Papers

This paper proposes a novel robust Model Predictive Control (MPC) scheme for linear discrete-time systems affected by model uncertainty described by interval matrices. The key feature of the proposed method is a bound on the uncertainty propagation along the prediction horizon which exploits a set-theoretic over-approximation of each term of the uncertain system impulse response. Such an approximation is based on matrix zonotopes and leverages the interval matrix structure of the uncertainty model. Its main advantage is that all the relevant bounds are computed offline, thus making the online computational load independent of the number of uncertain parameters. A variable-horizon MPC formulation is adopted to guarantee recursive feasibility and to ensure robust asymptotic stability of the closed-loop system. Numerical simulations demonstrate that the proposed approach is able to match the feasibility regions of the most effective state-of-the-art methods, while significantly reducing the computational burden, thereby enabling the treatment of nontrivial dimensional systems with multiple uncertain parameters.

In a decentralized balancing model, Balance Responsible Parties (BRPs) are encouraged by the Transmission System Operator (TSO) to deviate from their schedule to help the system restore balance, also referred to as implicit balancing. This could reduce balancing costs for the grid operator and lower the entry barrier for flexible assets compared to explicit balancing services. However, these implicit reactions may overshoot when their total capacity is high, potentially requiring more explicit activations. This study analyses the effect of increased participation in the decentralized balancing model in Belgium. To this end, we develop a market simulator that produces price signals on minute-level and simulate the implicit reactions for battery assets with different risk profiles. Besides the current price formula, we also study two potential candidates for the near-term presented by the TSO. A simulation study is conducted using Belgian market data for the year 2023. The findings indicate that, while having a significant positive effect on the balancing costs at first, the risk of overshoots can outweigh the potential benefits when the total capacity of the implicit reactions becomes too large. Furthermore, even when the balancing costs start to increase for the TSO, BRPs were still found to benefit from implicit balancing.

Offline safe reinforcement learning (RL) is increasingly important for cyber-physical systems (CPS), where safety violations during training are unacceptable and only pre-collected data are available. Existing offline safe RL methods typically balance reward-safety tradeoffs through constraint relaxation or joint optimization, but they often lack structural mechanisms to prevent safety drift. We propose LexiSafe, a lexicographic offline RL framework designed to preserve safety-aligned behavior. We first develop LexiSafe-SC, a single-cost formulation for standard offline safe RL, and derive safety-violation and performance-suboptimality bounds that together yield sample-complexity guarantees. We then extend the framework to hierarchical safety requirements with LexiSafe-MC, which supports multiple safety costs and admits its own sample-complexity analysis. Empirically, LexiSafe demonstrates reduced safety violations and improved task performance compared to constrained offline baselines. By unifying lexicographic prioritization with structural bias, LexiSafe offers a practical and theoretically grounded approach for safety-critical CPS decision-making.

Nonlinear system identificationhas proven to be effective in obtaining accurate models from data for complex real-world systems. In particular, recent encoder-based methods with artificial neural network state-space (ANN-SS) models have achieved state-of-the-art performance on various benchmarks, using computationally efficient methods and offering consistent model estimation in the presence of noisy data. However, inclusion of prior knowledge of the system can be further exploited to increase (i) estimation speed, (ii) accuracy, and (iii) interpretability of the resulting models. This paper proposes a model augmentation method that incorporates prior knowledge from first-principles (FP) models in a flexible manner. We introduce a novel linear-fractional-representation (LFR) model structure that allows for the general representation of various augmentation structures including the ones that are commonly used in the literature, and an encoder-based identification algorithm for estimating the proposed structures together with appropriate initialisation methods. The performance and generalisation capabilities of the proposed method are demonstrated on the identification of a hardening mass-spring-damper system in a simulation study and on the data-driven modelling of the dynamics of an F1Tenth electric car using measured data.

Processing sensory data close to the data source, often involving Edge devices, promises low latency for pervasive applications, like smart cities. This commonly involves a multitude of processing services, executed with limited resources; this setup faces three problems: first, the application demand and the resource availability fluctuate, so the service execution must scale dynamically to sustain processing requirements (e.g., latency); second, each service permits different actions to adjust its operation, so they require individual scaling policies; third, without a higher-level mediator, services would cannibalize any resources of services co-located on the same device. This demo first presents a platform for context-aware autoscaling of stream processing services that allows developers to monitor and adjust the service execution across multiple service-specific parameters. We then connect a scaling agent to these interfaces that gradually builds an understanding of the processing environment by exploring each service's action space; the agent then optimizes the service execution according to this knowledge. Participants can revisit the demo contents as video summary and introductory poster, or build a custom agent by extending the artifact repository.

In imaging inverse problems with Poisson-distributed measurements, it is common to use objectives derived from the Poisson likelihood. But performance is often evaluated by mean squared error (MSE), which raises a practical question: how much does a Poisson objective matter for MSE, even at low dose? We analyze the MSE of Poisson and Gaussian surrogate reconstruction objectives under Poisson noise. In a stylized diagonal model, we show that the unregularized Poisson maximum-likelihood estimator can incur large MSE at low dose, while Poisson MAP mitigates this instability through regularization. We then study two Gaussian surrogate objectives: a heteroscedastic quadratic objective motivated by the normal approximation of Poisson data, and a homoscedastic quadratic objective that yields a simple linear estimator. We show that both surrogates can achieve MSE comparable to Poisson MAP in the low-dose regime, despite departing from the Poisson likelihood. Numerical computed tomography experiments indicate that these conclusions extend beyond the stylized setting of our theoretical analysis.

A signal processing-based framework is proposed for detecting random segment failures in segmented waveguide-enabled pinching-antenna systems. To decouple the passively combined uplink signal and to provide per-segment observability, tagged pilots are employed. A simple tag is attached to each segment and is used to apply a known low-rate modulation at the segment feed, which assigns a unique signature to each segment. Based on the tagged-pilot model, a low-complexity per-segment maximum-likelihood (ML) detector is developed for the case in which the pilot length is no smaller than the number of segments. For the case in which the pilot length is smaller than the number of segments, sparsity in the failure-indicator vector is exploited and a compressive sensing-based detector is adopted. Numerical results show that the per-segment detector approaches joint ML performance, while the compressive sensing-based detector achieves reliable detection with a short pilot and can outperform baselines that require much longer pilots.

Freight vehicles approaching signalized intersections require reliable detection and motion estimation to support infrastructure-based Freight Signal Priority (FSP). Accurate and timely perception of vehicle type, position, and speed is essential for enabling effective priority control strategies. This paper presents the design, deployment, and evaluation of an infrastructure-based multi-modal freight vehicle detection system integrating LiDAR and camera sensors. A hybrid sensing architecture is adopted, consisting of an intersection-mounted subsystem and a midblock subsystem, connected via wireless communication for synchronized data transmission. The perception pipeline incorporates both clustering-based and deep learning-based detection methods with Kalman filter tracking to achieve stable real-time performance. LiDAR measurements are registered into geodetic reference frames to support lane-level localization and consistent vehicle tracking. Field evaluations demonstrate that the system can reliably monitor freight vehicle movements at high spatio-temporal resolution. The design and deployment provide practical insights for developing infrastructure-based sensing systems to support FSP applications.

This paper investigates goal-oriented remote monitoring of an unobservable Markov source using energy-harvesting sensors that communicate with a mobile receiver, such as a Low Earth Orbit (LEO) satellite or Unmanned Aerial Vehicle (UAV). Unlike conventional systems that assume stationary base stations, the proposed framework explicitly accounts for receiver mobility, which induces time-varying channel characteristics modeled as a finite-state Markov process. The remote monitoring problem is formulated as a partially observable Markov decision process (POMDP), which is transformed into a tractable belief-state MDP and solved using relative value iteration to obtain optimal sampling and transmission policies. Two estimation strategies are considered: Maximum Likelihood (ML) and Minimum Mean Distortion (MMD). Numerical results demonstrate that incorporating receiver mobility and channel state information into the optimization reduces the average distortion by 10% to 42% compared to baseline policies and constant-channel assumptions, highlighting the importance of base station motion knowledge for effective goal-oriented communication.

Electrified heating systems with thermal storage, such as electric boilers and heat pumps, represent a major source of demand-side flexibility. Under current electricity market designs, balance responsible parties (BRPs) operating such assets are required to submit binding day-ahead electricity consumption schedules, and they typically do it based on forecasts of heat demand and electricity prices. Common scheduling approaches implicitly assume that forecast uncertainty can be well characterized using historical forecast errors. In practice, however, the cumulative effect of uncertainty creates significant exposure to imbalance-price risk when the committed schedule cannot be followed. To address this, we propose a distributionally robust chance-constrained optimization framework for the day-ahead scheduling of a multi-MW electric boiler using only limited residual forecast samples. We derive a tractable convex reformulation of the problem and calibrate the ambiguity set directly from historical forecast-error data through an a priori tunable risk parameter. Numerical results show that enforcing performance guarantees on the heat-demand balance constraint reduces demand violations by 40% compared to a deterministic forecast-based scheduler and up to 10% relative to a nominal chance-constrained model with a fixed error distribution. Further, we show that modeling the real-time rebound cost of demand violations as a second-stage term can reduce the overall daily operating cost by up to 34% by hedging against highly volatile day-ahead electricity prices.

Near-field ultra-massive MIMO (U-MIMO) systems provide enhanced spatial resolution but present challenges for channel estimation, particularly when hybrid architectures are employed. Within this framework, dictionary-based channel estimation schemes are needed to achieve accurate reconstruction from a reduced set of measurements. However, existing near-field dictionaries generally provide full three-dimensional coverage, which is unnecessary when user equipments are primarily located on the ground. In this paper, we propose a novel near-field grid design tailored to this common scenario. Specifically, grid points lie on a reference plane located at an arbitrary height with respect to the U-MIMO system, equipped with a uniform planar array. Furthermore, a channel accuracy metric is used to improve codebook performance, and to remark the limitations of the traditional far-field angular sampling in the near field. Results show that, as long as user equipments are not far from the reference plane, the proposed grid outperforms state-of-the-art designs in both channel estimation accuracy and spectral efficiency.

This paper presents a framework for aerial manipulation of an extensible cable that combines a high-fidelity model based on partial differential equations (PDEs) with a reduced-order representation suitable for real-time control. The PDEs are discretised using a finite-difference method, and proper orthogonal decomposition is employed to extract a reduced-order model (ROM) that retains the dominant deformation modes while significantly reducing computational complexity. Based on this ROM, a nonlinear model predictive control scheme is formulated, capable of stabilizing cable oscillations and handling hybrid transitions such as payload attachment and detachment. Simulation results confirm the stability, efficiency, and robustness of the ROM, as well as the effectiveness of the controller in regulating cable dynamics under a range of operating conditions. Additional simulations illustrate the application of the ROM for trajectory planning in constrained environments, demonstrating the versatility of the proposed approach. Overall, the framework enables real-time, dynamics-aware control of unmanned aerial vehicles (UAVs) carrying suspended flexible cables.

Remote and resource-constrained Internet-of-Things (IoT) deployments often lack terrestrial connectivity for task offloading, motivating non-terrestrial networks (NTNs) with onboard multiaccess edge computing (MEC) capabilities. Nevertheless, in the presence of malicious actors, authentication needs to be performed to avoid non-authorized nodes from draining the computing resources of the NTN nodes. As a solution, we propose a four-layer MEC-enabled NTN with unmanned aerial vehicles (UAVs) acting as access nodes, a high altitude platform station (HAPS) acting as coordinator and authenticator, and a constellation of low-Earth orbit satellites (LEOSats) acting as remote MEC servers. We consider a tag-based physical-layer authentication (PLA) scheme to authenticate legitimate users, and formulate a joint task offloading decision and resource allocation for the admitted tasks, which is solved via block coordinate descent. Numerical results show that the PLA scheme is efficient and performs better than the benchmark schemes. We also demonstrate that the proposed scheme is robust against malicious attacks even under relaxed false-alarm constraints.

Robust control of mechanical systems with multiple uncertainties remains a fundamental challenge, particularly when nonlinear dynamics and operating-condition variations are intricately intertwined. Although deep reinforcement learning combined with domain randomization has shown promise in mitigating the sim-to-real gap, simultaneously handling all the sources of uncertainty often leads to sub-optimal policies and poor learning efficiency. This study proposes continual uncertainty learning (CUL), a curriculum-based continual learning framework for robust control of nonlinear systems on which multiple heterogeneous uncertainties are simultaneously superimposed. The core idea is to decompose the original control problem into a sequence of continual learning tasks by extending the system into a set of plants whose uncertainties are progressively expanded and diversified, so that the strategy for handling each uncertainty is acquired sequentially. Within this curriculum, the policy is updated across the plant sets under a memory-efficient anti-forgetting regularization, which preserves the strategies acquired for earlier uncertainties. In parallel, a model-based controller that guarantees a shared baseline performance across all the plant sets is embedded in the learning process, so that the agent learns only the residual compensation for each uncertainty, thereby substantially enhancing sample efficiency. The proposed framework is applied to the design of an active vibration controller for automotive powertrains as a practical industrial application. Comparative validation demonstrates that the resulting controller remains robust against structural nonlinearities and dynamic variations over a wide range of plant conditions while improving the control performance.

We present a robotics-oriented, coordinate-free formulation of inverse flight dynamics for fixed-wing aircraft on SO(3). Translational force balance is written in the world frame and rotational dynamics in the body frame; aerodynamic directions (drag, lift, side) are defined geometrically, avoiding local attitude coordinates. Enforcing coordinated flight (no sideslip), we derive a closed-form trajectory-to-input map yielding the attitude, angular velocity, and thrust-angle-of-attack pair, and we recover the aerodynamic moment coefficients component-wise. Applying such a map to tethered flight on spherical parallels, we obtain analytic expressions for the required bank angle and identify a specific zero-bank locus where the tether tension exactly balances centrifugal effects, highlighting the decoupling between aerodynamic coordination and the apparent gravity vector. Under a simple lift/drag law, the minimal-thrust angle of attack admits a closed form. These pointwise quasi-steady inversion solutions become steady-flight trim when the trajectory and rotational dynamics are time-invariant. The framework bridges inverse simulation in aeronautics with geometric modeling in robotics, providing a rigorous building block for trajectory design and feasibility checks.

We propose CC-G2PnP, a streaming grapheme-to-phoneme and prosody (G2PnP) model to connect large language model and text-to-speech in a streaming manner. CC-G2PnP is based on Conformer-CTC architecture. Specifically, the input grapheme tokens are processed chunk by chunk, which enables streaming inference of phonemic and prosodic (PnP) labels. By guaranteeing minimal look-ahead size to each input token, the proposed model can consider future context in each token, which leads to stable PnP label prediction. Unlike previous streaming methods that depend on explicit word boundaries, the CTC decoder in CC-G2PnP effectively learns the alignment between graphemes and phonemes during training, making it applicable to unsegmented languages. Experiments on a Japanese dataset, which has no explicit word boundaries, show that CC-G2PnP significantly outperforms the baseline streaming G2PnP model in the accuracy of PnP label prediction.

One of the key issues facing Direct-to-Cellular (D2C) satellite communication systems is ionospheric scintillation on the uplink and downlink, which can significantly degrade link quality. This work investigates the spatial and temporal characteristics of amplitude scintillation at D2C frequencies by scaling L-band scintillation observations from Global Navigation Satellite Systems (GNSS) receivers to bands relevant to D2C operation, including the low-band, and 3GPP's N255 and N256. These observations are then compared to scaled radio-occultation scintillation observations from the FORMOSAT-7/COSMIC-2 (F7/C2) mission, which can be used in regions that do not possess ground-based scintillation monitoring stations. As a proof of concept, five years of ground-based GNSS scintillation data from Sharjah, United Arab Emirates, together with two years of F7/C2 observations over the same region, corresponding to the ascending phase of Solar Cycle 25, are analyzed. Both space-based and ground-based observations indicate a pronounced diurnal scintillation peak between 20–22 local time, particularly during the equinoxes, with occurrence rates increasing with solar activity. Ground-based observations also reveal a strong azimuth dependence, with most scintillation events occurring on southward satellite links. The scintillation occurrence rate at the low-band is more than twice that observed at N255 and N256, highlighting the increased robustness of higher D2C bands to ionospheric scintillation. These results demonstrate how GNSS scintillation observations can be leveraged to characterize and anticipate scintillation-induced D2C link impairments, which help in D2C system design and the implementation of scintillation mitigation strategies.

In Video on Demand (VoD) scenarios, traditional codecs are the industry standard due to their high decoding efficiency. However, they suffer from severe quality degradation under low bandwidth conditions. While emerging generative neural codecs offer significantly higher perceptual quality, their reliance on heavy frame-by-frame generation makes real-time playback on mobile devices impractical. We ask: is it possible to combine the blazing-fast speed of traditional standards with the superior visual fidelity of neural approaches? We present HybridPrompt, the first generative-based video system capable of achieving real-time 1080p decoding at over 150 FPS on a commercial smartphone. Specifically, we employ a hybrid architecture that encodes Keyframes using a generative model while relying on traditional codecs for the remaining frames. A major challenge is that the two paradigms have conflicting objectives: the "hallucinated" details from generative models often misalign with the rigid prediction mechanisms of traditional codecs, causing bitrate inefficiency. To address this, we demonstrate that the traditional decoding process is differentiable, enabling an end-to-end optimization loop. This allows us to use subsequent frames as additional supervision, forcing the generative model to synthesize keyframes that are not only perceptually high-fidelity but also mathematically optimal references for the traditional codec. By integrating a two-stage generation strategy, our system outperforms pure neural baselines by orders of magnitude in speed while achieving an average LPIPS gain of 8% over traditional codecs at 200kbps.

Electromagnetic transient (EMT) simulation is essential for analyzing sub-cycle switching phenomena in industrial power systems; however, commercial EMT platforms present significant cost barriers for smaller utilities, consultancies, and academic institutions, particularly in developing regions. This paper validates KESTREL EMT, a free and open-source electromagnetic transient solver with Python integration, through three progressive case studies involving industrial capacitor switching transients. This work investigates energization, switching resonance and VFD interactions with capacitor banks. The results demonstrate that KESTREL, when supported by appropriate circuit modeling techniques, produces EMT responses consistent with analytical predictions and established IEEE benchmarks. This work establishes a validated and reproducible methodology for conducting industrial EMT studies using freely available, open-source tools.

Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing solely on vehicle-centric performance. This paper proposes STDSH-MARL (Spatio-Temporal Dual-Stage Hypergraph based Multi-Agent Reinforcement Learning), a multi-agent deep reinforcement learning framework that follows a centralized training and decentralized execution paradigm. The proposed method captures spatio-temporal dependencies through a novel dual-stage hypergraph attention mechanism that models interactions across both spatial and temporal hyperedges. In addition, a hybrid discrete action space is introduced to jointly determine the next signal phase configuration and its corresponding green duration, enabling more adaptive signal timing decisions. Experiments conducted on a corridor network under five traffic scenarios demonstrate that STDSH-MARL achieves strong overall multimodal performance, with substantial and relatively consistent reductions in tram waiting time, while improvements in bus waiting time are more variable across traffic scenarios. These results highlight the trade-off among overall network efficiency, tram priority, and bus service quality. Compared with state-of-the-art baseline methods, the proposed approach achieves superior overall performance. Further ablation studies confirm the contribution of each component of STDSH-MARL, with temporal hyperedges identified as the most influential factor driving the observed performance gains.

As power systems accommodate higher shares of renewable generation, short-term power imbalances become more frequent and can manifest as pronounced voltage and frequency excursions under low-inertia conditions. E-STATCOMs (STATCOMs equipped with energy storage) offer a practical means to provide both voltage support and fast frequency assistance under grid-forming control. Among candidate implementations, double-star multilevel-converter (DS-MC)-based E-STATCOMs enable centralized energy-storage integration at the dc link, which improves thermal management and maintainability. Nevertheless, conventional dc-side power-based internal-energy regulation in DS-MCs can undesirably couple loss compensation to the energy-storage path, accelerating storage cycling and constraining operation when the storage is unavailable. This paper introduces a control strategy that assigns DS-MC total internal-energy regulation to the ac-side active-power path, while reserving dc-side storage power solely for frequency support. By decoupling internal-energy management from inertial-response provision, the proposed scheme enables flexible operation as either a STATCOM or an E-STATCOM according to storage availability and mitigates unnecessary storage cycling. The proposed strategy is verified through offline simulations and laboratory-scale experiments.

This two-part paper aims to develop an environment-aware network-level design framework for generalized pinching-antenna systems to overcome the limitations of conventional link-level optimization, which is tightly coupled to instantaneous user geometry and thus sensitive to user mobility and localization errors. Part I investigates the traffic-aware case, where user presence is characterized statistically by a spatial traffic map and deployments are optimized using traffic-aware network-level metrics. Part II complements Part I by developing geometry-aware, blockage-aware network optimization for pinching-antenna systems in obstacle-rich environments. We introduce a grid-level average SNR model with a deterministic LoS visibility indicator and a discrete activation architecture, where the geometry-dependent terms are computed offline in advance. Building on this model, we formulate two network-level activation problems: (i) average-SNR-threshold coverage maximization and (ii) fairness-oriented worst-grid average-SNR maximization. On the algorithmic side, we prove the coverage problem is NP-hard and derive an equivalent mix-integer linear programming reformulation through binary coverage variables and linear SNR linking constraints. To achieve scalability, we further develop a structure-exploiting coordinate-ascent method that updates one waveguide at a time using precomputed per-candidate SNR contributions. For the worst-grid objective, we adopt an epigraph reformulation and leverage the resulting monotone feasibility in the target SNR, enabling an efficient bisection-based solver with low-complexity feasibility checks over the discrete candidate set. Simulations results validate the proposed designs and quantify their gains under different environments and system parameters.

Existing studies on pinching-antenna systems have primarily focused on link-level design, where system parameters are optimized for a given user set according to user-specific communication metrics. Such designs provide an effective means of exploiting the spatial reconfigurability of pinching antennas for short-term user-centric transmission. Complementing this perspective, this two-part paper develops an environment-aware network-level design framework, where pinching-antenna configurations are optimized according to long-term spatial information and evaluated through network-level performance metrics. Part I focuses on the traffic-aware case, where user presence is modeled statistically by a spatial traffic map and performance is optimized and evaluated in a traffic-aware sense; Part II addresses the geometry-aware case in obstacle-rich environments by explicitly modeling line-of-sight blocking and optimizing region-wide robustness objectives. In Part~I, we introduce traffic-weighted average SNR metrics and formulate two traffic-aware deployment problems: (i) maximizing the traffic-weighted network average SNR, and (ii) a fairness-oriented traffic-restricted max–min average-SNR design over traffic-dominant grids. To solve these nonconvex problems with low complexity, we reveal and exploit their separable structures. For the network-average objective, we establish unimodality properties of the hotspot-induced components and develop a candidate-based low-complexity method that only needs to evaluate the objective at a small set of candidate antenna positions. For the traffic-restricted max–min objective, we develop a block coordinate descent framework where each coordinate update reduces to a one-dimensional subproblem via an epigraph reformulation and bisection. Simulations show that the proposed design outperm.

This paper investigates the joint optimization of trajectory, user scheduling, and time-slot duration in unmanned aerial vehicle (UAV)-assisted wireless communication systems under minimum expected spectral efficiency (SE) constraints. Unlike most existing studies that approximate the expected SE by substituting the random channel gain with its mean value, thereby evaluating the SE at the average channel realization and overestimating the true expected SE due to Jensen's inequality, we approximate the expected SE by numerically integrating the SE over the channel distributions. Specifically, instead of relying on average-channel-based approximations, we develop a conservative yet tractable quadrature-based approximation by discretizing the associated cumulative distribution functions. The resulting finite-sum representation explicitly accounts for the probabilistic LoS structure and channel fading effects, while remaining tractable for optimization. Leveraging this lower bound, we formulate a mission completion time minimization problem subject to minimum expected-SE requirements for all ground nodes. The resulting problem is a mixed-integer nonconvex optimization, which is tackled via a penalty-based block coordinate descent framework. The proposed algorithm alternately optimizes the scheduling decisions and the UAV trajectory along with adaptive time-slot durations, and maintains feasibility with respect to the original expected-SE constraints by leveraging successive convex approximation and quadratic transform techniques. Simulation results demonstrate that the proposed method strictly satisfies the minimum expected-SE constraints and achieves a significantly shorter mission completion time than conventional average-channel-based approaches, which are shown to yield infeasible or overly conservative solutions.

Evaluating perceived video quality is essential for ensuring high Quality of Experience (QoE) in modern streaming applications. While existing subjective datasets and Video Quality Metrics (VQMs) cover a broad quality range, many practical use cases especially for premium users focus on high quality scenarios requiring finer granularity. Just Noticeable Difference (JND) has emerged as a key concept for modeling perceptual thresholds in these high end regions and plays an important role in perceptual bitrate ladder construction. However, the relationship between JND and the more widely used Mean Opinion Score (MOS) remains unclear. In this paper, we conduct a Degradation Category Rating (DCR) subjective study based on an existing JND dataset to examine how MOS corresponds to the 75% Satisfied User Ratio (SUR) points of the 1st and 2nd JNDs. We find that while MOS values at JND points generally align with theoretical expectations (e.g., 4.75 for the 75% SUR of the 1st JND), the reverse mapping from MOS to JND is ambiguous due to overlapping confidence intervals across PVS indices. Statistical significance analysis further shows that DCR studies with limited participants may not detect meaningful differences between reference and JND videos.

This paper investigates covert multi-hop communication in wireless networks where an adversary employs a cyclostationary (cycle) detector to reveal hidden transmissions. The covert route employs direct sequence spread spectrum (DSSS) signaling to ensure either maximum end-to-end covertness maximization or minimum latency minimization-under quality-of-service (QoS) and link budget constraints. Optimal bandwidth, transmit power, and spreading gain for each hop jointly satisfy reliability and either rate or covertness requirements. We show the equivalence between the covertness and the detection SNR gain-based widest-path formulations, and, hence, enabling efficient route computation. Numerical simulations in a realistic 3D environment illustrate that (i) end-to-end latency increases exponentially with the covertness requirement, (ii) the end-to-end latency increase is super-linear with the packet size M, and (iii) cycle and energy detectors impose different latency behavior as a function of the message length and the covertness requirement. The proposed framework provides important insights into resource allocation and routing design for covert networks against advanced detection adversaries.

Learning robust representations of 3D shapes from voxelized data is essential for advancing AI methods in biomedical imaging. However, most contemporary 3D computer vision approaches operate on point clouds, meshes, or octrees, while volumetric density maps, the native format of structural biology and cryo-EM, remain comparatively underexplored. We present Cryo-SWAN, a voxel-based variational autoencoder inspired by multi-scale wavelet decomposition. The model performs conditional coarse-to-fine latent encoding and recursive residual quantization across perception scales, enabling accurate capture of both global geometry and high-frequency structural detail in molecular density volumes. Evaluated on ModelNet40, BuildingNet, and a newly curated dataset of cryo-EM volumes, ProteinNet3D, Cryo-SWAN consistently improves reconstruction quality over state-of-the-art 3D autoencoders. We demonstrate that the molecular densities organize in learned latent space according to shared geometric features, while integration with diffusion models enables denoising and conditional shape generation. Together, Cryo-SWAN is a practical framework for data-driven structural biology and volumetric imaging.

Accurate wireless channel estimation is critical for next-generation wireless systems, enabling precise precoding for effective user separation, reduced interference across cells, and high-resolution sensing, among other benefits. Traditional model-based channel estimation methods suffer, however, from performance degradation in complex environments with a limited number of pilots, while purely data-driven approaches lack physical interpretability, require extensive data collection, and are usually site-specific. This paper presents a novel physics-informed neural network (PINN) framework that synergistically combines model-based channel estimation with a deep network to exploit prior information about environmental propagation characteristics and achieve superior performance under pilot-constrained scenarios. The proposed approach employs an enhanced U-Net architecture with transformer modules and cross-attention mechanisms to fuse initial channel estimates with RSS maps to provide refined channel estimates. Comprehensive evaluation using realistic ray-tracing data from urban environments demonstrates significant performance improvements, achieving over 5 dB gain in NMSE compared to state-of-the-art methods, with particularly strong performance in pilot-limited scenarios and robustness across different frequencies and environments with only minimal fine-tuning. We further extend the decoder for multi-step temporal prediction, enabling accurate forecasting of several future channel snapshots from a single estimate, useful for proactive beamforming and scheduling in mobile scenarios. The proposed framework maintains practical computational complexity, making it viable for massive MIMO systems in upper-mid band frequencies. Unlike black-box neural approaches, the physics-informed design provides a more interpretable channel estimation method.

We present a real-world multi-scenario unmanned aerial vehicle (UAV) radio frequency (RF) dataset, namely DRFF-R2, which is collected using a dedicated acquisition platform under diverse operational conditions. All signals are acquired within a unified framework to ensure consistency in hardware configuration and environmental settings. The dataset is systematically organized into seven well-defined subsets corresponding to different operational and signal composition scenarios to facilitate structured experimentation. Each file follows a clearly annotated naming convention to enable convenient data indexing and reproducible analysis. The dataset contains RF recordings from 26 UAV units spanning 8 distinct models, captured across varying flight states, altitudes, speeds, acquisition days, and receiver configurations. By covering diverse acquisition settings and signal compositions, the dataset provides a comprehensive resource for future UAV RF signal research, including RF fingerprinting (RFF) identification, model-level recognition, flight state analysis, time-varying RFF study, and interference-aware signal processing.

Accurate, high-performance radio-frequency (RF) filter circuits are ubiquitous in radio-frequency communication and sensing systems for accepting and rejecting signals at desired frequencies. Conventional RF filter design process involves manual calculations of design parameters, followed by intuition-guided iterations to achieve the desired response for a set of filter specifications. This process is time-consuming due to time- and resource-intensive electromagnetic simulations using full-wave numerical PDE solvers. This process is also highly sensitive to domain expertise and requires many years of professional training. To address these bottlenecks, we propose an automatic RF filter circuit design tool using neural simulator and reinforcement learning. First, we train a neural simulator to replace the PDE electromagnetic simulator. The neural-network-based simulator reduces each of the simulation time from 4 minutes on average to less than 100 millisecond while maintaining a high precision. Such dramatic acceleration enable us to leverage deep reinforcement learning algorithm and train an amortized inference policy to perform automatic design in the imagined space from the neural simulator. The resulted automatic circuit-design agent achieves super-human design results. The automatic circuit-design agent also reduces the on-average design cycle from days to under a few seconds. Even more surprisingly, we demonstrate that the neural simulator can generalize to design spaces far from the training dataset and in a sense it has learned the underlying physics–Maxwell equations. We also demonstrate that the reinforcement learning has discovered many expert-like design intuitions. This work marks a step in using neural simulators and reinforcement learning in RF circuit design and the proposed method is generally applicable to many other design problems and domains in close affinity