Papers

Affine frequency division multiplexing (AFDM) is a recently proposed multicarrier waveform whose bit error rate (BER) performance in doubly selective channels is comparable to that of orthogonal time-frequency space (OTFS) and superior to that of orthogonal frequency division multiplexing (OFDM). In this paper, the impacts of joint transmitter (Tx) and receiver (Rx) in-phase and quadrature imbalance (IQI) on AFDM signals are investigated, where we show that AFDM suffers more severe IQI than OFDM and OTFS due to the inherent feature of complicated chirp-assisted modulation. We further derive analytical expressions for the pairwise and average bit error probability as a function of the IQI parameters. These indicate that such distortions significantly limit the achievable operating signal-to-noise ratio at the receiver side and data rates. To this end, we propose a cascade compensation scheme to mitigate these effects. Specifically, we first compensate for Rx IQI to convert the improper Gaussian noise into additive white Gaussian noise, and then apply a judicious design to eliminate the Tx IQI. Both analytical and simulation results reveal that joint Tx and Rx IQI introduce an error floor in the BER performance of AFDM systems, whereas the proposed approach effectively compensates such impairments.

This paper investigates coordinated downlink transmission in a multi-base station (multi-BS) multi-reconfigurable intelligent surface (multi-RIS)-assisted pinching-antenna (PA) system, where each user equipment (UE) is associated with a single BS and each BS is equipped with movable PAs deployed on parallel waveguides. We formulate sum rate (SR) and energy efficiency (EE) maximization problems by jointly optimizing PA placement, RIS phase shifts, transmit beamforming, and BS-UE association under constraints of inter-PA spacing, power budget, and unit-modulus phase shift. To address the resulting highly coupled mixed-variable problem, we propose a three-stage graph neural network (GNN) that integrates heterogeneous and homogeneous graph representations and is trained end-to-end in an unsupervised manner. Extensive numerical results demonstrate that the proposed three-stage GNN consistently outperforms representative system and learning baselines, generalizes well to unseen numbers of UEs, RISs, and BSs, and maintains millisecond-level inference time. Besides, the results validate the effectiveness of the proposed design from both system and architectural perspectives. Moreover, PAs are shown to enhance SR and EE, and the performance gain is enlarged with increasing number of PAs.

In MRI, variations in scan parameters, sequence, or hardware can lead to discrepancies in image appearance, even for the same subject. These inconsistencies, known as domain shifts, can hinder image analysis and degrade the performance of deep learning models trained on data from specific target domains. MRI image harmonization aims to address these issues by aligning source domain images to the target domain images while preserving biological information such as anatomical structures. However, most existing harmonization approaches require access to both source and target domain data in training or test time. This dependence induces data sharing between institutions, raising concerns about patient privacy and substantially limiting the harmonization approaches that can be practically deployed in clinical settings. To overcome these limitations, we introduce TgtFreeHarmony, the harmonization framework tailored for target-free scenarios, eliminating the need for target domain data and any data sharing, enabling privacy-preserving harmonization directly within the source institution. Our approach estimates the target domain style by searching the manifold of MRI domain style constructed via a disentanglement-based generator using Bayesian optimization guided by the performance of a downstream task model, which is trained on target domain data. We evaluated our method on the brain tissue segmentation task across multiple institutes and demonstrated that it effectively harmonizes source images into target images, leading to improved downstream task performance. By enabling harmonization without any access to target-domain data, TgtFreeHarmony establishes a new direction of harmonization preserving data privacy that can be realistically deployed within clinical environments.

The development of video game streaming has grown rapidly, with major platforms such as YouTube and Twitch using different codecs. To support quality assessment models that work consistently across any codec, it is necessary to have access to large, diverse subjective gaming quality datasets. Currently, there are only a few available, each having limitations. To address this gap, we present the largest gaming video quality dataset to date, incorporating both user-generated content (UGC) and professional-generated content (PGC) with extensive visual diversity. Our dataset covers the most widely used codecs - H.264, H.265, and AV1 - and consists of 4,048 video samples, each annotated by an average of 37 mean opinion score (MOS) ratings. In addition to overall quality scores, we collect coarse-grained quality attributes, enabling a better understanding of perceptual factors. We study the performance of leading video quality assessment methods on this dataset, including a vision language model that outperforms all the benchmarks. To the best of our knowledge, this is the first dataset that comprehensively addresses gaming video quality assessment across multiple codecs and content types with quality attributes. Our dataset is publicly available at https://rajeshsureddi.github.io/GameScope/.

This work explores the integration of pixel antennas and rate-splitting multiple access (RSMA) to enhance spectral efficiency in multi-user multiple-input single-output (MU-MISO) systems. Pixel antennas offer controllable antenna characteristics via antenna coding from the analog domain, whereas RSMA provides efficient interference management from the digital domain. We propose a novel pixel antenna empowered RSMA transmission framework where each user employs a pixel antenna. Under imperfect channel state information at the transmitter, we formulate a joint precoding and antenna coding design problem to maximize the ergodic sum-rate. An alternating optimization algorithm based on the weighted minimum mean square error (WMMSE) approach and the successive exhaustive Boolean optimization (SEBO) is first developed to solve the problem. We then propose an efficient online antenna coder selection algorithm relying on an offline-designed codebook to reduce computational complexity. Numerical results show that the proposed pixel antenna empowered RSMA significantly improves spectral efficiency compared to both RSMA with fixed antennas and space-division multiple access (SDMA) employing the same pixel antenna configuration. Moreover, compared to SDMA, RSMA maintains the same performance with a simpler pixel antenna configuration or a smaller codebook size.

The rapid deployment of Low Earth Orbit (LEO) satellite constellations has enabled the emergence of in-orbit edge computing and data centers, where satellites with onboard processing and high-speed inter-satellite links can collaboratively process data in space. This paper investigates whether such architectures, integrated with a deep learning-based computer vision pipeline, can achieve sub-minute information freshness suitable for real-time wildfire detection. To evaluate this hypothesis, we develop a simulation framework that models orbital dynamics, distributed processing, and network routing, using Age of Information (AoI) as the primary performance metric. A total of 720 simulation trials are conducted across 12 real-world constellation configurations, including Starlink, Kuiper, Telesat, and OneWeb. The results demonstrate that constellation design has a significant impact on AoI performance, with average AoI values ranging from 66.5 s to over 6300 s. The best-performing configurations achieve an average AoI below 70 s and a peak AoI under 100 s, indicating that orbital edge computing systems can provide the level of timeliness required for near-instantaneous environmental monitoring.

The increase in space activities has increased the risks of space debris generation, affecting space safety and sustainability. Traditional space situational awareness (SSA) relies on single star trackers and ground-based tracking facilities. There is limited discussion on the use of in-orbit optical sensors on low Earth orbit (LEO) satellite constellations for SSA, despite their importance for efficient space traffic management systems. In this paper, we aim to address this important challenge. We first present a new analytical system model for utilizing LEO satellite constellations for in-orbit SSA. We then develop a method to evaluate and analyze such a system. We also propose a Poisson expected revisit period algorithm and introduce the period of equivalent orbital distributions to reveal the relationship between revisit period and geometric variables, with insightful results based on real-world and custom satellite constellations. Experiments on real-world constellation show that the representative Poisson expected revisit period ranges from 0.4 days to 5.7 days for targets whose apogee altitude ranges from 552 km to 650 km, while requiring a per-case computation time of 0.4 s to 4.8 s. Our work can inform the future design of in-orbit and onboard computing systems for SSA, such as space object detection and space traffic monitoring systems.

In this paper, we introduce a family of novel sparse array designs called the augmented ULAs (AULAs) for the localization of non-circular signals (NCS). Accurate direction of arrival (DOA) estimation and the ability to resolve multiple targets are critical in modern wireless communication systems. Most existing sparse arrays are optimized solely for the difference co-array, making them less efficient at utilizing the sum co-array resulting from the non-zero pseudo-covariance of NCS. Meanwhile, state-of-the-art designs for joint optimization of the sum and difference co-arrays remain constrained by a three-way performance trade-off. The proposed AULAs configure single sparse and two dense ULAs alongside two separate elements to achieve a perfect splicing of holes and lags in the difference and sum co-array. This results in a larger virtual aperture and increased DOFs for NCS. Building on this structure, other variants of AULAs are developed, each exhibiting distinct characteristics. The shifted AULAs (SAULAs) judiciously displace the AULAs structure to minimize co-array redundancy and further enhance the DOFs. A transformed SAULAs (TSAULAs) design is proposed, which mitigates mutual coupling effects by converting the dense ULAs of SAULAs into sparse ULAs. By reconfiguring the elements of TSAULAs, the complementary TSAULAs (Co-TSAULAs) design inherits the desirable properties of SAULAs and TSAULAs.All these structures belong to a unified design framework, within which one configuration can be adapted into another during the design phase to meet different performance requirements. Meanwhile, they provide in-built physical locations for convenient extension to a larger aperture. Closed-form expressions for precise element placements, DOFs, and weight functions are derived. Simulation results validate the effectiveness of the proposed approach.

Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortions are often asymmetric, where one modality may be severely degraded while the other remains clean. Still, most contemporary AVQA metrics treat audio and video as equally reliable, causing confidence-unaware fusion to emphasize unreliable signals. This paper proposes MCM-AVQA, a multimodal confidence-aware AVQA framework that explicitly estimates modality-specific confidence and injects it into a dedicated audio-visual mixer for cross-modal attention. The Audio-Visual Mixer utilizes frame-level, confidence-guided channel attention to gate fusion, modulating feature interaction between modalities so that high-confidence streams dominate while unreliable inputs are suppressed, preserving temporal degradation patterns. A multi-head visual confidence estimator turns frame-level artifact probabilities into temporally smoothed, clip-level visual confidence scores, while an audio confidence module derives confidence from speech-quality cues without requiring a clean reference. Experiments on multiple AVQA benchmarks show that MCM-AVQA, and specifically its confidence-guided Audio-Visual Mixer, improve correlation with human mean opinion scores and yield more interpretable behavior under real-world asymmetric audio-visual distortions.

The rapid expansion of uplink-intensive applications necessitates video coding solutions that balance high Rate-Distortion (RD) efficiency with ultra-low latency. This paper presents a longitudinal performance analysis of NVIDIA hardware encoding (NVENC), spanning from Pascal to the emerging Blackwell generation. We specifically evaluate the operational viability of the new "Ultra High Quality" (UHQ) tuning mode against standard low-latency configurations. Our results demonstrate that while the Blackwell architecture breaks historical efficiency plateaus, achieving a 5.94% BD-Rate gain in standard modes and up to 22.79% in UHQ modes, these gains incur severe system-level penalties. We reveal that UHQ operates as a hybrid pipeline, offloading complexity to CUDA cores and enforcing aggressive temporal structures (up to 7 B-frames) that increase end-to-end latency by over 400% and GPU board power consumption by up to 40%. Consequently, while UHQ successfully bridges the quality gap with software encoders, its prohibitive serialization delay renders it unsuitable for interactive real-time communications, positioning it instead as a specialized solution for Video-on-Demand (VoD) transcoding.

A framework is established that assesses the impact of variations in artificial intelligence (AI) data center (DC) loads on the fatigue damage of steam/gas turbines of the synchronous generators (SGs) from torsional oscillations. Next, a simple three-step process that is supported by frequency-domain analysis is laid out to quantify the limits on fluctuations in AI DC loads. In the first step, the maximum allowable variation in electrical power output at each SG terminal is independently determined from the first principles. This step needs only a lumped multi-mass model of the mechanical side of the SG. In the second step, we propose a new approach that relies on load flow to determine the so-called algebraic `interaction factor' that maps the change in AI DC load at a given bus to the corresponding change in each of the SG power outputs. In the third step, we propose a screening method to rank the candidate buses to site AI DCs and solve an optimization problem to determine the optimal allowable fluctuations in the AI DCs. We demonstrate the applicability of the proposed approach through frequency-domain and time-domain analyses in the modified IEEE 4-machine and IEEE-68 bus systems using a dynamic phasor framework. Finally, we demonstrate the scalability of the proposed approach on the synthetic 2000-bus Texas system.

Recent advances in speech synthesis have shifted from phoneme representations to direct grapheme modeling. While phonemes address the one-to-many mapping between text and acoustics, they rely on grapheme-to-phoneme (G2P) systems that fail to capture speaker-specific acoustic variation. Prior work demonstrates that grapheme-based models outperform phoneme-based systems at scale, but not in low-resource settings. In this paper, we propose SPARCLE, a speaker-aware grapheme representation model that enriches characters with their precise acoustic realizations. SPARCLE is trained with a contrastive objective to align graphemes with corresponding Wav2Vec2 acoustic representations while conditioned on speaker identity. The resulting model serves as a replacement to G2P systems for downstream text-to-speech (TTS) tasks. We demonstrate that SPARCLE improves generation quality, reducing word error rates by half in extreme low-resource settings compared to standard grapheme-based models.

In this paper we investigate the chaotic behavior of the class of oscillators denoted as Clapp oscillators. Clapp oscillator is a simple oscillator containing one transistor and a few reactive elements - inductors and capacitors. This oscilllator is chosen for its design simplicity and a good performance. Oscillator with chaotic behavior can be used to construct chaotic radar. For that matter, in this paper is investigated approach for construction of the chaotic Clapp oscillator, which can be further verified experimentally using microstrip technology.

Fairness studies of medical imaging AI often explain subgroup performance gaps through under-representation in the training data. We show that intersectional analysis can disentangle fairness and performance gaps arising from clinical and acquisition confounders that co-vary with the target. As a case, we study scan-time fetal weight estimation from obstetric ultrasound, analyzing two models: a state-of-the-art deep learning (DL) model and the clinical gold-standard Hadlock formula. Using unsupervised slice discovery, we find that high-error subgroups share extreme in the image-acquisition pixel spacing (PS) and in the scan-to-delivery (STD) interval. Of these, PS is an acquisition parameter that can be optimized, while STD is a potential confounder for both PS and our bias diagnostics. Subgroup inspection alone cannot separate them. We disentangle the factors using a model-agnostic analysis with identical metadata partitions and partial regression. Holding STD fixed, the apparent PS effect collapses to a small residual (standardized coefficient $\beta=-0.17$), whereas holding PS fixed, STD dominates error ($\beta=+0.56$). Both models degrade with increasing STD, including the biometric formula, indicating much of the error is intrinsic to the prediction target rather than imaging. The DL model is $\sim$1.5$\times$ more sensitive to STD than Hadlock, though it remains more accurate in every subgroup. We conclude that fairness analyses need to carefully analyze potential confounds, or risk attributing an effect such as temporal or acquisition-related dependency to demographics.

Silent-watch operation makes electrified ground platforms depend on supervisory energy management because mission loads must be sustained from stored energy while the engine is off. This paper develops a mission-centric cyber-resilience benchmark for this operating mode. The benchmark connects battery state-of-charge (SOC) spoofing to mission outcomes rather than evaluating the attack only through detector response or control error. It combines a reduced-order DC-bus model, residual-based detection, fallback shedding, and five mission-facing metrics for endurance, critical-load service, priority-weighted loss-of-load cost, unsafe-voltage exposure, and detection delay. The study shows that SOC spoofing creates a structured stealth-versus-impact envelope. Small biases have limited mission effect, intermediate biases produce an endurance deficit well approximated by a first-order expression in bias magnitude, shed power, and average battery draw, and large biases disable the SOC-driven guard. The results also show that defense value depends on fallback depth, not detection alone. An undersized fallback action can leave the Defended case failing to complete the mission despite early detection. MATLAB-to-Simulink parity across five regression scenarios provides a software-verified basis for hardware-in-the-loop testing.

Extremely large aperture arrays (ELAAs) benefit the dual functions of integrated sensing and communication (ISAC) systems by enabling high-throughput data streams and high angular resolution with near-field spatial diversity. However, near-field spherical wavefront effects and spatial non-stationarity (SNS) bring challenges to both communication and sensing. This paper studies near-field spatially non-stationary channel estimation and environment mapping by jointly accounting for multi-bounce, blockage-induced partial visibility, and hybrid reflection-scattering propagation. We propose a unified parametric sensing channel model that represents the SNS phenomenon (due to partial array blockage, diffraction, and specular reflection) through spatially varying visibility and amplitude of each multipath across the array. To regularize the spatially varying delays caused by propagation mechanisms, we incorporate geometric constraints (GCs) based on environmental interaction points, embedding them into the model as absolute propagation delays. We then develop a GC-space-alternating generalized expectation-maximization (GC-SAGE) algorithm to estimate near-field channel parameters and locate environment scatterers/reflectors. Moreover, the GC-SAGE calculates per antenna path amplitudes based on the delays determined by the coordinates of scatterers/reflectors and transceivers, thereby effectively detecting channel SNS. Both ray-based simulation and field measurement are used to validate the proposed approach.

In this paper, a distributed multi-agent formation control driven by the gradient of the Lennard-Jones potential is analyzed. For collision-free initial data, we prove global well-posedness together with a uniform lower bound on all inter-agent distances, thereby excluding hard collisions. Taking the total energy as a Lyapunov function, LaSalle's invariance principle shows that every positive limit point is an equilibrium. Since trajectories remain uniformly away from collisions, the energy is analytic along the flow and an argument yields convergence to a single equilibrium modulo translations. Illustrative numerical examples are presented.

Freight Signal Priority (FSP) systems have emerged as a promising strategy to enhance freight mobility and reduce corridor delays in urban networks. While extensive research has focused on priority control algorithms and operational performance evaluation, comparatively limited attention has been devoted to the architectural design of sensing processes that shape reliable priority decisions. In practice, uncertainties in vehicle detection, communication, and estimated time of arrival (ETA) may propagate within the sensing-to-decision process, affecting priority timing and downstream signal performance. This paper presents a systematic review of FSP systems from a sensing-to-decision perspective. We propose a generic two-layer architecture consisting of a sensing-to-decision layer and a control execution layer. The sensing-to-decision layer transforms sensing inputs into priority decisions, while the control execution layer implements approved actions within traffic controllers. Within this architecture, we systematically compare major sensing modalities, including loop detectors, vision sensors, and V2I, across dimensions such as classification capability, state estimation accuracy, latency, and information richness. We further examine representative FSP systems to analyze how modality-specific characteristics and uncertainties influence ETA computation, priority triggering, and decision reliability. By linking sensing design to decision outcomes, this review identifies key deployment challenges and research gaps in reliability-aware sensing-to-decision design. Ultimately, this work provides a conceptual foundation for developing scalable and robust FSP systems that explicitly account for sensing imperfections rather than assuming idealized inputs.

This paper presents a proof of concept of the Virtual Speech Therapist (VST), an intelligent multi-agent based system designed to support stuttering assessment and individualized therapy planning through artificial intelligence (AI) driven workflows. VST integrates deep learning (DL) based stuttering detection fSD with large language model (LLM) based agentic system to assist clinicians in developing evidence informed therapy plans. The VST system begins with the acquisition and feature extraction of given speech samples, followed by the detection of stuttering types. Building on these speech driven information S, VST initiates an agentic reasoning process in which specialized LLM agents autonomously generate, critique, and iteratively refine individualized therapy plans P. A dedicated CriticAgent {\pi}ca acts as a structured self-refinement mechanism, reviewing the generated therapy plans P and identifying areas for potential improvement in consistency, methodological soundness, and alignment with available evidence and professional guidelines. The resulting therapy plan P is presented then as a draft for clinician review. Clinician feedback can then be incorporated to produce a revised plan P, thereby maintaining a clinician-in-the-loop (CITL) paradigm. An initial evaluation, involving expert speech language pathologist (SLP) examines the clinical interpretability and feasibility of the generated therapy plans. Taken together, the results show the potential of VST to augment clinician-led therapy planning and provide a promising basis for future studies evaluating its integration into real world clinical settings. An interactive user interface for the proposed prototype is available online at: https://vocametrix.com/ai/stuttering-therapy-planning-agent, facilitating interactive stuttering assessment and stuttering therapy planning.

Closed-loop bioelectronic regulation of engineered secretory cell systems is challenging because electric-field (EF) stimulation acts indirectly through transcription-factor activation, in the presence of delayed, nonlinear, and noisy intracellular dynamics, sparse measurements, and constrained burst-based actuation. We develop a framework for robust closed-loop endocrine regulation in electrically stimulated engineered cell factories, illustrated through extracellular thyroid hormone \(T_4\) production in engineered thyroid-like cells. The plant is modeled by a control-oriented ODE formulation combining a reduced mechanistic \(T_4\) pathway, an EF-responsive Hill module, and a linear-chain Erlang cascade representing distributed intracellular delay. On this basis, we design a sampled-data adaptive proportional-integral-derivative (PID) controller with derivative filtering, anti-windup, saturation and rate limits, and hysteretic band-locking, together with a robust adaptive extension that accounts for parameter mismatch, sensor noise and bias, actuator mismatch, delay/jitter, and exogenous rhythmic disturbance through a scenario-based risk-aware update. We provide local sampled-data input-to-state stability interpretations for both APID and RAPID, showing that, under standard local Lyapunov and bounded-disturbance conditions, the sampled tracking error is ultimately bounded by a disturbance-dependent constant. In silico experiments demonstrate sustained regulation of extracellular \(T_4\) across prescribed targets despite significant uncertainty.

Ensuring the structural integrity of building tiles is important for public safety and the durability of urban infrastructure. This study proposes a controlled experimental framework to quantify the effect of Unmanned Aerial vehicle (UAV) induced dynamic perturbations on acoustic tap-testing reliability for facade inspection. This work explicitly analyzes vibration-induced degradation and introduces an energy-based signal correction method to preserve classification performance under motion disturbances. In addition, Principal Component Analysis (PCA) is applied to process and classify wirelessly acquired acoustic data, reducing dimensionality while preserving key defect related features. A Stewart platform is used to reproduce controlled oscillatory conditions derived from UAV flight characterization, enabling systematic evaluation across multiple vibration amplitudes. Results show that classification accuracy degrades significantly under increasing perturbations, but can be restored above 98% using the proposed energy-based filtering approach.

Statistical change point (CP) detection methods typically rely on likelihood-based inference and ignore contextual information about plausible CP locations beyond the observed sequence. Although informative priors provide a natural way to incorporate such information, general and computationally efficient methods for doing so are lacking, especially for multiple CP detection. To address this gap, we propose a prior-informed CP detection algorithm (Pi-Change) that incorporates prior information on CP locations through a time-varying penalty term. We prove that the proposed penalty can be embedded in the Pruned Exact Linear Time framework while preserving the dynamic programming recursion and pruning rule required for efficient multiple CP detection. Across simulation studies and three time-series applications, Pi-Change discourages spurious CPs unsupported by prior information, remains robust to prior misspecification, and improves detection accuracy. More broadly, Pi-Change extends multiple CP detection beyond purely data-driven fitting by incorporating partial prior knowledge in a computationally efficient and interpretable way. It is particularly useful when CPs arise from heterogeneous mechanisms or are associated with known external events, helping quantify the delay between an event and the resulting structural change.

Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, most existing self supervised learning methods treat these signals as interchangeable views, overlooking the directional temporal dynamics that link them. A canonical example is the relationship between electrocardiography (ECG), which captures the electrical activation initiating each heartbeat, and photoplethysmography (PPG), which records the resulting peripheral pulse delayed by vascular dynamics. To capture this structured relationship, we introduce xMAE, a biosignal pretraining framework that leverages masked cross modal reconstruction across temporally ordered biosignals as a training time constraint to encourage physiologically meaningful timing structure in the learned representations. We show that pretraining with xMAE yields representations that outperform both unimodal and multimodal baselines on 15 of 19 downstream tasks, including cardiovascular outcome prediction, abnormal laboratory test detection, sleep staging, and demographic inference, while generalizing across devices, body locations, and acquisition settings. Further analysis suggests that the ECG PPG timing structure is reflected in the learned PPG representations. More broadly, xMAE demonstrates the effectiveness of incorporating temporal structure into multimodal pretraining when signals observe different stages of a shared underlying process. Code is available at https://github.com/hzhou3/xMAE.

Background: Sensitivity of AI-assisted lung nodule detection systems is known to vary with CT acquisition parameters including radiation dose, reconstruction kernel, and slice thickness. However, the dependence of detection probability on nodule position within the reconstruction cycle – the z-phase – has not, to the author's knowledge, been characterized for deep learning-based detection systems. Methods: A retrospective analysis was performed using the LIDC-IDRI dataset. Detection results from a previously validated 154-case perturbation study were re-analyzed. For each consensus nodule (>=4-reader agreement), z-phase was defined as the fractional position of the nodule center within the reconstruction cycle, folded to [0, 0.5]. Detection sensitivity was stratified by z-phase bin, reconstruction interval (1mm, 3mm, 5mm), and by the ratio of reconstruction interval to nodule diameter (d/D). Results: At 5mm reconstruction interval, sensitivity was 71.6% vs 84.8% at 1mm baseline. Within the 5mm condition, sensitivity varied by 17.6 percentage points across z-phase bins. Stratified by d/D ratio, sensitivity was 92.4% for d/D < 0.5, 78.0% for 0.5 <= d/D < 1.0, and 61.4% for d/D >= 1.0, with a systematic z-phase effect present only in the d/D >= 1.0 stratum. Conclusions: AI detection sensitivity depends on the ratio of reconstruction interval to nodule diameter. When this ratio approaches or exceeds 1.0 – as occurs for 3-6mm nodules at 5mm reconstruction – z-phase becomes the dominant source of per-study detection variance. This stochastic effect is invisible to protocol-level quality metrics and not reflected in AI confidence scores.

Wireless foundation models (WFMs) have emerged as a promising paradigm for unified channel state information (CSI) acquisition across diverse tasks in sixth-generation (6G) networks. Although WFMs significantly outperform task-specific small models, their zero-shot cross-scenario generalization still remains limited for real-world applications. Existing positional embeddings, the sole interface through which self-attention perceives the temporal-frequency-antenna 3D physical coordinates of CSI, fail to capture the highly dynamic and axis-dependent coherence inherent in wireless channels. This paper proposes Adaptive 3D-RoPE, a channel-driven 3D rotary positional embedding framework for WFMs to dynamically align the 3D positional embeddings with the instantaneous coherence state of heterogeneous CSI. The design proceeds in three stages: first, an axis-wise learnable rotary prior independently preserves the temporal, frequency, and antenna coordinate structures; second, a feature-guided rotary modulation module maps the feature-wise standard deviation of visible CSI tokens to compact, sample-adaptive scales; third, identical coordinate offsets induce dynamically adjusted query-key interactions tailored to the instantaneous channel state. Extensive experiments on both simulated and measured datasets validate the effectiveness of Adaptive 3D-RoPE across three complementary dimensions. It reduces NMSE by 10.14, 6.25, and 4.61 dB relative to baselines under antenna, temporal, and frequency scaling, respectively. It transfers effectively to real-world measured CSI and remains robust under imperfect CSI. Finally, it transfers to the independently designed LWM backbone and beam-prediction task, improving zero-shot Top-1 accuracy by 8.03 percentage points.

Monitoring high-dimensional engineering structures in extreme environments is limited by non-stationary excitation, nonlinear structural kinematics, and stochastic forcing. Traditional model-based and black-box data-driven methods often struggle to resolve these dynamics in real time, particularly under sensor failure or partial observability. This paper introduces a rank-optimized digital twin framework based on Koopman operator theory, Hankel-matrix embeddings, and dynamic mode decomposition. By lifting operational data into a linear invariant subspace, the method enables autonomous, input-blind reconstruction of structural states without requiring a priori mass or stiffness matrices. The framework is validated on an NREL 5MW spar-buoy floating offshore wind turbine, representing a challenging coupled aero-hydro-servo-elastic system. Results show that the rank-optimized Koopman-Hankel manifold separates structural resonances from deterministic 3P rotor harmonics under colored noise, where standard subspace identification can be unreliable. A rolling-horizon virtual sensing strategy achieves high-fidelity reconstruction at critical structural hotspots, with coefficient of determination greater than 0.95 at 1 Hz data assimilation and accuracy exceeding 0.99 at higher sampling rates. By estimating a physical Lyapunov time of approximately 1.0 s, the study defines the predictability horizon associated with the system information barrier. The proposed framework provides a computationally efficient and resilient digital twin approach for real-time identification and virtual sensing of complex structural dynamics.

With the development of deep learning, medical image processing has been widely used to assist clinical research. This paper focuses on the denoising problem of low-dose computed tomography using deep learning. Although low-dose computed tomography reduces radiation exposure to patients, it also introduces more noise, which may interfere with visual interpretation by physicians and affect diagnostic results. To address this problem, inspired by Cycle-GAN for unsupervised learning, this paper proposes an end-to-end unsupervised low-dose computed tomography denoising framework. The proposed framework combines a U-Net structure for multi-scale feature extraction, an attention mechanism for feature fusion, and a residual network for feature transformation. It also introduces perceptual loss to improve the network for the characteristics of medical images. In addition, we construct a real low-dose computed tomography dataset and design a large number of comparative experiments to validate the proposed method, using both image-based evaluation metrics and medical evaluation criteria. Compared with classical methods, the main advantage of this paper is that it addresses the limitation that real clinical data cannot be directly used for supervised learning, while still achieving excellent performance. The experimental results are also professionally evaluated by imaging physicians and meet clinical needs.

A speaker encoder used in multilingual voice cloning should treat the same speaker identically regardless of which script the audio was uttered in. Off-the-shelf encoders do not, and the failure is accent-conditional. On a 1043-pair Western-accented voice corpus across English, Hindi, Telugu, and Tamil, WavLM-base-plus-sv loses 0.082 absolute cosine similarity when the same voice changes script and ECAPA-TDNN loses 0.105. On a 1369-pair Indian-accented voice corpus, the gap shrinks to 0.006 (WavLM-SV) and 0.044 (ECAPA-TDNN). The leak is largest where it matters most for cross-script TTS: when a system projects a non-Indic-trained voice into Indic scripts. We present LASE (Language-Adversarial Speaker Encoder), a small projection head over frozen WavLM-base-plus trained with two losses: a supervised contrastive loss over voice identity, and a gradient-reversal cross-entropy against a 4-language classifier that pushes the embedding to be language-uninformative while remaining speaker-informative. Trained on 1118 quality-gated cross-script pairs synthesised from 8 commercial multilingual voices, LASE's residual gap is consistent with zero on both corpora (Delta = 0.013 Western, Delta = 0.026 Indian; both bootstrap 95% CIs include zero) and amplifies the cross-script-vs-floor margin 2.4-2.7x over both baselines. An ECAPA+GRL ablation shows the GRL objective improves either backbone but the WavLM choice contributes too. In synthetic multi-speaker diarisation, LASE matches ECAPA-TDNN on cross-script speaker recall (0.788 vs 0.789) with ~100x less training data. We release the r1 checkpoint, both corpora, and the bootstrap recipe.

This paper provides a detailed investigation of voltage ride-through in large loads, such as Artificial Intelligence data centers. Voltage ride-through capability of large loads during transient disturbances in the power grid is important because of the potential impact on the stability and reliability of the Bulk Power System. A mathematical analysis is presented and it is shown how the traditional approach, based on reactive power compensation, may not be adequate for voltage ride-through in large loads. Ultimately, due to capacity limits of the load's power distribution infrastructure and grid's constraints, there is a limit to using reactive power as a corrective tool. A new dual active and reactive power (PQ) approach is proposed in which non-grid resources with dynamic P and Q capabilities are shown to be needed to help with voltage ride-through. Additionally, the analysis illustrates that at extreme voltage dips in the power grid maintaining an acceptable level of load voltage can become practically or theoretically unattainable, which may lead to the load's disconnection from the grid. Analytical results are provided with practical numerical examples.

Communications in highly dynamic channels relying on training-based channel estimation experience a trade-off between increasing channel measurement accuracy by sending more frequent training sequences and increasing data rate by sending fewer training sequences. Simultaneously, most communication systems use forward error correction to enable error detection and correction at the receiver. This paper presents decoder-provided pilots for time-varying channels by using decoded codewords as training sequences to update the channel estimate at the receiver. In contrast to approaches such as data-aided channel estimation, decision-feedback equalization, joint channel estimation and error correction, and turbo equalization, the decoder-provided pilots approach is non-iterative, which is ideal for low-latency requirements in highly dynamic scenarios. Furthermore, it is modulation-, code-, and decoder-agnostic, meaning it can be implemented on top of virtually any communication system that uses forward error correction. From an information-theoretic perspective, we derive the fundamental limits of decoder-provided pilots' ability to simultaneously sense the channel and transmit data. Simulation results demonstrate that decoder-provided pilots significantly improve performance, that when coding across frequency, soft-output can further enhance performance, and that when coding across time, short codes can outperform long codes of the same rate in fast-fading channels.