Papers

Integrating renewable generation, hydrogen production, and renewable ammonia (RA) synthesis into power-to-ammonia (P2A) systems creates interactions across electricity and hydrogen markets. Limited operational flexibility, however, places RA at a disadvantage at the Nash equilibrium (NE). Recent advances in ammonia synthesis reactor design enable hot standby (HSB) operation, improving flexibility but introducing integer decision variables that complicate market equilibrium analysis. To address this challenge, we develop a potential game model and derive a convergent {\epsilon}-approximate equilibrium via an iterative best-response approach. Case studies show that HSB reduces RA's reliance on hydrogen purchases and increases its profit by 20.14%. More importantly, HSB shifts the market equilibrium toward a more mutually beneficial outcome.

Electromagnetic transient (EMT) models are index-2 differential-algebraic equations when they include certain topologies and are formulated with modified nodal analysis. Such systems are difficult to numerically integrate, a challenge that is currently addressed by applying model approximations or reformulating with index-reduction algorithms. These algorithms exist in general-purpose software tools, but their reliance on symbolic representation makes them computationally prohibitive for large network-wide EMT models. This paper derives and presents two modular index-reduced subsystem models that allow EMT models to be integrated with standard solvers, without approximations or symbolic algorithms. Both subsystems include a transformer, one isolated and one machine-coupled. We measure the computational performance of constructing EMT models with up to 1152 buses using the custom subsystem models and the symbolic algorithms. The custom approach reduces memory usage and runtime of model construction by several orders of magnitude compared to the general approach, shifting the bottleneck from construction to integration.

Monocular depth estimation (MDE) has attracted increasing interest in the past few years, owing to its important role in 3D vision. MDE is the estimation of a depth map from a monocular image/video to represent the 3D structure of a scene, which is a highly ill-posed problem. To solve this problem, in this paper, we propose a LiftFormer based on lifting theory topology, for constructing an intermediate subspace that bridges the image color features and depth values, and a subspace that enhances the depth prediction around edges. MDE is formulated by transforming the depth value prediction problem into depth-oriented geometric representation (DGR) subspace feature representation, thus bridging the learning from color values to geometric depth values. A DGR subspace is constructed based on frame theory by using linearly dependent vectors in accordance with depth bins to provide a redundant and robust representation. The image spatial features are transformed into the DGR subspace, where these features correspond directly to the depth values. Moreover, considering that edges usually present sharp changes in a depth map and tend to be erroneously predicted, an edge-aware representation (ER) subspace is constructed, where depth features are transformed and further used to enhance the local features around edges. The experimental results demonstrate that our LiftFormer achieves state-of-the-art performance on widely used datasets, and an ablation study validates the effectiveness of both proposed lifting modules in our LiftFormer.

The purpose of this paper is to investigate the coherent feedback $H^\infty$ control problem for linear quantum systems. A key contribution is a simplified design methodology that guarantees closed-loop stability and a prescribed level of disturbance attenuation. It is shown that for general linear quantum systems, a physically realizable quantum controller can be obtained by solving at most four Lyapunov equations. In the passive case, a necessary and sufficient condition is provided in terms of two uncoupled pairs of Lyapunov equations. These results represent a significant simplification over the standard approach, which requires solving two coupled algebraic Riccati equations. The effectiveness of the proposed method is demonstrated through two typical quantum optical devices: an empty optical cavity and a degenerate parametric amplifier. These results provide a computationally efficient procedure for the robust and optimal control of quantum optical and optomechanical systems.

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce reconstructions with deviation from the original images, leading to suboptimal compression results. To address this problem, in this paper, we propose a Noise Constrained Diffusion (NC-Diffusion) framework for high fidelity image compression. Unlike existing diffusion-based compression methods that add random Gaussian noise and direct the noise into the image space, the proposed NC-Diffusion formulates the quantization noise originally added in the learned image compression as the noise in the forward process of diffusion. Then a noise constrained diffusion process is constructed from the ground-truth image to the initial compression result generated with quantization noise. The NC-Diffusion overcomes the problem of noise mismatch between compression and diffusion, significantly improving the inference efficiency. In addition, an adaptive frequency-domain filtering module is developed to enhance the skip connections in the U-Net based diffusion architecture, in order to enhance high-frequency details. Moreover, a zero-shot sample-guided enhancement method is designed to further improve the fidelity of the image. Experiments on multiple benchmark datasets demonstrate that our method can achieve the best performance compared with existing methods.

Implicit Neural Video Representation (INVR) has emerged as a novel approach for video representation and compression, using learnable grids and neural networks. Existing methods focus on developing new grid structures efficient for latent representation and neural network architectures with large representation capability, lacking the study on their roles in video representation. In this paper, the difference between INVR based on neural network and INVR based on grid is first investigated from the perspective of video information composition to specify their own advantages, i.e., neural network for general structure while grid for specific detail. Accordingly, an INVR based on mixed neural network and residual grid framework is proposed, where the neural network is used to represent the regular and structured information and the residual grid is used to represent the remaining irregular information in a video. A Coupled WarpRNN-based multi-scale motion representation and compensation module is specifically designed to explicitly represent the regular and structured information, thus terming our method as CWRNN-INVR. For the irregular information, a mixed residual grid is learned where the irregular appearance and motion information are represented together. The mixed residual grid can be combined with the coupled WarpRNN in a way that allows for network reuse. Experiments show that our method achieves the best reconstruction results compared with the existing methods, with an average PSNR of 33.73 dB on the UVG dataset under the 3M model and outperforms existing INVR methods in other downstream tasks. The code can be found at https://github.com/yiyang-sdu/CWRNN-INVR.git}{https://github.com/yiyang-sdu/CWRNN-INVR.git.

High-dimensional hyperspectral imaging (HSI) enables the visualization of ultrafast molecular dynamics and complex, heterogeneous spectra. However, applying this capability to resolve spatially varying vibrational couplings in two-dimensional infrared (2DIR) spectroscopy, a type of coherent multidimensional spectroscopy (CMDS), necessitates prohibitively long data acquisition, driven by dense Nyquist sampling requirements and the need for extensive signal accumulation. To address this challenge, we introduce a physics-informed neural representation approach that efficiently reconstructs dense spatially-resolved 2DIR hyperspectral images from sparse experimental measurements. In particular, we used a multilayer perceptron (MLP) to model the relationship between the sub-sampled 4D coordinates and their corresponding spectral intensities, and recover densely sampled 4D spectra from limited observations. The reconstruction results demonstrate that our method, using a fraction of the samples, faithfully recovers both oscillatory and non-oscillatory spectral dynamics in experimental measurement. Moreover, we develop a loss-aware adaptive sampling method to progressively introduce potentially informative samples for iterative data collection while conducting experiments. Experimental results show that the proposed approach achieves high-fidelity spectral recovery using only $1/32$ of the sampling budget, as opposed to exhaustive sampling, effectively reducing total experiment time by up to 32-fold. This framework offers a scalable solution for accelerating any experiments with hypercube data, including multidimensional spectroscopy and hyperspectral imaging, paving the way for rapid chemical imaging of transient biological and material systems.

The low-rank alternating direction implicit (ADI) method is an efficient and effective solver for large-scale standard continuous-time algebraic Riccati equations that admit low-rank solutions. However, the existing low-rank ADI algorithm for Riccati equations (RADI) cannot be directly applied to general-form Riccati equations. This paper introduces a generalized RADI algorithm based on an $LDL^\top$ factorization, which efficiently handles the general Riccati equations arising in important applications like state estimation and controller design. An efficient implementation is presented that avoids the Sherman-Morrison-Woodbury formula and instead uses a low-rank Cholesky factor ADI method as the base algorithm to compute low-rank factors of general-form Riccati equations. Sample MATLAB-based implementations of the proposed algorithm are also provided. An approach for automatically and efficiently generating ADI shifts is discussed. Numerical examples solving several Riccati equations of orders ranging from $10^6$ to $10^7$ accurately and efficiently are presented, demonstrating the effectiveness of the proposed algorithm.

Decentralized Gaussian process (GP) methods offer a scalable framework for multi-agent scalar-field estimation by replacing a centralized global model with multiple local models maintained by individual agents. A team of agents operates through overlapping domains; neighboring agents generally produce inconsistent distributions over shared regions. This paper investigates whether these inter-agent posterior discrepancies can be systematically exploited to improve team-level predictive performance and answers this question positively through a novel decentralized intersection data-sharing and assimilation protocol. Specifically, each agent constructs neighbor-specific packets from its local GP together with the geometry of the overlap between subdomains and selectively assimilates information received from neighboring agents to improve consistency of its posterior over the shared regions. The proposed architecture preserves locality in both computation and communication, supports decentralized neighbor-to-neighbor data assimilation, and allows local GP models to evolve cooperatively across the network without requiring the exchange full packet exchange or centralized inference.

The increasing interconnection of power systems through AC and DC links enables energy storage units to access multiple electricity markets yet most existing arbitrage models remain limited to singlemarket participation This gap restricts understanding of the economic value and operational constraints associated with crossborder storage operation To address this an optimal multiregion energy storage arbitrage model is developed for a gridscale battery located at one end of an interconnector linking two distinct dayahead markets The formulation incorporates battery capacity and ramping limits converter and interconnector losses and marketspecific buying and selling prices Using disjunctive linearization of nonlinear terms this work exactly reformulates the multiregion energy arbitrage optimization as a mixedinteger linear programming problem The proposed formulation ensures that the battery either charges or discharges from all participating energy markets simultaneously at any given time Case studies using eight years of BelgianUK price data demonstrate that multiregion participation can increase arbitrage revenue by more than 40% compared to local energy arbitrage operation only while also highlighting the negative impact of interconnector congestion on achievable gains The results indicate that crossborder market access substantially enhances storage profitability while considering the cycle of battery and that the proposed formulation provides a computationally efficient framework for evaluating and operating storage assets in interconnected power systems Finally a pseudoefficiency term is introduced to improve battery utilization by discarding less profitable charging and discharging battery cycles

Physics-informed neural networks (PINNs) have emerged as a powerful framework for modeling physical systems and solving inverse problems. In such settings, sensors are deployed to capture observable system responses; however, the quality of reconstruction critically depends on how these sensors are selected. Existing sensor selection strategies for PINNs are closely related to active learning and experimental design, typically relying on iterative refinement schemes that sequentially add sensors and retrain the model. While effective under limited data regimes, these approaches incur substantial computational cost due to repeated retraining and primarily focus on selecting subsets of sensors, without providing a global characterization of sensor importance. In this work, we propose FOSSA, a first-order optimality-based sensor selection algorithm for inverse PINNs. Unlike existing methods, FOSSA evaluates sensor importance in a post-training manner, requiring only a single trained PINN. FOSSA assigns importance scores to all candidate sensing locations based on the first-order optimality condition at convergence. To improve robustness, a refinement scheme is further proposed to handle instability in the inverse solver. FOSSA facilitates a global assessment of the contribution of each sensor to reconstruction. We validate the proposed approach on the inverse electrocardiography (ECG) modeling and show that not all sensors contribute positively to predictive performance. Incorporating low-importance sensors can, in fact, degrade reconstruction accuracy. These findings highlight the need for principled sensor importance evaluation and provide a scalable pathway for guiding sensor deployment in physics-informed inverse modeling.

The mean-field Schrödinger bridge (MFSB) problem concerns designing a minimum-effort controller that guides a diffusion process with nonlocal interaction to reach a given distribution from another by a fixed deadline. Unlike the standard Schrödinger bridge, the dynamical constraint for MFSB is the mean-field limit of a population of interacting agents with controls. It serves as a natural model for large-scale multi-agent systems. The MFSB is computationally challenging because the nonlocal interaction makes the problem nonconvex. We propose a generalization of the Hopf-Cole transform for MFSB and, building on it, design a Sinkhorn-type recursive algorithm to solve the associated system of integro-PDEs. Under mild assumptions on the interaction potential, we discuss convergence guarantees for the proposed algorithm. We present numerical examples with repulsive and attractive interactions to illustrate the theoretical contributions.

While the ASAM OpenSCENARIO 2.1 Domain-Specific Language (DSL) enables declarative, intent-driven authoring for Scenario-Based Testing (SBT), its integration into open-source simulators like CARLA remains limited by legacy parsers. We propose a multi-pass modern compiler architecture that translates the OpenSCENARIO 2.1 DSL directly into executable CARLA behaviors. The pipeline features an ANTLR4 frontend for Abstract Syntax Tree (AST) generation, a semantic middle-end, and a runtime backend that synthesizes deterministic py_trees behavior trees. Mapping the standardized domain ontology directly to CARLA's procedural API via a custom method registry eliminates the need for external logic solvers. A demonstrative multi-actor cut-in and evasive maneuver, selected from a wider suite of validated scenarios, confirms the compiler's ability to process concurrent actions, dynamic mathematical expressions, and asynchronous signaling. This framework establishes a functional baseline for reproducible, large-scale SBT, paving the way for future C++ optimizations to mitigate current Python-based computational overhead.

As edge AI deployments scale to billions of devices running always-on, real-time compound AI pipelines, they represent a massive and largely unmanaged source of energy consumption and carbon emissions. To reduce carbon emissions while maximizing Quality-of-Service (QoS), this paper proposes FM-CAC, a proactive carbon-aware control framework that leverages a battery as an active temporal buffer. By decoupling energy acquisition from energy consumption, FM-CAC can maximize the use of low-carbon energy, substantially reducing carbon emissions. At each control step, FM-CAC jointly optimizes the software pipeline variant, the hardware operating point, and the battery charging and discharging actions. To support this decision process, FM-CAC leverages edge-friendly Time-Series Foundation Models (TSFMs) for zero-shot carbon forecasting and integrates these forecasts into a dynamic programming solver with deferred cost attribution to prevent myopic battery depletion. Results show that FM-CAC reduces carbon emissions by up to 65.6% while maintaining near-maximum inference accuracy.

In network congestion games, system operators often utilize latency models, estimated from real-world traffic flow and travel time data, to design monetary incentives which steer equilibrium user behaviors towards lowering system-wide latency. This work studies the impact of latency model uncertainty when designing incentives in non-atomic network congestion games. Our approach leverages distributionally robust optimization (DRO), which captures data-driven uncertainty in latency models by considering worst-case distribution shifts. We prove that, under mild and practically relevant assumptions, the distributionally robust tolling problem in single origin-destination, affine-latency congestion games can be solved via convex programming. Numerical simulations illustrate that tolls designed to be distributionally robust against unknown disturbances can outperform tolls designed using fixed, nominal disturbance models in minimizing system-wide latency.

Optical Music Recognition (OMR) aims to convert printed or handwritten music score images into editable symbolic representations. This paper presents an end-to-end OMR framework that combines residual bottleneck convolutions with bidirectional gated recurrent unit (BiGRU)-based sequence modeling. A convolutional neural network with ResNet-v2-style residual bottleneck blocks and multi-scale dilated convolutions is used to extract features that encode both fine-grained symbol details and global staff-line structures. The extracted feature sequences are then fed into a BiGRU network to model temporal dependencies among musical symbols. The model is trained using the Connectionist Temporal Classification loss, enabling end-to-end prediction without explicit alignment annotations. Experimental results on the Camera-PrIMuS and PrIMuS datasets demonstrate the effectiveness of the proposed framework. On Camera-PrIMuS, the proposed method achieves a sequence error rate (SeER) of $7.52\%$ and a symbol error rate (SyER) of $0.45\%$, with pitch, type, and note accuracies of $99.33\%$, $99.60\%$, and $99.28\%$, respectively. The average training time is 1.74~s per epoch, demonstrating high computational efficiency while maintaining strong recognition performance. On PrIMuS, the method achieves a SeER of $8.11\%$ and a SyER of $0.49\%$, with pitch, type, and note accuracies of $99.27\%$, $99.58\%$, and $99.21\%$, respectively. A fine-grained error analysis further confirms the effectiveness of the proposed model.

Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the development of algorithms to support the early diagnosis of neurodegenerative diseases, including Amyotrophic Lateral Sclerosis (ALS). Voice changes in subjects suffering from ALS typically manifest as progressive dysarthria, which is a prominent neurodegenerative symptom because it affects patients as the disease progresses. Since voice signals are complex data, the development and use of advanced AI techniques are fundamental to extracting distinctive patterns from them. Validating AI algorithms for ALS diagnosis and monitoring using voice signals is challenging, particularly due to the lack of annotated reference datasets. In this work, we present the outcome of a collaboration between a multidisciplinary team of clinicians and Machine Learning experts to create both a clinically annotated validation dataset and the "Speech Analysis for Neurodegenerative Diseases" (SAND) challenge based on it. Specifically, by analyzing voice disorders, the SAND challenge provides an opportunity to develop, test, and evaluate AI models for the automatic early identification and prediction of ALS disease progression.

Data-driven models for building thermal dynamics are a scalable approach for enabling energy-efficient operation through fault detection & diagnosis or advanced control. To obtain accurate models, measurement data from a target building spanning months to years are required. Transfer Learning (TL) mitigates this challenge by employing pretrained models based on single or multiple source buildings. General multi-source TL models promise to outperform single-source TL, but alternative multi-source modeling architectures remain to be explored, and evaluation on real-world data is missing. Moreover, time series foundation models (TSFM) have emerged as candidates for the best-performing general models. Hence, we conduct a first, comprehensive assessment of general modeling approaches for building thermal dynamics, including multi-source TL and TSFMs. Our assessment includes ablations using four state-of-the-art multi-source TL architectures and evaluations on synthetic as well as real-world data. We demonstrate that multi-source TL models are highly effective in accurately modeling buildings in real-world applications, yielding up to 63% lower forecasting errors compared to single-source TL. Moreover, our results suggest a trade-off between multi-source TL models exclusively pretrained with building data and TSFMs pretrained with a multitude of different time series, revealing that data from 16-32 source buildings must be available over 1 year for pretraining multi-source TL models to consistently outperform TSFMs as evaluated using the mean absolute error. These findings provide practical guidance for selecting modeling strategies based on the number of source buildings available for pretraining multi-source TL models.

Sleep staging is essential for the assessment of sleep quality and the diagnosis of sleep-related disorders. Conventional polysomnography (PSG), while considered the gold standard, is intrusive, labor-intensive, and unsuitable for long-term monitoring. This study evaluates the performance of the Sleepal AI Lamp, a contactless, radar-based consumer-grade sleep tracker, in comparison with gold-standard polysomnography (PSG), using a large-scale dataset comprising 1022 overnight recordings. We extract multi-scale respiratory and motion-related features from radar signals to train a frequency-augmented deep learning model. For the binary sleep-wake classification task, experimental results demonstrated that the model achieved an accuracy of 92.8% alongside a macro-averaged F1 score of 0.895. For four-stage classification (wake, light NREM (N1 + N2), deep NREM (N3), REM), the model achieved an accuracy of 78.5% with a Cohen's kappa coefficient of 0.695 in healthy individuals and maintained a stable accuracy of 77.2% with a kappa of 0.677 in a heterogeneous population including patients with varying severities of obstructive sleep apnea (OSA). These experimental results demonstrate that the sleep staging performance of the contactless Sleepal AI Lamp is in high agreement with expert-labeled PSG sleep stages. Our findings suggest that non-contact radar sensing, combined with advanced temporal modeling, can provide reliable sleep staging performance without requiring physical contact or wearable devices. Owing to its unobtrusive nature, ease of deployment, and robustness to long-term use, the contactless Sleepal AI Lamp shows strong potential for clinical screening, home-based sleep assessment, and continuous longitudinal sleep monitoring in real-world medical and healthcare applications.

Existing deep learning methods for radiology report generation enhance diagnostic efficiency but often overlook physician-informed medical priors. This leads to a suboptimal alignment between the structured explanations and disease manifestations. Eye gaze data provides critical insights into a radiologist's visual attention, enhancing the relevance and interpretability of extracted features while aligning with human decision-making processes. However, despite its promising potential, the integration of eye gaze information into AI-driven medical imaging workflows is impeded by challenges such as the complexity of multimodal data fusion and the high cost of gaze acquisition, particularly its absence during inference, limiting its practical applicability in real-world clinical settings. To address these issues, we introduce Gaze2Report, a framework which leverages a scanpath prediction module and Graph Neural Network (GNN) to generate joint visual-gaze tokens. Combined with instruction and report tokens, these form a multimodal prompt used to fine-tune LoRA layers of large language models (LLMs) for autoregressive report generation. Gaze2Report enhances report quality through eye-gaze-guided visual learning and incorporates on-the-fly scanpath prediction, enabling the model to operate without gaze input during inference.

Large volumes of medical data remain underutilized because centralizing distributed data is often infeasible due to strict privacy regulations and institutional constraints. In addition, models trained in centralized settings frequently fail to generalize across clinical sites because of heterogeneity in imaging protocols and continuously evolving data distributions arising from differences in scanners, acquisition parameters, and patient populations. Federated learning offers a promising solution by enabling collaborative model training without sharing raw data. However, incorporating differential privacy into federated learning, while essential for privacy guarantees, often leads to degraded accuracy, unstable convergence, and reduced generalization. In this work, we propose an adaptive differentially private federated learning (ADP-FL) framework for medical image segmentation that dynamically adjusts privacy mechanisms to better balance the privacy-utility trade-off. The proposed approach stabilizes training, significantly improves Dice scores and segmentation boundary quality, and maintains rigorous privacy guarantees. We evaluated ADP-FL across diverse imaging modalities and segmentation tasks, including skin lesion segmentation in dermoscopic images, kidney tumor segmentation in 3D CT scans, and brain tumor segmentation in multi-parametric MRI. Compared with conventional federated learning and standard differentially private federated learning, ADP-FL consistently achieves higher accuracy, improved boundary delineation, faster convergence, and greater training stability, with performance approaching that of non-private federated learning under the same privacy budgets. These results demonstrate the practical viability of ADP-FL for high-performance, privacy-preserving medical image segmentation in real-world federated settings.

In this work, we develop a control-theoretic framework for constrained optimization problems with composite objective functions including non-differentiable terms. Building on the proximal augmented Lagrangian formulation, we construct a plant whose equilibria correspond to the stationary points of the optimization problem. Within this framework, we propose two control strategies - a static controller and a dynamic controller - leading to two novel optimization algorithms. We provide a theoretical analysis, establishing global exponential convergence under strong convexity assumptions. Finally, we demonstrate the effectiveness of the proposed methods through numerical experiments, benchmarking their performance against state-of-the-art approaches.

Spatiotemporal chaos in fluid systems exhibits severe parametric sensitivity, rendering classical adjoint-based optimal control intractable because each operating regime requires recomputing the control law. We address this bottleneck with hyperFastRL, a parameter-conditioned reinforcement learning framework that leverages Hypernetworks to shift from tuning isolated controllers per-regime to learning a unified parametric control manifold. By mapping a physical forcing parameter {\mu} directly to the weights of a spatial feedback policy, the architecture cleanly decouples parametric adaptation from spatial boundary stabilization. To overcome the extreme variance inherent to chaotic reward landscapes, we deploy a pessimistic distributional value estimation over a massively parallel environment ensemble. We evaluate three Hypernetwork functional forms, ranging from residual MLPs to periodic Fourier and Kolmogorov-Arnold (KAN) representations, on the Kuramoto-Sivashinsky equation under varying spatial forcing. All forms achieve robust stabilization. KAN yields the most consistent energy-cascade suppression and tracking across unseen parametrizations, while Fourier networks exhibit worse extrapolation variability. Furthermore, leveraging high-throughput parallelization allows us to intentionally trade a fraction of peak asymptotic reward for a 37% reduction in training wall-clock time, identifying an optimal operating regime for practical deployment in complex, parameter-varying chaotic PDEs.

Ensuring safety under unknown and stochastic dynamics remains a significant challenge in reinforcement learning (RL). In this paper, we propose a model predictive control (MPC)-based safe RL framework, called Probabilistic Ensembles with CBF-constrained Trajectory Sampling (PECTS), to address this challenge. PECTS jointly learns stochastic system dynamics with probabilistic neural networks (PNNs) and control barrier functions (CBFs) with Lipschitz-bounded neural networks. Safety is enforced by incorporating learned CBF constraints into the MPC formulation while accounting for the model stochasticity. This enables probabilistic safety under model uncertainty. To solve the resulting MPC problem, we utilize a sampling-based optimizer together with a safe trajectory sampling method that discards unsafe trajectories based on the learned system model and CBF. We validate PECTS in various simulation studies, where it outperforms baseline methods.

Prime Video regularly conducts load tests to simulate the viewer traffic spikes seen during live events such as Thursday Night Football as well as video-on-demand (VOD) events such as Rings of Power. While these stress tests validate system capacity, they can sometimes miss service behaviors unique to real event traffic. We present a graph-based anomaly detection system that identifies under-represented services using unsupervised node-level graph embeddings. Built on a GCN-GAE, our approach learns structural representations from directed, weighted service graphs at minute-level resolution and flags anomalies based on cosine similarity between load test and event embeddings. The system identifies incident-related services that are documented and demonstrates early detection capability. We also introduce a preliminary synthetic anomaly injection framework for controlled evaluation that show promising precision (96%) and low false positive rate (0.08%), though recall (58%) remains limited under conservative propagation assumptions. This framework demonstrates practical utility within Prime Video while also surfacing methodological lessons and directions, providing a foundation for broader application across microservice ecosystems.

This paper presents a field-based evaluation of Long Range Wide Area Network (LoRaWAN) signal propagation conducted at two locations within the Aerial Experimentation and Research Platform for Advanced Wireless (AERPAW) testbed: Lake Wheeler Field and NC State University's Centennial Campus. Three distinct transmission platforms were deployed, a ground vehicle, a multirotor drone at 50 meters, and a helikite at a steady altitude of 150 meters and 300 meters approximately. These platforms enabled a comparative study on how altitude, mobility, and terrain influence wireless signal reception across a LoRaWAN gateway network. We analyze received signal strength (RSSI) and signal-to-noise ratio (SNR) as functions of distance and spreading factor (SF). Three complementary metrics are visualized: SNR versus distance with demodulation thresholds, probability of successful reception, and SNR boxplots grouped by distance bins. These plots reveal link degradation patterns and demonstrate the role of adaptive SF selection in maintaining communication reliability. To characterize propagation behavior, we apply a log-distance path loss model to empirical data from the ground vehicle experiment, which encompass both rural and urban non-line-of-sight (NLOS) conditions. Model parameters are optimized through error minimization techniques. Our results show that the helikite platform, due to its stable high-altitude position, provided the most reliable and consistent link performance. Conversely, the drone and vehicle exhibited higher variability due to movement, obstructions, and terrain-induced multipath. These findings demonstrate the influence of platform dynamics and altitude on LoRaWAN reception performance, providing support for future aerial network planning efforts.

We study asynchronous distributed decision-making for scalable multi-agent bandit submodular maximization. We are motivated by distributed information-gathering tasks in unknown environments and under heterogeneous inter-agent communication delays. To enable scalability despite limited communication delays, existing approaches restrict each agent to coordinate only with its one-hop neighbors. But these approaches assume homogeneous communication delays among the agents and a synchronous global clock. In practice, however, delays are heterogeneous, and agents operate with mismatched local clocks. That is, each agent does not receive information from all neighbors at the same time, compromising decision-making. In this paper, we provide an asynchronous coordination algorithm to overcome the challenges. We establish a provable approximation guarantee against the optimal synchronized centralized solution, where the suboptimality gap explicitly depends on communication delays and clock mismatches. The bounds also depend on the topology of each neighborhood, capturing the effect of distributed decision-making via one-hop-neighborhood messages only. The clock-mismatch penalty is expressed through a bounded oscillation of the reward in the execution times, which, unlike a Lipschitz condition, is available for discrete-valued rewards such as target monitoring. We validate the approach through numerical simulations on multi-camera target monitoring through the lenses of two different reward structures and simulation setups.

High-performance piezoelectric resonators are promising energy storage elements for piezoelectric power conversion due to their compact footprint and low loss at frequencies where conventional magnetic components become bulky and inefficient. However, their practical use is often limited by the trade-off between a high electromechanical coupling coefficient (k^2) for wide-band operation and the emergence of spurious acoustic modes that limit the resonators' inductive bandwidth. This work reports a spurious-free thickness-extensional (TE)-mode bulk acoustic wave (BAW) resonator in single-crystal lithium niobate (LN) based on a grounded-ring electrode architecture. The proposed structure is analyzed through simulation and experimentally validated using electrical characterization and laser Doppler vibrometry (LDV). The results show that the grounded ring modifies the effective boundary conditions of the acoustic device, enabling a piston-like modal response that suppresses lateral spurious modes across the inductive band. The demonstrated device operates at 10.14 MHz and achieves an electromechanical coupling coefficient of 29.6%, a maximum in-band Bode quality factor (Q_Bode) of 5230, and a figure of merit (FoM, Q*k^2) of 1548. These results establish the grounded-ring TE-mode LN BAW resonator as a practical platform for piezoelectric power conversion and a broader design approach for realizing high-performance spurious-free acoustic resonators.

The declining synchronous inertia in power systems undergoing the energy transition increases the sensitivity of system frequency to generation and interconnector disturbances, making accurate frequency risk quantification increasingly important. Existing methods for frequency risk assessment, while valuable, lack formal uncertainty quantification, continuous hazard curves, and source-level disaggregation. This paper introduces Probabilistic Frequency Hazard Analysis (PFHA), a framework that adapts the mathematical architecture of Probabilistic Seismic Hazard Analysis (PSHA), the standard methodology in earthquake engineering, to power system frequency exceedance risk. The PFHA hazard integral computes annual exceedance rates by integrating over all combinations of loss sources, disturbance sizes, and system operating states through a frequency response prediction equation with calibrated aleatory variability. The framework is implemented with a 51-source catalogue constructed from operational data, empirical loss distributions from settlement-period generation records, Bayesian occurrence rate estimation, a dual analytical and physics-based frequency response prediction architecture, and a 324-path logic tree for epistemic uncertainty quantification. Application to the Great Britain power system using four years of operational data demonstrates agreement with the independently developed Frequency Risk and Control Report to within a factor of 1.5 at 49.2 Hz, while also quantifying the risk reduction from Dynamic Containment and Low-Frequency Demand Disconnection controls. To the author's knowledge, this is the first published explicit PSHA-style hazard-integral formulation for bulk power-system frequency exceedance risk.

We present top-down and bottom-up approaches for solving large-scale instances of joint task and motion planning problems in Graphs of Convex Sets (GCS). Planning what tasks to perform and how to move between them can be encoded exactly as a Shortest Path Problem (SPP) using an Augmented GCS (AGCS), but this graph grows exponentially with the number of tasks, limiting prior work to only 11 tasks. Both of our approaches significantly improve scalability by carefully pruning the AGCS before it is constructed. The top-down approach replaces the complete graph with a sparse Delaunay graph that maintains a natural nearest-neighbor connectivity, reducing the number of vertices, edges, and subgraphs relative to the full AGCS. The bottom-up approach uses classical Traveling Salesman Problem (TSP) heuristics to create an initial ordering, then expands it within a fixed search window, pruning the AGCS to a bounded maximum width independent of the problem size. Both approaches can obtain optimal or near-optimal solutions in a fraction of the time required by the original AGCS. The bottom-up approach can solve instances with 1000 tasks in about two minutes. We additionally discuss lower bounds based on minimum 1-trees to quantify suboptimality of the proposed approaches.