Papers

The problem of simultaneous placement of distributed generators and DSTATCOMs in radial distribution networks (RDNs) is a combinatorial mixed-integer optimization problem whose scalability with growing decision dimensionality has been insufficiently explored. A cross-scale analysis of seven metaheuristic algorithms, GWO, SCA, PSO, WOA, GA, HHO and SMA, is conducted on the IEEE 33-bus, 69-bus, and 136-bus systems at three problem dimensions \( d = 4, 8, 12 \), with 30 independent runs per configuration being validated through Wilcoxon and Friedman tests. Mean-performance statistics are extended with a Catastrophic Failure Rate (CFR) metric. The main result will be that dimensional scaling serves as a behavioral discriminator. The Friedman \( \chi^2 \) rises with the dimensionality, reaching its maximum value of \( \chi^2 = 143.79 \) in the 136-bus at \( d = 12 \) that corresponds to the progressive phase separation of the algorithms into two clusters of high and low performance. GA is the best performer in terms of the lowest rank in all the configurations. SCA has low variance but convergence to increasingly sub-optimal solutions. HHO exhibits catastrophic instability at all scales. Perhaps most strikingly, GA and PSO obtain a \( 3.3\% \) CFR on the 136-bus at \( d = 12 \) while the 33-bus at identical dimensionality has a \( 73\%-83\% \) CFR, showing that topology influences the reliability in a manner that is not captured by single-system measures.

Full-duplex spoken dialogue models are trained on conversational speech in which each speaker is represented as a separate stream, but existing large-scale public speech corpora are mostly monaural, making them unsuited for SDLM training. We present DuplexChat, an open-source corpus for full-duplex spoken dialogue models, and DuplexChat-Pipe, a pipeline for constructing speaker-separated full-duplex dialogue speech from public podcast feeds. DuplexChat-Pipe filters language-specific podcast feeds, retrieves and cleans episode audio, extracts diarization-guided two-speaker dialogue clips, and applies speech separation and restoration to produce one channel per speaker. Running this pipeline yields a speaker-separated spoken dialogue corpus covering 282,634 hours of English and 132,723 hours of Japanese. Analysis results on DuplexChat show that it contains turn-taking dynamics present in human dialogues.

We address energy-efficiency (EE) maximization in a multiuser (MU) multiple-input single-output (MISO) downlink system assisted by a hybrid reconfigurable intelligent surface(RIS), where each element can be dynamically configured to operate in either active or passive mode depending on whether its power amplifier is engaged. Practical hardware effects are explicitly incorporated, including base station (BS) and RIS power budgets, active-element amplifier gain limits, amplification noise, and binary phase control. To solve the problem, we develop an alternating-optimization framework in which the BS beamforming subproblem is handled via zero-forcing with closed-form power allocation, while the RIS subproblem is addressed using a model-driven deep unfolding approach. Numerical results show that the proposed method achieves faster convergence and higher EE than the considered benchmark schemes. In particular, it attains about 30% higher EE than the procedure without deep unfolding. Furthermore, our simulations demonstrate at least 10% EE improvement over the fully active RIS configuration and up to threefold EE gains compared with the fully passive RIS design. The results also show that most of the achievable EE gain can be captured by activating only a small fraction of RIS elements and allocating only a small portion of the dynamic power budget to the RIS.

Magnetic Induction (MI) communication is effective in underground tunnels for emergency rescue vehicle due to the small-size antenna. It can highly benefit from a cooperative decode-and-forward (DF) relay to achieve a higher data rate. However, its channel gain is extremely position-and-orientation-selective. The unreachable space increases the complexity of the antenna deployment. To find the best antenna position and orientation (PO) of the relay achieving the higher data rate, this paper formulates the optimization problem of the relay MI antenna PO with tunnel constraints. To solve the problem more quickly, we propose to use geometric modeling to eliminate the tunnel constraints and develop a random-search algorithm achieving a fast convergence and excellent global search ability. Simulations show that the proposed algorithm can quickly converge to one optimum which signifies a noticeable improvement of data rate for vehicle MI systems with weak signals.

Clandestine tunneling beneath oil and gas pipelines enables fuel theft, smuggling, and sabotage, yet conventional monitoring detects damage only after a pipeline has been compromised. Ground-penetrating radar (GPR) can image such tunnels non-invasively, but manual radargram interpretation does not scale to continuous corridor surveillance, and supervised detectors require tunnel examples that are scarce in practice. We present a fully unsupervised detection pipeline trained exclusively on normal subsurface radargrams collected at a purpose-built field site containing three buried tunnels at 1.5-3 m depth. A denoising convolutional autoencoder learns the structure of anomaly-free ground; at inference, tunnels are flagged by reconstruction error. Our central contribution is a depth-restricted top-k anomaly score, which pools the highest reconstruction errors only within the depth band where tunnels can physically occur. This physically motivated rule raises AUC from 0.986 to 0.994 and cuts missed detections from 74 to 17 of 634 tunnel windows, relative to whole-image scoring, without any retraining or labels. We further show that the optimal top-k fraction interacts with the depth restriction - 1% pooling is best on full images, 5% once scoring is depth-restricted - and that spatial voting across overlapping survey windows helps weak per-image detectors but offers no benefit once the scoring rule is strong. The final system attains AUC 0.994, F1 0.975, recall 0.973, and precision 0.976 on 1,600 field test windows spanning 55 survey lines, at a 1.6% false-alarm rate, using no tunnel labels for training, scoring, or threshold calibration.

This paper addresses bistatic snapshot radio SLAM, in which a user equipment (UE) with unknown 6-D pose and clock bias is localized and environmental landmarks are reconstructed from a single multipath channel snapshot. Under mixed line-of-sight (LoS)/non-line-of-sight (NLoS) propagation, existing robust snapshot SLAM methods are mainly developed or validated in planar/2-D settings and often use path-amplitude or path-loss information for LoS handling, which makes them sensitive to calibration errors and propagation-model mismatch. We propose an amplitude-independent robust radio SLAM method built on a uniffed angle-delay formulation for LoS and single-bounce NLoS inlier paths. In the coarse stage, the method estimates the UE state and selects geometrically consistent inliers directly from angle-delay measurements, without amplitudebased LoS preclassiffcation or path-wise latent variables; the formulation is further extended to general 3-D/6-D pose estimation through twist-swing two-stage traversal initialization and local reffnement on SO(3). A subsequent Jacobian-row-equilibrated iteratively reweighted least-squares (IRLS) reffnement, combined with quasi-Akaike information criterion (QAIC) model comparison, detects the LoS path and jointly reffnes the UE state and scattering points. We also analyze formulation-speciffc local-rank properties and their minimal-set implications under unknown path identity. Simulations show that the proposed method remains competitive with calibrated amplitude-dependent baselines and is more robust to path-loss-model mismatch.

With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasingly larger and more opaque ”black-box” models. Autoencoders are among the most widely used architectures for this task; however, without a clear understanding of their internal behavior, these models tend to grow in complexity to achieve more performance gains. In this paper, we investigate whether universal behaviors can be detected from the internal operations of bias-free autoencoders through Jacobian analysis. If such behaviors exist, they may be extracted to design low-complexity image compression models inspired by high-complexity deep learning architectures.

We systematically investigate neural speech enhancement systems, ranging from very small ($\sim$10\,k parameters) to medium-large ($\sim$2-5\,M parameters), which specialize to acoustic conditions using contextual information such as speaker identity, noise type, speaker gender, spoken language, and SNR. By fine-tuning generalist models on specific data subsets, we find that specializing to a speaker's identity consistently yields the largest gains in estimated speech intelligibility and quality. In contrast, specializing to SNR, noise type, or gender offers only marginal benefits. Crucially, we show that a small model specialized to both a specific speaker and a specific noise type can match or exceed the performance of a generalist model ten times its size. Further, cross-lingual tests reveal that models specialized to a target language outperform multilingual generalists, suggesting that language is a salient feature for specialization. These findings highlight the potential of small, adaptive models for resource-constrained applications like hearing aids, which specialize on-the-fly to contextual information.

In frequency-division duplexing systems, the performance gains of pinching-antenna systems (PASS) critically depend on accurate channel state information (CSI) at the base station. However, PASS CSI exhibits structured correlations over the waveguide-antenna grid and pronounced heterogeneity across users, making conventional fixed feedback mappings difficult to generalize. To address this challenge, this letter proposes an end-to-end CSI feedback scheme over a noisy uplink feedback link based on deep joint source-channel coding, termed Shift-based Mixture-of-Experts (Shift-MoE). Specifically, Shift-MoE leverages channel-grouped one-step shift operations to capture grid dependencies without global attention, and employs a gated multilayer perceptron mixture-of-experts module to adapt to heterogeneous CSI statistics across users. Numerical results demonstrate that the proposed Shift-MoE consistently outperforms representative learning-based CSI feedback baselines in normalized mean squared error and remains effective under different system parameter settings.

Fluid Antennas (FAs)-assisted Unmanned Aerial Vehicle (UAV) networks leverage the FA position adaptivity and flexible beamforming to overcome the limitations of Fixed-Positioned Antennas (FPAs) in dynamic UAV channels and Multi-User (MU) interference. This letter investigates a dual FA-assisted UAV network for MU-Multiple-Input-Multiple-Output (MIMO) downlink communications, aiming to maximize the average achievable rate through the joint optimization of UAV trajectory, the transmit/receive FA positions, and beamforming. The formulated problem is highly coupled and non-convex. Accordingly, an efficient Alternating Optimization (AO)-based algorithm is developed for decomposed subproblems, yielding a suboptimal solution. Numerical results demonstrate significant performance gains of 120% and 110% over conventional FPA-based and existing FA-based baselines, respectively.

This study proposes a precipitation control framework integrating a realistic Numerical Weather Prediction (NWP) model with model predictive control (MPC). At each control instant in MPC, a finite-difference sensitivity matrix is constructed from the NWP model and used as a local linear model of how perturbations to the atmospheric state affect future precipitation. A sparse convex optimization problem is then solved to compute the control input, which is implemented as a perturbation to the atmospheric state. To reduce computational cost in sensitivity analysis, multiple grid points in the NWP model are treated collectively as a single block, and a uniform perturbation is applied to all points within each block. Moreover, a tailored convex optimization problem is introduced to effectively control the accumulated precipitation at the end of a weather event, using a prediction horizon much shorter than the entire event duration while promoting spatially sparse atmospheric perturbations. To evaluate the proposed MPC method, four control methods are compared: (i) initial-only open-loop optimal control (IO-OL), (ii) full-horizon open-loop optimal control (FH-OL), (iii) shrinking-horizon optimal control (SHOC) with a fixed terminal time, and (iv) single-move MPC with a fixed prediction-horizon length. Numerical experiments on a warm bubble benchmark demonstrate that MPC achieves precipitation reduction comparable to SHOC while reducing the total computational time relative to FH-OL and SHOC. Moreover, despite using a linear prediction model, MPC successfully achieves a challenging level of precipitation reduction, even when open-loop optimal control methods, namely, IO-OL and FH-OL, fail because of nonlinear atmospheric evolution. These findings suggest that MPC is a promising control framework for NWP-based precipitation reduction in complex weather events.

Aerial robots are increasingly moving from remote observation toward physical interaction with objects, surfaces, structures, loads, and surrounding flows. This review argues that aerial manipulation cannot be understood as classical manipulation simply mounted on a flying base. Because flying agents remain aloft through continuous momentum and energy exchange with the surrounding medium, support, locomotion, stabilization, and task-directed interaction are intrinsically coupled. Building on broad views of manipulation as intentional environmental regulation through physical interaction, we propose a medium-aware interpretation of aerial manipulation in which interaction may be mediated by contact, by the surrounding fluid, or by both. The review organizes biological and robotic examples into a repertoire of interaction modes and a capability ladder, then develops an actuation-geometric viewpoint in which redundancy induces task-equivalent fibers. Internal motion along these fibers can trade energy for active readiness, aerodynamic promptness, and passive medium coupling. This perspective clarifies why aerial manipulation is difficult, why biological flyers remain broader than robotic systems, and how future platforms may command forces while also shaping how the medium acts back on them.

Inverse Synthetic Aperture Radar (ISAR) imaging of UAV swarms presents significant challenges due to the coherent superposition of backscattered signals from multiple closely spaced targets. This work explores the extension of the Fast Reweighted Atomic Norm Denoising (FRAND) algorithm to this multi-target scenario. We develop a comprehensive mathematical framework that reformulates the atomic norm minimization problem for swarm imaging, incorporating weighted regularization and efficient optimization via the TwoDimensional Alternating Direction Method of Multipliers (2DADMM). The proposed method handles both sparse aperture conditions and additive white Gaussian noise while maintaining computational efficiency. We simulate an ISAR system receiving composite echoes from UAV swarms, each modeled with distinct scattering centers. The results demonstrate that FRAND effectively disentangles the mixed signals and generates high-resolution range-Doppler profiles for individual UAVs, outperforming traditional methods like Multiple Signal Classification (MUSIC) and Cadzow in low Signal-to-Noise Ratio (SNR) conditions. Quantitative evaluation using MeanSquare Error (MSE) criteria confirms the superiority of the proposed approach. This study establishes the strong potential of atomic norm minimization for complex multi-target radar imaging applications.

Spatial consistency is a fundamental physical property of wireless channels that reflects the smooth evolution of the channel between spatial locations. At the cluster level, it requires similar multipath components (MPCs) remain grouped into the same clusters as the transceivers move, enabling consistent cluster tracking. Cluster-level spatial consistency is essential for realistic cluster-based channel models, especially for potential 6G techniques such as massive MIMO, integrated sensing and communication, and terahertz (THz) communication. However, existing clustering and tracking methods do not fully exploit spatial correlations of MPCs. In tracking-after-clustering, clustering and tracking are decoupled, while joint clustering-and-tracking mainly relies on cluster centers from the previous snapshot. In this work, we propose a Mahalanobis-distance-based simultaneous clustering and tracking (MD-SCT) algorithm to capture the joint distribution of clustered MPCs in the delay, angular and spatial domains. Under Mahalanobis distance, MPCs in successive snapshots are associated with existing clusters, thereby inherently tracking while clustering. The algorithm is further applied in the sub-THz band. Performance is evaluated using mean square successive difference and gradient change rate. The results demonstrate that the proposed algorithm yields smoother cluster evolution. This improves the reliability of clustered channels for spatial consistency modeling in 6G.

We develop a repair-oriented inspection and maintenance decision framework for water distribution networks. This work is motivated by utilities operating in data-sparse environments, such as in remote locations like the U.S. Virgin Islands, where data collection about network state and underground pipeline outages is limited to above-ground and easy to access information (e.g., water tank levels and pump operations). We formulate the problem as a discounted Markov decision process and integrate it with high-fidelity hydraulic simulation. The model captures latent system dynamics without requiring pipe-level sensing. The results reveal state-dependent optimal policies and heterogeneous failure characteristics across pipes, including rare but high-impact behaviors. We further show that certain observable system states uniquely correspond to specific pipe failures, enabling a form of virtual sensing. These findings demonstrate that system-level dynamics can support inspection planning and maintenance decisions under uncertainty in resource-constrained settings.

This report presents our solutions to the QoMEX 2026 Grand Challenge on Video Quality Assessment for Asymmetric Encoded Videos, comprising a full-reference (FR) model, CompressedVQA-AEV-FR, and a no-reference (NR) model, CompressedVQA-AEV-NR. The FR approach leverages a Swin-B backbone to extract multi-stage similarity statistics between reference and distorted videos for quality prediction. For the NR setting, our model employs complementary frame-level encoders based on SigLIP2 and Swin-B, followed by temporal mean pooling and cross-fold ensembling to estimate perceptual quality without reference data. Our CompressedVQA-AEV-FR achieves first place in the FR track of QoMEX 2026 Grand Challenge, while CompressedVQA-AEV-NR secures fourth place in the NR track, demonstrating the effectiveness of our proposed models. The code is available at https://github.com/sunwei925/CompressedVQA-AEV.

Home Energy Management Systems (HEMS) can reduce residential electricity costs, but many require users to express everyday preferences as technical constraints. This paper presents a tool-calling ReAct agent that converts natural-language requests into schedules for multiple household appliances using half-hourly Octopus Agile prices, weather forecasts, photovoltaic generation estimates, and household demand data. Five large language model backends are evaluated against a mixed-integer linear programming benchmark across dynamic tariff conditions, constraint conflicts, weather-aware scheduling, and a seven-day rolling deployment. Native function calling achieves high scheduling success and near-optimal cost on ordinary tariff days, whereas text-parsed actions reduce reliability. Constraint-conflict testing shows that low cost does not guarantee safe or feasible behaviour. Claude Sonnet 4.6 performs best in power-cap and infeasibility scenarios, while Qwen-3 achieves higher overall constraint compliance than GPT-4o-mini. The evaluation also identifies fabricated schedules, failed commitments, and reasoning-to-action failures in which models explain a deadline correctly but commit an invalid schedule. Weather-aware scheduling reduces cost and increases solar self-consumption under overcast conditions, but provides limited or adverse economic value under some dynamic-price regimes. Across the evaluated seven-day period, the agents capture 96.7-98.0% of the savings available between an off-peak timer and the MILP oracle and outperform the rule-based policies. The results support LLM-based HEMS orchestration, provided that every committed schedule is checked by an independent deterministic feasibility validator before actuation. Code and a live demonstration are available at https://github.com/sokistar24/ecohome-experiments and https://www.ecohomeagent.com/.

Water electrolysis plants, hyperscale data centers, and aluminum potlines represent gigawatts of demand-side flexibility for bulk power system balancing, operational planning, and procurement services. Such loads are scheduled through per-interval power bounds and horizon energy windows, whereas co-located battery energy storage systems (BESS) operate under state-of-charge dynamics. The two formulations share no common mathematical structure, and the joint procurement value of co-located loads and storage goes unrealized as a result. This paper establishes the connection between the two formulations through a virtual storage (VS) equivalence. Every feasible large-load trajectory under power-bound and energy-window constraints is a valid charge trajectory of a VS device that operates at unity accounting efficiency in the grid power balance. Production and service-level costs lie outside this abstraction and enter the dispatch through curtailment opportunity costs. For a portfolio co-located with a BESS, aggregation reduces the constraint count from O(NT) to O(T) and yields a co-dispatch price for both resources. Validation on the IEEE RTS-GMLC with three representative load classes shows that virtual storage delivers the dominant share of joint procurement savings. In the tested case, savings are additive because the two resources dispatch to non-overlapping intervals, and the curtailment shadow price tracks the peak-price band onset rather than the daily peak price.

Hyperscale data centers and other large concentrated loads can impose substantial new demand on existing transmission networks. If import corridors lack sufficient transfer capability, operators may need to curtail load, delay interconnection, or reinforce the network to maintain reliable service. An energy storage system (ESS) deployed as a storage-as-transmission asset (SATA) offers a non-wires alternative by providing operator-directed support to constrained import corridors. However, the operating-level reliability value of SATA dispatch remains insufficiently quantified. This paper evaluates operator-directed SATA using a day-ahead DC optimal power flow that co-optimizes generation, ESS dispatch, and load curtailment across Monte Carlo scenarios of demand and generator availability. Operating reliability is assessed using expected energy not served (EENS), loss-of-load hours (LOLH), and the conditional value at risk (CVaR) of daily unserved energy. Congestion-price and flow-sensitivity metrics are used to identify the limiting corridor and storage location. The interconnection is then screened to determine whether SATA is suitable, reinforcement is required, or storage would provide little transmission value. Results show that operator-directed SATA reduces average unserved energy, loss-of-load exposure, and tail risk compared with deploying the same ESS for pure arbitrage. These results demonstrate that the operating designation of storage is a primary driver of its transmission value.

The modulating function method is an algebraic framework that, thus far, has been used for state and parameter estimation, as well as fault detection, of linear, fractional-order, distributed, and some nonlinear systems. At the core of the method lies the modulating function, which can either be selected directly or be obtained as a solution to an auxiliary system. By introducing the notion of dual modulating functions and dual modulations using auxiliary systems and duality, this paper shows that this framework is not only an estimation framework, but also a controller design framework for LTV systems. In particular, necessary and sufficient conditions for the existence of the associated control laws are introduced; the well-known state feedback law is obtained as a particular case of the dual modulation approach, along with output feedback, LTI sliding mode control, the reachability gramian, and the state-transition matrix; and a new fixed-time control law is proposed for both LTI and LTV systems, including an estimate of the transient behavior. Moreover, numerical simulations of the newly proposed control law are performed, indicating similar performance levels to a benchmark LQR even when handling unmatched disturbances.

Low-precision neural networks are attractive for resource-constrained hardware, but fixed-point arithmetic introduces failure modes that are often hidden by idealised quantisation models. In particular, two's-complement overflow wrapping can corrupt hidden activations by changing both their magnitude and sign, leading to unstable numerical error propagation and severe accuracy degradation. This paper proposes a Lyapunov-stabilised quantisation framework for low-precision neural networks operating under hardware-style wrapping arithmetic. The hidden-state energy is monitored through a layerwise Lyapunov function, and a monotone projection is applied to enforce bounded and non-increasing state evolution across depth. The method is evaluated on MNIST using a compact patch-based transformer under post-training quantisation and quantisation-aware training with fixed-point bit-widths from 4 to 16 bits. Monte Carlo results show that unconstrained wrapped quantisation-aware training collapses to near-chance accuracy across 6-16 bits, with activation overflow rates exceeding 11%. In contrast, the proposed monotone Lyapunov projection suppresses activation overflow to below 0.012% and restores stable low-precision learning, achieving 86.55% accuracy at 12 bits. These results demonstrate that Lyapunov-based state control can act as a hardware-aware stabilisation mechanism for reliable fixed-point neural inference and training.

Linear spatial filters (beamformers) enable robust, generalizable and interpretable speech enhancement with performance guarantees under ideal parameterization. Modern beamformers are often parameterized by deep neural networks, whose performance degrades in dynamic scenarios with multiple moving speakers of unknown directions. We propose a data-driven beamforming pipeline, which only requires an estimate of the target's initial direction. Building on a higher-order ambisonics representation, we show that neural temporal-spectral processing can be decoupled from linear spatial processing, and thereby achieve generalizable and array-agnostic enhancement. By incorporating autoregression into a frame-wise causal framework, we maintain consistent performance throughout fast speaker motion and long recordings. Evaluation on synthetic data demonstrates robust enhancement under challenging conditions with closely spaced and crossing speakers. Real-world recordings in a dynamic office meeting scenario complement these findings and show generalizability across varying ambisonics orders.

The assessment of planktonic standing stocks and microorganism structures is critical for understanding upper ocean biological processes. Currently, autonomous underwater vehicles (AUVs) equipped with in-situ optical imaging and artificial intelligence (AI) methods offer a promising solution for persistent surveillance, mapping and monitoring of planktonic life. However, current AI methods often lack robustness in dynamic, unstructured environments, where environmental noise and non-biological artifacts lead to frequent misclassifications. Standard convolutional neural network (CNN) classifiers often struggle with such conditions, leading to misclassifications that require time-consuming manual validation by marine biologists. To address this issue, we propose a novel robustness verification framework for in-situ plankton classifiers based on reachability analysis. We also introduce a continuous-time neural ordinary differential equation (neural ODE) classification model leveraging the high-resolution imaging capabilities of the SilCam particle imager. In this paper, we demonstrate the effectiveness of the proposed framework by formally verifying the robustness of the neural ODE model against environmental perturbations. We demonstrate that our verification framework acts as an automated filter providing formal guarantees of model stability against ambiguous data, thereby improving the reliability of autonomous sampling and reducing the post-processing workload.

Non-invasive blood glucose estimation from wearable physiological signals remains difficult because longitudinal photoplethysmography (PPG) data are subject to distribution drift, whereas reference capillary blood glucose labels are sparse and costly to acquire. We propose a \rev{deep-learning-based} dynamic incremental learning (DIL) framework that combines a mutual entropy-optimized replay-based dynamic clustering module (MERDC) with an uncertainty-quantified proxy gradient bridging agent (PGBA) for label-efficient adaptation to unlabeled PPG streams. To support this setting, we further establish a longitudinal benchmark dataset comprising PPG, reference capillary blood glucose, and cuff blood pressure measurements from 183 participants collected over 285 days, and we make this resource available to the research community. Under 5-fold subject-independent validation, the proposed method achieves a mean absolute error (MAE) of $0.64 \pm 0.01$ millimoles per liter (mmol/L) and a root mean square error (RMSE) of $1.29 \pm 0.10$ mmol/L, with $97.69 \pm 1.63\%$ of estimates falling within Clarke zones A+B. Aggregation-level analyses further support the robustness of the observed error distribution beyond window-level evaluation. \rev{These results provide a proof-of-concept for adaptive non-invasive glucose estimation in wearable physiological sensing and establish a longitudinal benchmark for subsequent research.

Power-constrained 25kV AC railway sections, particularly under degraded feeding, are protected today by blunt, section-wide power limits that penalise every train irrespective of whether it contributes to the binding condition. This paper presents a real-time, location-aware controller that restores the electrical feasibility of a feeding section with minimal impact on the timetable: it curtails only the trains that bind, where and when they bind, evaluating feasibility and per-train available power online with a solver-free estimate as an in-loop surrogate for the full power flow. Because the estimate is accurate on average but slightly optimistic at the binding instants, the controller screens with a small voltage margin, and a full multi-conductor power-flow solver confirms the restored feasibility. The resulting selective-curtailment policy is delivered through a cloud-to-edge connected driver advisory system. On a representative GB 25kV corridor under outage feeding, solver-selected to be infeasible uncontrolled yet restorable, the controller is compared against the uncontrolled case, the incumbent static limit, and an offline genetic-algorithm optimum, with every feasibility figure solver-validated. The static limit restores feasibility at a large journey-time cost by throttling the whole section; the location-aware controller restores the same feasibility at one thirtieth of that cost by advising a single train, and matches the offline optimum's solution in about a second and a half against the optimiser's minute. Aggregate peak demand is unmoved, because the active constraint is local far-field voltage rather than gross demand. All claims are relative to the baselines on a representative corridor; a specific-route deployment study is future work.

Low-Earth-orbit (LEO) relay networks deliver finite objects – sensing tiles, telemetry blocks, model updates, and checkpoints – over intermittent inter-satellite and space-to-ground contact plans. Partial delivery is insufficient when the complete object misses its deadline. When an object is split across candidate paths, a path-private evaluation can count the same contact service more than once and silently under-count completion. We develop a residual-service-aware delivery layer that consumes candidate paths from contact-plan route generation and tests whether the complete object can be delivered before its deadline under per-edge first-in-first-out residual service. Under controlled shared-contact contention, path-private evaluation under-counts completion by up to 154 s and can report finite completion for a fixed plan with no residual-service completion. For edge-disjoint complementary contacts, the layer reduces to fixed-path service; we derive a sufficient service-budget condition under which two-way striping strictly enlarges the feasible payload region. We verify a restricted exhaustive reference, characterize runtime over a 20-180-satellite procedural contact model, and show that bounded two-way striping reduces mean and median gaps to the restricted reference by about 40%, while P90 and worst-case gaps remain unchanged.

Binary change detection in remote sensing requires both complete changed-region localization and accurate boundary delineation. We present MambaRefine-CD, a region-boundary temporal refinement framework built on a shared MambaVision encoder. The proposed D-RBI module constructs temporal evidence from paired features, absolute differences, and signed differences, then separates it into region and Sobel-conditioned boundary streams. Region features are enhanced with CRAM-lite and decoded by an adaptive receptive-field FPN, while the finest boundary stream guides a bounded residual refinement of the coarse prediction. Experiments on DSIFN-CD and WHU-CD show strong changed-class F1 and IoU under verified evaluation settings, and ablations support the contribution of signed temporal evidence and the full region-boundary refinement pipeline.

Explainable AI (XAI) is important for deploying machine learning systems in domains where stakes are very high and where transparency, trust and accountability are critical. Although black box models like deep neural networks often perform with high efficiency, interpreting their decisions remains as a difficult task. This paper proposes a reusable end-to-end XAI framework that is the combination of prediction, explanation generation, evaluation and converting these explanations into natural language text of explanation which can be easily understood by the non-technical stakeholders as well. This framework initially trains deep neural network for both classification and regression tasks. Local and global explanations are generated using XAI algorithms, including Local Interpretable Model-agnostic Explanation (LIME) and SHapley Additive exPlanations (SHAP) respectively. To evaluate these explanations, we use fidelity and stability metrics to know how accurately and consistently explanations reflect the model behavior. The generated explanation includes feature importance scores, prediction specific attributes, and then transformed into a structured input to the Large Language Model (LLM), which generates a natural language explanation through which everyone can understand the explanations generated by XAI algorithms. This framework is tested on power system fault dataset detection dataset and building energy labels dataset. For fault detection, the neural network model achieved 99% accuracy with ROC-AUC score of 1.00. For building energy prediction, model achieves R2 score of 0.67. These findings say that the proposed approach produces a stable and faithful explanations while improving the interpretability of black box model to everyone with the help of LLMs.

Volterra series feedback linearizes a class of nonlinear hyperbolic PDEs but produces a controller that, even after truncation, demands solving a tower of plant-specific kernel PDEs and evaluating nested integrals. We prove the truncated controller is jointly Lipschitz in plant and state, and learn it as a single neural operator from plant nonlinearity and state to boundary control. Once trained, no kernel is ever solved again, for any plant in the trained class. The closed loop is practically stable in class-$\mathcal{KL}$ form, with a residual ball scaling linearly with training accuracy.

Backstepping for nonlinear PDEs yields exact feedback linearizing laws in the form of infinite Volterra series – elegant in theory, but with challenges for implementation. This paper shows that even very low-order truncations of such controllers, no longer exactly linearizing, retain the stabilizing power. The key insight is that higher-order terms become negligible near the origin, so stability is recovered for any fixed truncation order by restricting the initial condition size. We establish spatial sup-norm results: finite-time practical stability and asymptotic stability characterized by a class-$\mathcal{KL}$ estimate. The region-of-attraction estimate grows with the truncation order and shrinks with the growth rate of the nonlinearity. The analysis overcomes the lack of pointwise kernel bounds and resolves well-posedness of the nonlinear closed loop, showing that surprisingly simple approximations already capture the essence of nonlinear PDE feedback linearization.