using a novel Semantic Bayesian Optimization (SBO) approach integrated with Multi-Transmission Bayesian Optimization (MTBO). This framework employs Age of Information (AoI) as a freshness metric, incorporates a hybrid deep neural network-Gaussian process surrogate model, and formulates a propagation-aware Aol metric to enhance real-time environmental monitoring. Results are provided and compared with other competing methods to quantify the proposed method's superiority.

Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself. The controller may use any causal, history-dependent rule and act differently across environments as data arrive. Only its safety guarantee is uniform: the same rule must satisfy it under every initially plausible model. Performance is measured against a safe oracle that knows the realized model. Many finite-time analyses assume persistent excitation of the uniformly safe closed loop, so the data distinguish every pair of models requiring different control decisions. Under that assumption, feasibility is already settled; only the rate remains. We ask instead: Do the safety constraints permit such an informative experiment at all? While an alternative remains plausible, the controller must preserve a safe continuation under it. We call the first action that forecloses such a continuation commitment. Chance safety allows commitment only on an event rare under the alternative, and the evidence must arrive beforehand: the observation generated by the committing action is too late. We define precommitment information as the KL divergence between learner-visible laws stopped before commitment. Our main result is a causal reduction. The commitment rule determines (1) the probability that safety permits commitment under the alternative, (2) the target-side cost of remaining noncommittal, (3) and the information available when the decision is made. Bounded precommitment information therefore leaves a fixed fraction of the oracle gap unavoidable. If the gap is {\Omega}(T), every uniformly safe policy has linear regret. We establish the obstruction in a constrained linear system with quadratic regulation cost. We also prove recovery in special cases and derive semidefinite upper certificates for deterministic linear-Gaussian systems.

The increasing complexity of next-generation wireless networks has driven the integration of artificial intelligence (AI) into wireless communications. However, most existing studies focus on developing task-specific deep learning techniques for single scenarios, which limits their ability to generalize across diverse tasks, channel conditions, and system configurations. To address this generalization bottleneck, we propose a hierarchical wireless foundation model (WFM) for multi-task optimization. The proposed WFM couples an upstream foundation channel encoder (FCE) with a downstream foundation optimization decoder (FOD) via geometry-aware cross-attention. Specifically, the FCE extracts task-agnostic channel representations via self-supervised masked reconstruction while the FOD generates multi-task optimization decisions through differentiable output heads. Moreover, a hybrid supervised-to-unsupervised training strategy is employed to overcome the performance ceiling of purely supervised learning, and the modular architecture of the WFM enables efficient adaptation to unseen communication tasks with minimal parameter overhead. Simulation results show that the proposed WFM learns high-fidelity channel representations and achieves competitive multi-task optimization performance while substantially reducing optimization inference latency relative to numerical baselines. Furthermore, it exhibits robust generalization to unseen propagation environments, varying constraint parameters, and heterogeneous system configurations.

Supercharging of lithium-ion batteries (LiBs) requires robust health monitoring to ensure durability, safety, and user confidence, particularly for emerging vehicle-to-grid applications with bidirectional energy flows. Yet battery management remains largely disconnected from the material and structural origins of aging, limiting both interpretable health assessment and informed battery design. Here we propose a physics-informed learning framework with virtual sensing that infers hard-to-measure design parameters, including solid-state diffusion coefficient, electrode thickness, ion concentration, and particle size, directly from standard battery management system (BMS) measurements. Across diverse fast-charging strategies and driving profiles, embedding a digital-twin-derived particle-cracking mechanism as a soft constraint reduces trajectory and lifetime prediction errors by 6-8 times relative to state-of-the-art machine learning baselines using only 2% early-life observations. We further show that accurate degradation extrapolation does not require fully resolved governing equations; validated partial mechanisms, jointly refined with limited data, provide sufficient guidance. Virtual sensing transforms standard charging signals into latent design variables without additional sensors, bridging observable battery behavior and underlying aging processes while reducing capacity loss error by up to 39%, end-of-life (EOL) error by 17%, and prediction variability by up to 54%, enabling real-time exploration of new battery configurations. More broadly, the proposed framework establishes a practical feedback loop between deployment and development, demonstrating how real-world operation can continuously inform upstream design decisions across complex multiphysics systems.

In this paper, we propose a novel precoded faster-than-Nyquist (FTN) signaling scheme with power-domain-multiplexing in non-orthogonal multiple access (NOMA) downlink for tapping the joint benefits of high spectral efficiency and simultaneous multiuser connectivity. Non-orthogonality is introduced in both the symbol-interval (time) domain as well as in the multiple-access (power) domain to achieve a flexible resource allocation. Eigendecomposition of the FTN-specific intersymbol interference (ISI) matrix is used to achieve efficient cancellation of ISI, while successive interference cancellation is used to eliminate multiuser interference induced by NOMA. We derive the achievable analytical rate bound and demonstrate the numerical results of the bit error rate performance for the proposed scheme.

Understanding why a traffic situation is demanding for the human driver is central to safe and comfortable partially automated driving. Existing complexity metrics characterize only external environmental factors, while driver monitoring systems detect only endogenous states such as distraction. Neither side captures how external demands translate into driver-perceived situational load. Driver behavior serves as the natural bridge between both, and this paper investigates the inverse inference problem of estimating traffic complexity from behavioral signals. A systematic screening of 175 behavioral features across five domains (gaze, head pose, longitudinal control, guiding fixation, scanning strategy) is applied to data from 20 drivers in real urban traffic. Of these, 31 features exhibit statistically confirmed complexity effects, while 140 are confirmed as null effects through equivalence testing. Mixed-effects variance decomposition reveals that complexity explains only 1.5% of behavioral variance, whereas driver identity accounts for 23% and residual variance for 75%. This unfavorable ratio explains both the failure of all eight evaluated feature-level personalization strategies and the convergence of four classification architectures at F1 around 0.45 under leave-one-subject-out cross-validation. Guiding fixation rate emerges as the single most deployment-ready feature, combining speed-robustness, universality across drivers, and minimal inter-driver variation in complexity sensitivity. The results define three deployment regimes for complexity-adaptive advanced driver assistance systems and establish the variance structure as the primary bottleneck for complexity estimation.

Fine-grained offensive language detection organizes labels into a hierarchical structure, for which two modeling paradigms exist: cascaded decomposition and joint multi-task modeling. Prior work rarely provides a direct, controlled comparison of the two paradigms in terms of accuracy, parameter count, and inference latency, and rarely verifies whether a chosen class-imbalance handling strategy is actually optimal. This paper proposes a three-level cascaded detection system whose training strategy is customized per subtask, together with two verification mechanisms. First, a controlled ablation study determines the best class-imbalance handling strategy for each subtask. Second, a joint multi-task model with a shared encoder is trained as an architectural control, yielding real measurements along the dimensions of accuracy, parameter count, and inference latency. Experiments show that the cascaded system attains macro-F1 scores of 0.795, 0.716, and 0.557 on the three subtasks of the official test set. The ablation study reveals that configuring the loss function purely by imbalance-severity intuition is suboptimal; reconfiguring based on the ablation results improves both performance and stability. End-to-end cascade evaluation shows that roughly one-fifth of the errors in the cascade pipeline originate from the first-stage filter and cannot be corrected by subsequent stages. Relative to the joint multi-task model, the cascaded architecture achieves higher accuracy on all three subtasks, with a 7.1-point macro-F1 gain on the most severely imbalanced subtask, at the cost of three times the parameters and 1.67 times the inference latency. Together, these results establish an explicit, quantifiable trade-off between the accuracy advantage of cascaded architectures and their deployment cost.

Chaotic modulation is an effective communication technique that exploits deterministic chaos to produce pseudo-random signals. A widely adopted approach involves modulation of the chaotic bifurcation parameter. This paper introduces a deep learning-based demodulation method for keying of the bifurcation parameter. It describes the architecture of the convolutional neural network and evaluates performance metrics for signals generated using the chaotic logistic map. The study assesses the bit error rate for binary signals and reports a bit error rate of 0.0819 for a bifurcation parameter deviation of 1.34% under additive white Gaussian noise at a signal-to-noise ratio of -13 dB (corresponding to a normalized signal-to-noise ratio of +20 dB). The results demonstrate the capability to detect chaotic patterns even when the specific patterns were not included in the training dataset.

Edge inference has emerged as a promising solution for the proliferation of artificial intelligence (AI) services by deploying models at the network edge to circumvent cloud-routing latency. Existing edge inference approaches mainly focused on either cooperative inference to reduce latency or lightweight model design to fit resource-constrained devices. These solutions often address the communication and computation challenges separately, and thus struggle to achieve a balanced trade-off among transmission efficiency, on-device processing cost, and inference accuracy. To bridge this gap, this paper proposes a hybrid-precision task-oriented communication framework for edge inference to holistically balance communication, on-device computation, and utility. In this framework, a binarized front-end is deployed on the edge device to extract and transmit binary features via orthogonal frequency-division multiplexing (OFDM) signals, while a full-precision back-end on the edge server performs the final inference. To ensure model consistency, we introduce an on-device binarization method tailored for split inference and develop an integrated channel-aware transmission scheme featuring subcarrier-based feature calibration. Furthermore, a knowledge distillation (KD)-based training strategy, supported by specialized gradient estimators, is developed to optimize the end-to-end system and inherit semantic knowledge from a full-precision teacher model. Extensive experiments on the large-scale ImageNet dataset demonstrate the superiority of the proposed hybrid system. Our analysis confirms that this design achieves an optimal trade-off among communication efficiency, on-device computational cost, and inference accuracy, outperforming existing edge inference solutions.

This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes. Each recording is between 15 and 35 seconds long and contains temporally precise annotations for 15 common domestic sound classes. In contrast to existing SED datasets, which typically rely on simulated soundscapes or broad web-crawled audio, RealDESED consists exclusively of recordings captured in natural domestic environments, reflecting realistic variability in recording devices, device placement, acoustic conditions, background sounds, and naturally occurring event co-occurrences. A distinguishing characteristic of the dataset is its multi-annotator labeling scheme, where each recording is independently annotated by multiple annotators, while the validation and test sets undergo an additional review process to ensure high annotation quality and reliable benchmarking. Furthermore, the dataset provides rich metadata, including recording device, device placement, environment labels, and textual scene descriptions. We establish a strong transformer-based baseline and investigate annotation aggregation strategies, post-processing methods, long-form inference, and the impact of recording metadata on model performance. Our baseline achieves a macro-averaged PSDS1 score of 0.731 on the test set. We believe RealDESED provides a valuable benchmark for developing and evaluating robust SED systems under realistic domestic conditions, helping to bridge the gap between current research benchmarks and real-world deployment.

This paper studies joint uplink (UL) and downlink (DL) resource optimization for interactive augmented reality (AR) services, where the live video captured by an AR device is uploaded to the network edge, and then the augmented video is subsequently downloaded. By modeling the AR transmission process as a tandem queuing system, we derive an upper bound for the probabilistic quality of service (QoS) requirement concerning end-to-end latency and reliability. The derived bound transforms the probabilistic QoS requirement into a tractable service-time condition that jointly characterizes the UL and DL service processes. Based on this condition, we formulate a weighted UL-DL transmit-power minimization problem and propose a learning-based framework to jointly optimize UL power allocation and DL beamforming. To enable gradient-based training, we further derive a differentiable upper bound for the service-time condition. Moreover, we design GNN-based policies for UL power allocation and DL beamforming, where the UL GNN exploits permutation equivariance (PE) and the DL GNN incorporates both PE and the optimal structure of wideband DL beamforming. Simulation results show that the proposed method satisfies the AR reliability requirement and reduces the weighted transmit power compared with baselines that optimize UL and DL resources separately.

Live fuel moisture content controls vegetation flammability and is a high-importance variable in fire management. Nevertheless, it remains difficult to estimate and map over large areas due to the concentration of field observations in specific regions. We develop a unified machine-learning framework that estimates live fuel moisture content from satellite vegetation indices, meteorological variables, topography and seasonal predictors. GlobeLFMC 2.0 measurements are matched to Terra and Aqua MODIS, VIIRS, Landsat 8/9, Sentinel-2 and Sentinel-3 surface-reflectance products, combining the long MODIS record with finer-resolution recent observations. To account for differences among sensors, optical predictors are restricted to a common red, near-infrared and shortwave-infrared feature space; site–product combinations and field time series are screened for remote-sensing suitability; and spectral response function diagnostics are combined with target-independent empirical reflectance calibration toward a Sentinel-2 reference domain. Preliminary single-product experiments show that weather, topography and cyclic day-of-year provide most of the predictive gain beyond vegetation indices, whereas optional product-specific predictors do not justify their additional dependencies. Separate Grass, Shrub and Tree models are trained with Random Forest and XGBoost regressors. Under the primary validation design, which withholds observation dates from sites represented in training, the best models achieve pooled R2 values of 0.715, 0.693 and 0.700 for Grass, Shrub and Tree, respectively. The framework can incorporate additional optical sensors when compatible reflectance bands, documented spectral responses and sufficient overlap observations are available for calibration and validation.

Non-uniform scaling control enables a multi-agent formation to adjust its shape by compressing or stretching independently along different coordinate axes through inter-agent interactions, offering high flexibility in complex environments. The fundamental idea is encoding the desired formation shape as the kernel of a matrix-valued Laplacian. In open multi-agent systems, however, changes in number of agents, number of edges, and leader selection dynamically alter this Laplacian, destroying the required spectral properties: positive semidefiniteness, correct kernel, and positive definiteness of the follower block (we summarize these properties as the formation spectrum). In this paper, we develop distributed protocols to strategically adjust partial weights of the Laplacian matrix for formation control in arbitrary dimensional space. By implementing the protocols, the desired formation spectrum can be preserved under dynamic topology changes including agent joining, edge addition, agent leaving, and edge removal, while any pair of agents can serve as leaders. Unlike existing Laplacian design methods for affine formation control under topology changes, the proposed approach requires a sparser sensing graph, avoids a predefined parent-child hierarchical structure, and supports leader reassignment. The effectiveness of the proposed protocols is validated through both theoretical analysis and numerical simulations.