Papers

Chest X-ray (CXR) machine learning relies heavily on automated evaluation using reference standards that aim to approximate clinical judgment. However, commonly used report-derived labels for pathology classification or generic image quality metrics for reconstruction may not reliably reflect clinical judgment. We systematically investigate how evaluation-reference choices affect model performance and ranking in both pathology classification and image quality assessment (IQA). To enable controlled comparison across evaluation references, we collected paired expert image- and report-derived labels for thoracic findings from a clinical cohort at Cambridge University Hospitals (CUH) and curated a subset of the public MIMIC-CXR dataset, along with expert ratings of diagnostic image quality. We show that for supervised image classifiers (ResNet, DenseNet), several zero-shot and fine-tuned vision-language models (e.g., MedKLIP, GLoRIA, and ConVIRT), changing the label source leads to substantial differences not only in performance estimates but also in model rankings. In parallel, alignment of IQA measures with expert judgment depends heavily on the choice of measure, and commonly used IQA metrics such as SSIM and PSNR often fail to align with expert assessments of diagnostic usability. Our results demonstrate that evaluation choices are crucial: they can determine which models and methods appear best and are therefore selected for further development or deployment. The selection of evaluation references should therefore be treated as a central component of clinical validity in CXR machine learning, and justified with respect to the pathology, imaging task, and intended downstream clinical use.

Solar-powered high-altitude platform stations (HAPSs) provide a promising platform for integrated sensing and communication (ISAC) owing to their wide-area coverage and long-endurance operation. This paper proposes a solar-powered HAPS-enabled ISAC framework for sustainable day-night operation, where a figure-eight loitering architecture is adopted to provide persistent ISAC services over geographically separated regions while harvesting solar energy. A unified communication-sensing-energy model is developed by jointly characterizing solar energy harvesting, battery dynamics, propulsion power consumption, communication transmission, and synthetic aperture radar (SAR) imaging. Based on this model, coupled optimization problems are formulated for daytime operation (DTO) and nighttime operation (NTO), where the battery state bridges the two operational phases through a long-term energy budget. The proposed framework jointly optimizes communication, sensing, mobility, and energy management to maximize daytime communication performance while minimizing nighttime propulsion energy consumption. Efficient iterative algorithms are developed to solve the resulting non-convex optimization problems. Simulation results verify the effectiveness of the proposed communication-sensing-energy co-design and demonstrate that the proposed framework effectively supports sustainable day-night ISAC operation.

AI data-center growth is increasingly constrained by limited deliverable electricity, interconnection capacity, and cooling demand. This study develops a boundary-consistent screening framework for waste-to-energy (WtE)-coupled AI data-center cooling. It treats cooling as an energy service that can be supplied through grade matching rather than only through electricity-driven mechanical chilling. The framework translates plant-side exportable heat into corridor-level planning metrics by accounting for thermal attenuation, absorption conversion, and parasitic electricity for delivery and auxiliaries. In a reference case, a regulated WtE plant processing 1500 t/day of municipal solid waste at 10 MJ/kg provides about 78.1 MWth of exportable heat. At a 20 km corridor, this yields about 53.0 MW of delivered cooling and 8.0 MWe of net avoided cooling electricity after parasitic loads. The coupled system is governed by operating regimes rather than a single efficiency score. Under baseline assumptions, full thermal coverage extends to about 20.9 km, the quality-adjusted criterion remains positive to about 22.9 km, and net electricity relief remains positive to about 44.7 km. For a 1 GW IT campus at 70 percent utilization and a 5 km corridor, net grid relief ranges from about 116.9 to 264.4 MW across scenarios. The required WtE footprint ranges from about 3 to 148 representative plants, or 0.6 to 40 full-load-equivalent plants at a 25 percent displacement target. The framework identifies when WtE-coupled cooling is corridor-feasible, when hybrid operation is required, and when infrastructure scale becomes the binding constraint. It is intended for screening and comparison, not project-specific hydraulic or plant-cycle design.

Simultaneous wireless information and power transfer (SWIPT) has been advocated as a highly promising technology to provide near-perpetual operation to low-powered wireless devices in Internet-of-Things (IoT)-based wireless networks. In this paper, a SWIPT-enhanced cell-free massive MIMO network is proposed. In such a network, a large set of spatially distributed access points (APs) interconnected via a central processing unit (CPU) can collaboratively serve a large number of both energy harvesting mobile stations (MSs) (requiring wireless energy transfer) and conventional MSs (not requiring wireless energy transfer) on the same time-frequency resources. We consider spatially correlated Rician fading channels and the use of different precoding schemes that are based on different channel estimators differing on the assumed knowledge of the line-of-sight component. Mathematically manageable expressions are derived for the harvested energy during the downlink (DL) energy harvesting phase and the achievable spectral and energy efficiencies during the uplink (UL) payload transmission phase. A coupled UL/DL optimization problem is formulated aiming at finding the power control coefficients that maximize the minimum of the weighted achievable UL signal-to-interference-plus-noise ratios (SINRs) of all MSs. Extensive numerical results are presented that serve to highlight the existing trade-offs among the achievable spectral and energy efficiencies, the harvested energy, the energy dedicated to UL pilot transmission or the system configuration.

This paper develops data-driven conditions for certifying internal stability and induced-$\ell_2$ performance of discrete-time Lurye systems. The Lurye system is an interconnection of a nominal LTI system in feedback with a static, memoryless nonlinearity. The nonlinearity satisfies a known set of quadratic constraints on the inputs and outputs. Existing conditions for Lurye systems require a state-space realization of the nominal LTI dynamics. Our first data-driven result instead formulates the stability and performance conditions using finite input, output, and state trajectories of the nominal LTI block. Our second condition removes the need for measured state trajectories by reconstructing the state sequence, up to a similarity transformation, from input/output data. This state reconstruction is performed using deterministic subspace-identification techniques. Both data-driven conditions are expressed as convex semidefinite programs. These conditions, given sufficiently exciting inputs, recover the corresponding model-based Lurye condition in the noiseless setting. The proposed methods are illustrated via a simple example with a sector-bounded nonlinearity. Both proposed methods obtain the same induced-$\ell_2$ gain bound as the model-based approach while using only trajectory data from the nominal system.

A hydrogen-based direct reduced iron-electric arc furnace system integrated with methanol synthesis (H2-DRI-EAF-MeOH) provides a feasible pathway toward zero-carbon steel production. However, the volatility and intermittency of renewable energy sources (RES) may lead to capacity oversizing, while conventional annualized-cost and levelized-cost metrics are insufficient to evaluate investment return. To address these issues, this paper develops a fractional programming-based optimal sizing model for the H2-DRI-EAF-MeOH system. Hourly production rate limits are decoupled from annual production capacities and formulated as independent decision variables. Theoretical analysis demonstrates that increasing hourly production rate limits expands the multi-period operating feasible region, increases the theoretical upper bound on RES matching, and provides an investment-efficiency condition for increasing production rate limits. The annualized net return on investment (ANROI) is then adopted to represent investment return, and the resulting mixed-integer linear fractional programming model is solved using the Dinkelbach method. Case studies show that compared with the annualized net return (ANR) benchmark, the ANROI-based sizing yields higher internal rates of return (IRR), reaching 20.67% and 17.08% under the on-grid and off-grid scenarios, respectively. As the equivalent annual operating hours decrease from 8000 to 4000 h, the IRR increases from 19.68% to 20.67% under the on-grid scenario and from 12.64% to 17.08% under the off-grid scenario, while the corresponding battery storage capacities decrease by 113.56 and 796.31 MWh. The off-grid zero-carbon constraint enables CO2-to-MeOH conversion but reduces the system IRR to 14.99%, indicating that the resulting revenues are insufficient to offset the additional costs.

We investigate lightweight raptor-species classification for real-time edge deployment in wind-turbine collision mitigation. Using DINOv2-L (304M parameters) as a teacher, we distilled three lightweight students (MobileNetV4, ViT-Small, and EfficientNet-B0). To reduce confusion between closely related species, we expanded the dataset to 12,519 images, including an increase in Steller's Sea Eagle images from 463 to 2,050 via video-frame extraction. Under a group split that separates samples at the video- and source-image level to mitigate source leakage at that granularity, the three-student ensemble achieved a macro recall of 0.935 +/- 0.004 over five distillation seeds (0.955 on a conventional image-level split, retaining 97.5% of the teacher's macro recall) with roughly one-eighth as many parameters. On a subset of 1,258 images disjoint from the former training images, White-tailed Eagle recall improved by up to 38.6 percentage points, while the rate at which it was misclassified as the Steller's Sea Eagle decreased from 61% to 15% of errors. TensorRT FP16 deployment of EfficientNet-B0 on an NVIDIA Jetson Orin Nano achieved 3.19 ms/image including host-device transfer (313 images/s), with 99.95% argmax agreement with FP32. In five-seed controlled comparisons, neither distillation (versus CE-only) nor the change from a DINOv2-L to a DINOv3-L teacher yielded a clear ensemble-level improvement; the primary gains stem from the dataset expansion and teacher re-fine-tuning.

Cell-free massive multiple input multiple output (CF-mMIMO) is an emerging technology for next-generation wireless systems, where dynamically adapting the set of active access points (APs) is crucial to balance quality of service (QoS) requirements and network energy consumption under highly time-varying and spatially non-uniform traffic loads. Existing AP ON/OFF mechanisms–typically based on worst-case dimensioning or greedy heuristics–explore the combinatorial activation space inadequately, leading to suboptimal energy-efficiency outcomes. This paper introduces two evolutionary AP-selection strategies tailored to CF-mMIMO networks. The first, a constrained genetic algorithm (CGA), identifies the near-optimal subset of active APs for any fixed activation cardinality, while an outer search determines the globally optimal operating point. The second, a Pareto-driven genetic algorithm (PDGA), jointly optimizes spectral and energy efficiency by evolving a Pareto front over all feasible activation patterns. A detailed computational-complexity analysis is provided for both techniques. Simulations conducted under realistic spatially inhomogeneous traffic and considering both conjugate beamforming (CB) and minimum mean square error (MMSE) processing confirm consistent performance gains. The proposed methods consistently outperform state-of-the-art greedy benchmarks, delivering noticeable improvements in energy efficiency for both CB and MMSE schemes, while simultaneously enhancing the energy-spectral efficiency tradeoff, which is typically difficult to improve without incurring penalties elsewhere. These results highlight the strong potential of evolutionary optimization as a powerful and reliable approach for energy-efficient CF-mMIMO deployments.

The spatial organization of cells and tissues provides important diagnostic cues in histopathology images. Although graph-based approaches can model these relationships, many rely on fixed or heuristic graph structures that may not accurately represent tissue connectivity. In this work, we propose $G_2^*$-Net, an optimized two-level graph learning framework for classifying large-scale histopathology images, such as whole-slide images (WSIs) or large regions of interest (ROIs). Here, $G_2$ denotes the two-level hierarchical graph representation, and the superscript $*$ indicates the optimized image-level graph structure learned from the proposed framework. The method first divides each WSI or large ROI into image patches, constructs cell-level graphs within each patch to capture local tissue architecture, and then represents each patch as a node in a learnable image-level graph. $G_2^*$-Net formulates image-level graph structure learning as a second-order bilevel optimization problem, separating graph connectivity learning from classifier optimization while coupling them through validation-driven feedback. To make this formulation computationally practical, we adopt a DARTS-inspired one-step unrolled approximation for efficient hypergradient estimation. Experimental validation on three distinct histopathology datasets demonstrates the effectiveness of our proposed method.

Prompt-based video streaming transmits compact semantic prompts instead of pixel-level content for generative reconstruction, enabling ultra-low-bitrate communication. However, the state-of-the-art Promptus framework is vulnerable to network fluctuation, where partially received prompts lead to catastrophic quality collapse. We propose ScalablePromptus, which enhances Promptus with semantic and color-aware prompt inversion, spherical linear interpolation for intermediate frames, and–most critically–a dropout training strategy that produces rank-ordered prompt representations. This allows the receiver to reconstruct meaningful video from arbitrarily truncated prompts without any adaptation. Under stable networks, ScalablePromptus achieves modest quality gains. Under lossy conditions, it reduces the performance degradation caused by truncation by 82%-95% compared to the baseline, making prompt-based streaming robust enough for real-world deployment.

Reliable joint-angle measurement outside laboratory environments is important for posture assessment and technique analysis in sports and rehabilitation. Yet, wearable IMU systems, despite being the most practical solution, remain constrained by drift, multisensor timing consistency, validation, and cost. This paper presents a synchronized, cost-efficient, modular IMU wearable platform and an end-to-end pipeline for joint-angle estimation tailored to high-dynamic sports motion analysis. The system combines high-rate sensing with robust local logging, a Real Time Clock-disciplined microsecond timestamping scheme for inter-node synchronization, an indirect Kalman filter-based orientation estimator followed by relative-rotation joint-angle extraction, high-pass drift mitigation, and range normalization. Reference-based validation used a standardized seated knee flexion-extension protocol, comparing IMU-derived knee trajectories against a markerless vision reference computed from YOLOv11. The proposed method reproduced the expected 14-cycle motion and achieved low normalized error. Instrumentation performance was further evaluated using a long-duration (2h 12min) rigid-body elbow hold, yielding near-zero drift ($r_{\mathrm{drift}}=1.5\times10^{-6}$ deg/min) and a practical noise-limited resolution of $0.6442^\circ$. The system was also demonstrated on a high-dynamic clean & jerk task with two participants (professional and amateur) performing five consecutive lifts. Measured elbow and knee trajectories preserved stage-dependent signatures and rapid transients for technique interpretation, while enabling expertise-level discrimination through differences in transient timing and trajectory regularity. Overall, the results support the proposed system as a practical, temporally consistent, and cost-effective wearable approach for multi-joint technique analysis in high-dynamic settings.

Open Sound Control (OSC) is the dominant wire protocol for real-time parametric control in professional audio, live performance, and virtual production. Large language models can emit plausible OSC, but they hallucinate addresses, mishandle type tags, and fail under paraphrase- unacceptable in show-critical contexts. We present LLM4OSC, a local-first architecture in which models propose structured intent JSON over a human-reviewed device profile, and deterministic code validates, clamps, and encodes before any UDP send. We introduce a frozen evaluation harness with CI gates on wrong-send rate: mismatches that would still pass validation and transmit. On a Max/MSP hero profile (12 patterns; 8 literal + 8 paraphrase + 4 refusal cases), after profile tag enrichment, symbolic slot fill, NL refine, and a retrieval confidence gate, backends B0–B3 all pass frozen gates (100% semantic accuracy, 0% wrong-send). B0 (rules) remains the production default at ~0.05ms; LLM backends remain ~3-4s. Historical few-shot B2 accuracy of 62.5% rises to 100% on this suite only after symbolic post-processing- not because the 0.5B model alone becomes show-safe. We argue for propose-validate-send and wrong-send rate as first-class metrics for language-to-control systems.

The problem of finding the optimal compression rate for a given random variable has been traditionally studied under two main constraints: distortion and perception. The distortion constraint enforces the fidelity of our reconstruction with respect to the observed realization of the random variable, while the perception constraint ensures that the reconstruction is close to a sample from the distribution of the random variable of interest. In this work, we explore the possibility of reconstruction, such that the reconstructed sample is still within a desired fidelity level with our original realization of the random variable, but at the same time, it resembles a sample from a different target distribution. We term this criterion as the deception constraint and find the fundamental tradeoffs of rate-distortion and deception.

Unmanned aerial vehicles (UAVs), particularly quadcopters, present unique challenges for autonomous control due to their underactuated dynamics: only four available control inputs must govern six degrees of freedom. This paper investigates a physics-aware, end-to-end deep reinforcement learning (DRL) approach that acts directly on low-level body inputs, total thrust and body torques $(T, \tau_x, \tau_y, \tau_z)$, and closes the loop through a high-fidelity Simulink environment. Our simulator integrates a 12-state rigid-body model (MATLAB Level-2 S-Function) with (i) an Action2RPM allocation based on the Moore-Penrose pseudo-inverse of a coefficient matrix derived from thrust and drag terms, and (ii) first-order actuator dynamics for each motor (time constant $T_m = 0.076$ s), including rotor gyroscopic coupling. A shaped reward balances goal-reaching and stability using an exponential position well, attitude penalties, and quadratic velocity costs. Four DRL algorithms, DDPG, TD3, PPO, and SAC, are evaluated in two stages: (S1) thrust-only hover and (S2) hover with pitch torque and a translated goal. Results show that SAC and TD3 achieve superior stability and exploration efficiency, while PPO is less sample-efficient. The study highlights the significance of modeling actuator lags and aerodynamic moments for stable low-level control and provides a reproducible benchmark for quadcopter DRL.

Dynamic 3D Gaussian Splatting (GS) enables high quality real-time rendering for immersive media, but its large representation size and frame-wise redundancy create significant challenges for adaptive streaming. This paper presents SplatStream, a fine granular scalable Gaussian splatting framework for dynamic 3D scene delivery. The proposed method decompose the GS scenes into quality and resolution layers, and introduces inter-layer predictive coding to achieve scalability. For temporal direction, B-frames are introduced to have temporal quality scalability. A lightweight cross-layer transformer based predictor is utilized for both cross layer and temporal predictions. In addition, a volume-opacity based importance measure is used for fine-grained Gaussian packetization, allowing visually important primitives to be transmitted earlier for progressive refinement. Finally, the scalable GS bitstream is mapped to an MPEG-DASH compatible sub-representation structure, enabling fine granular adaptive, low-latency delivery of dynamic Gaussian splatting content under bandwidth-varying conditions.

Secure energy efficiency (SEE) has emerged as a key performance metric for next-generation wireless networks, where energy sustainability and information security must be jointly guaranteed. This paper investigates secure uplink transmission in a full-duplex (FD) base station (BS) system equipped with movable antennas (MAs) and assisted by a movable-element reconfigurable intelligent surface (ME-RIS) in the presence of multiple cooperative passive eavesdroppers. The objective is to maximize SEE by jointly optimizing the users' transmit powers, BS receive postcoders, artificial noise (AN) transmit power and beamforming, RIS phase shifts, and the two-dimensional positions of both the BS antennas and RIS elements. The resulting optimization problem is highly nonconvex due to the fractional SEE objective, coupled secrecy-rate expressions, residual self-interference (SI), unit-modulus RIS phase-shift constraints, movable-position constraints, inter-element spacing requirements, and the nonlinear dependence of the channels on the movable antenna and RIS-element positions. To address these challenges, we propose a hybrid gradient-based meta-learning (H-GML) framework. In the proposed method, the BS receive postcoders and AN direction are updated using closed-form solutions derived from generalized Rayleigh quotient formulations, while the remaining coupled variables are updated by neural meta-optimizers that learn gradient-based update directions directly from the SEE optimization objective without requiring offline labeled training data. Simulation results show that the proposed H-GML design achieves better performance than the AO benchmark and significantly outperforms fixed-geometry, random RIS, no-AN, and no-Eve-knowledge baselines.

Despite the rising popularity of immersive audio, binaural music remains underexplored in music information retrieval (MIR), particularly regarding the task of music source separation (MSS). While existing stereo MSS models can process binaural audio, they often degrade the spatial quality of the separated stems and undermine listener immersion. Through a perceptual study comparing binaural and stereo MSS outputs, we evaluate how well objective spatial distortion metrics correlate with human perception. Our findings reveal varied agreement between these metrics and human judgment, highlighting a lack of reliability when used to evaluate binaural music tasks. Specifically, we find that Interaural Time Difference (ITD) estimation is highly sensitive to noise and separation artifacts. In evaluating two alternative ITD estimation methods, we uncover a critical trade-off between robustness and accuracy, particularly for narrow-band instruments like bass. These results underscore the need for accurate, interpretable spatial metrics designed for binaural music to develop models that preserve source localization and listener immersion.

Automatic analysis of multimodal speech has shown strong potential for computationally detecting and monitoring a wide range of neurological, psychiatric, and respiratory conditions. However, progress in this field is limited by existing publicly accessible datasets, which are often small in scale, focused on a single condition or disease, and primarily speech focused. Moreover, if key confounding variables such as education, medication use, comorbidities, or mood state are insufficiently documented, the reliability and interpretability of computational analyses are further compromised. To address these limitations, we introduce CARE v1.0, a curated multimodal English dataset of approximately 144 hours of short video interviews collected from 612 individuals across 12 medical conditions plus a control cohort. For each video, a comprehensive set of clinically relevant multimodal descriptors is provided, alongside structured metadata covering factors such as medication, life impacts, and expressed emotions. The corpus's breadth and heterogeneity support a wide range of applications, including automatic disease and symptom detection, multimodal modelling of speech and non-verbal behaviour under emotionally charged contexts, and studies of disease trajectories and coping processes.

This study identifies new depression biomarkers based on the dynamical properties of tract variables, which represent geometric features describing the configuration of the speech articulators. A key advantage of this approach lies in its ability to quantify aspects of the articulatory process that have not been previously explored in the context of depression, namely predictability, complexity, and randomness. These properties are respectively characterised using the Largest Lyapunov Exponent, the Correlation Dimension, and the Sample Entropy. Thorough experiments were conducted on the Androids Corpus, a publicly available dataset comprising 64 speakers diagnosed with depression by clinicians and 54 control speakers with no reported history of mental health conditions. The results indicate that the proposed biomarkers effectively discriminate between the depressed and control speakers, as evidenced by the high Cliffs delta values across both read and spontaneous speech.

This paper explores the effectiveness of domain adaptation techniques when using convolutional neural network (CNN)-based and transformer-based feature representations for acoustic scene classification. Two well-known domain adaptation techniques, namely domain adversarial neural network (also called DANN) and conditional domain adversarial network (also called CDAN) are evaluated under various domain shifts. Our study indicates that DANN provides effective domain adaptation fairly consistently for both feature extractors. On the other hand, CDAN provides effective domain adaptation only for CNN-based feature extractors. The study gives insights into how domain adaptation methods may need to be tailored to the underlying feature representation. Experimental evaluation with multiple devices on the DCASE 2020 dataset supports the observations.

Voice activity detection (VAD) triggers downstream speech processing in always-on systems under strict memory, latency, and compute constraints. Recent compact models report strong accuracy but rely on components that are not widely supported: learnable filterbanks, recurrent layers, or non-causal post-processing. We propose kiloVAD, designed for embedded inference using standard Mel features, CNN-only layers, and tunable context/spectral parameters. We introduce per-layer structured pruning with self-distillation and angle-based quantization-aware training (QAT) that outperforms standard QAT by 1-4%. Evaluated per-frame under causal conditions, kiloVAD achieves 0.850 AUC on AVA-Speech with 2.1 k parameters and 200 ms context, establishing a new state of the art for causal, deployment-ready VAD.

Many time-series forecasts depend not only on prior observations but also on actions specified during the forecast period. In intensive care units (ICUs), future vital signs and laboratory values are influenced by treatments such as vasopressors. However, models that predict the full future sequence all at once make little use of these treatments, whereas autoregressive models can accumulate errors. We introduce DRIFT, a hybrid framework in which a direct model produces the primary forecast and a recursive, action-conditioned model contributes constrained corrections. We evaluate DRIFT on 6,046 admissions from MIMIC-IV and 8,345 admissions from eICU-CRD. Averaged across the 8-, 24-, and 48-hour forecast endpoints, DRIFT reduces mean absolute error for mean arterial pressure (MAP) by 0.673% relative to an action-conditioned Temporal Fusion Transformer (TFT-action) on MIMIC-IV and achieves the lowest corresponding error among the compared models on eICU-CRD. Although the overall accuracy improvement is modest, a MIMIC-IV audit restricted to windows in which the supplied treatment sequence was altered showed that DRIFT achieved lower observed-target MAP error than TFT-action at 8 and 24 hours. Treatment-sequence alteration increased DRIFT's MAP error by 0.21-0.26 mmHg more than it increased TFT-action's error, with prediction changes occurring primarily after the supplied paths diverged. In a separate robustness experiment, the MAP advantage persisted under three shared checkpoint-selection rules emphasizing overall endpoint error, MAP error, or both equally.

This paper studies leakage-aware beam selection for multi-target multiple-input multiple-output (MIMO)-orthogonal frequency-division multiplexing (OFDM) sensing. We focus on ensuring that each hypothesized target remains detectable at its own delay-Doppler (DD) bin despite leakage from other targets. For this, we derive a visibility metric that separates the desired focused power from pairwise leakage caused by the finite-grid OFDM ambiguity kernel, receive angular coupling, and transmit codebook gains. Then, we formulate a max-min beam-selection and power-allocation problem in which the sensing signal over the fixed OFDM time-frequency grid is transmitted by a limited number of selected beams. The resulting problem is solved via a bisection-based mixed-integer successive convex approximation framework. A time-sharing formulation is also presented as a globally solvable benchmark. Numerical results show that the proposed pairwise leakage-aware design achieves higher worst-target visibility than the time-sharing, global leakage-suppression, illumination-based, and random beam-selection baselines, especially when targets are close in angle or DD.

The integration horizon during the training plays a critical role in Physics-Enhanced Neural Ordinary Differential Equations. We draw conclusions about horizon extension in the training of Neural Ordinary Differential Equations based on classical nonlinear system identification of input-output models. In light of this insight, we propose a framework that exploits longer horizons to reduce bias in physical parameter estimates, extracts residual information from data, and acts as a regularizer improving generalization. In the learning of a model for permanent magnet synchronous machine, the method is used to jointly estimate the flux map and the resistance.

Integrated electric-hydrogen infrastructures are becoming increasingly important with the growing deployment of electric vehicles (EVs) and hydrogen vehicles (HVs) in transport systems. However, the strong coupling between vehicle scheduling and multi-energy dispatch introduces significant operational challenges. This paper models an integrated electric-hydrogen-transport system (EHTS) and proposes a hierarchical optimisation framework that couples vehicle scheduling and downstream energy dispatch through a sequential, demand-driven two-layer structure. In the vehicle scheduling layer, a solver-free greedy heuristic (SFGH) algorithm is developed to avoid repeated optimisation solving, enabling real-time EV charging and HV refuelling under non-preemptive service and within-interval sequential assignment. The resulting charging and refuelling demands are subsequently passed to the energy dispatch layer, where a deep reinforcement learning (DRL)-based approach is designed to optimise battery operation, hydrogen-tank operation, and PV generation allocation to minimise the overall operational cost of the EHTS while satisfying the scheduled transport demand. Representative case studies, together with comparative, ablation, and generalisation analyses, demonstrate the effectiveness and robustness of the proposed framework. Furthermore, the learned dispatch policy maintains strong performance across diverse transport-demand scenarios and PV penetration levels without retraining, demonstrating robust generalisation capability for practical deployment.

Ensuring measurement data quality is essential for reliable condition monitoring of industrial wind turbine drivetrains, where vibration measurements can be affected by sensor malfunctions, turbine shutdown conditions, and other non-diagnostic states. Such invalid measurements may compromise the reliability of subsequent monitoring and data-driven analysis procedures. This study proposes a Multi-Dimensional Entropy (MDE) metric as a front-end data quality assessment and control mechanism for vibration measurement validity evaluation. By characterizing signal distributions from multiple perspectives, including time-domain amplitude, spectral amplitude, and frequency-band energy, MDE captures statistical differences between valid and erroneous vibration measurements. By integrating MDE and RMS as feature representations, lightweight machine learning models are employed as evaluation tools to assess the effectiveness of the proposed representation. Experiments on a large-scale, heterogeneous real-world dataset comprising 57,643 vibration samples collected from 12 wind farms and 14 turbine units, covering multiple drivetrain components, diverse sensor brands, and varying sampling configurations over long-term operation, demonstrate that the proposed method achieves over 99 percent accuracy in identifying erroneous vibration measurements. The proposed approach can be deployed as a front-end data quality gate before downstream signal processing, feature extraction, and condition monitoring procedures, ensuring that subsequent analyses are performed using reliable vibration measurements. The results demonstrate the robustness of MDE under heterogeneous sensor configurations and highlight its potential for industrial-scale vibration measurement quality assessment.

In electric drive modeling, identifying the magnetic flux maps is essential for predicting accurately the torque, parameterizing a controller for tracking the torque or creating a simulation model. However, the voltage output by the controller (commanded voltage) is usually disturbed by non-linearity of the inverter, which needs to be taken into account. This paper presents a novel approach to enhance the offline flux identification from commanded voltage inputs, circumventing the need for prior identification of inverter parameters. In the dq reference frame, the flux maps are represented as static relationships between dq fluxes and dq currents. We utilize a tensor product spline model to accurately capture saturation and cross-saturation effects. The effects of the voltage disturbance on the estimated flux maps are not negligible. It is demonstrated that a joint identification of the flux maps and a simple model of the inverter can highly improve the flux model. The method is validated on FEM simulation and test-bench data.

Synchronization often emerges spontaneously among interacting people, yielding practical benefits for tasks such as sports, physical rehabilitation, and collaborative manufacturing, and fostering a sense of unity and trust. Although visual interaction is typically considered the primary channel for achieving synchronization, it is constrained by sensorimotor delays, occlusions, and limited attentional resources. Here, we tested whether haptic communication can induce or enhance synchronization in a group motor task. Six quartets performed oscillatory wrist flexion/extension while being connected via virtual elastic bands; we compared haptic only, visual only, combined haptic&visual, and no feedback conditions. Even weak haptic coupling induced group synchronization, and combining haptic with visual feedback yielded higher and more stable synchronization than either modality alone. Haptic feedback also increased the frequency at which groups coordinated, and movement smoothness rose with frequency. These findings lay the groundwork for designing haptic interaction protocols for collaborative group environments.

Semantic communication systems such as deep semantic communication (DeepSC) offer high efficiency but are vulnerable to adversarial attacks on their underlying neural networks. We address a physical-layer man-in-the-middle (MitM) threat in which an adversary injects perturbations into the transmitted signal to distort its meaning. We propose SignDeepSC, an architectural defense that achieves adversarial robustness without requiring explicit adversarial example generation during training. The approach is built on a perceiver-inspired semantic signature, a compact vector summary of the source features transmitted over a separate low-rate auxiliary channel. This signature is used by a self-repairing decoder that leverages cross-attention to correct distortions and can additionally drive a scrambler that shuffles the feature layout. We evaluate SignDeepSC over Rayleigh fading and additive white Gaussian noise channels under both single-step fast gradient sign method (FGSM) and iterative projected gradient descent (PGD) attacks. Under PGD ($\epsilon = 0.7$), at 12~dB signal-to-noise ratio with Rayleigh fading, SignDeepSC achieves a bilingual evaluation understudy (BLEU-4) score of 0.237 and bidirectional encoder representations from transformers (BERT) sentence similarity of 0.646, outperforming all baselines without degrading clean-channel performance, when the signature channel is well protected.

In this paper, we study measurement-driven signal-to-interference-plus-noise ratio (SINR) maximization for a multi-reconfigurable intelligent surface (RIS)-aided single-input single-output (SISO) system with unknown strong interference sources. Specifically, the objective is to optimize the reflection coefficients such that the SINR is maximized at the receiver. As the interference channels are unknown, such an optimization problem is a black-box optimization problem with an objective function whose closed-form analytical expression is unknown. To address the high-dimensional black-box optimization problem with discrete variable constraints, we introduce a group-based phase parameterization that significantly reduces the search dimension. Building on this model, we develop a group-based zeroth-order adaptive moment (ZO-AdaMM) algorithm. Simulation results show that the proposed grouping strategy markedly accelerates the convergence speed and achieves a superior interference suppression performance under limited measurement budgets, especially in the small-budget regime.