Papers

This paper presents a novel approach to many-vs-many missile guidance using virtual targets (VTs) generated by a Normalizing Flows-based trajectory predictor. Rather than assigning n interceptors directly to m physical targets through conventional weapon target assignment algorithms, we propose a centralized strategy that constructs n VT trajectories representing probabilistic predictions of maneuvering target behavior. Each interceptor is guided toward its assigned VT using Zero-Effort-Miss guidance during midcourse flight, transitioning to Proportional Navigation guidance for terminal interception. This approach treats many-vs-many engagements as many-vs-distribution scenarios, exploiting numerical superiority (n > m) by distributing interceptors across diverse trajectory hypotheses rather than pursuing identical deterministic predictions. Monte Carlo simulations across various target-interceptor configurations (1-6 targets, 1-8 interceptors) demonstrate that the VT method matches or exceeds baseline straight-line prediction performance by 0-4.1% when n = m, with improvements increasing to 5.8-14.4% when n > m. The results confirm that probabilistic VTs enable effective exploitation of numerical superiority, significantly increasing interception probability in many-vs-many scenarios.

This paper presents a decentralized methodology for detecting and mitigating flapping phenomena in power systems, primarily caused by the operation of discrete devices. The proposed approach applies moving-window autocorrelation to local measurements, enabling each device to autonomously identify sustained oscillations. Upon detection, a probabilistic, device-specific mitigation strategy is executed. Flexible demand resources (DFRs), under-load tap changers (ULTCs), and automatic voltage regulators (AVRs) are utilised to illustrate the performance of the proposed approach to both discrete and continuous-operation devices. Results show that the proposed method is robust and properly distinguishes damped oscillations from persistent flapping, allowing devices to independently recognize problematic operating scenarios and implement corrective actions accordingly.

There is an urgent reflection on traditional nonlinear signal processing methods in communications before Artificial Intelligence (AI) dominates the field. It implies a need to reassess or reinterpret established theories and tools, highlighting the tension between data-driven and model-based approaches. This paper calls for preserving valuable insights from classical signal processing while exploring how they can coexist or integrate with emerging AI methods.

The paper proposes a novel general definition of coherency among power system devices of any type. The proposed approach is thus not limited to synchronous machines. With this aim, the paper shows that coherency can be formally based on the difference in the complex frequency of the current injections of any two devices electrically connected to the same grid. The proposed definition is model-agnostic, making it general and suitable for modern power systems composed of a heterogeneous mix of technologies. The paper also provides a systematic analytical procedure to study the properties that specific device models must satisfy to be coherent. Time-domain simulations are conducted in three case studies whose results illustrate the ability of our definition to evaluate coherency among any type of device.

Intelligent transportation systems (ITS) still have a hard time accurately predicting traffic in cities, especially in big, multimodal settings with complicated spatiotemporal dynamics. This paper presents HybridST, a hybrid architecture that integrates Graph Neural Networks (GNNs), multi-head temporal Transformers, and supervised ensemble learning methods (XGBoost or Random Forest) to collectively capture spatial dependencies, long-range temporal patterns, and exogenous signals, including weather, calendar, or control states. We test our model on the METR-LA, PEMS-BAY, and Seattle Loop tree public benchmark datasets. These datasets include situations ranging from freeway sensor networks to vehicle-infrastructure cooperative perception. Experimental results show that HybridST consistently beats classical baselines (LSTM, GCN, DCRNN, PDFormer) on important metrics like MAE and RMSE, while still being very scalable and easy to understand. The proposed framework presents a promising avenue for real-time urban mobility planning, energy optimization, and congestion alleviation strategies, especially within the framework of smart cities and significant events such as the 2030 FIFA World Cup.

This paper proposes a novel control framework designed for Inverter-Based Resources (IBRs), denoted as Generalized Swing Control (GSC). The proposed GSC framework generalizes the definition of Grid-Forming (GFM) control schemes and exploits the coupling between active and reactive power dynamics. To validate the proposed scheme, we conduct extensive time-domain simulations and small-signal analysis using a modified version of the WSCC 9-bus system and a 1479-bus dynamic model of the all-island Irish transmission system. The case studies focus on evaluating the dynamic performance of the proposed framework under different configurations, including Virtual Synchronous Machine (VSM), coupled-VSM and dual-VSM schemes. To address the nonlinear nature of power system dynamics, sensitivity analysis based on Monte Carlo methods are employed to improve parameter tuning and assess the stability of GSC configurations in the studied systems.

This study investigates brain connectivity and information flow during mental workload (MWL) by integrating electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals. Utilizing the N-back task to induce varying levels of MWL in 26 participants, we analyzed both functional and effective connectivity across 25 cortical regions derived from combined EEG and fNIRS signals. Functional connectivity was assessed using Pearson Correlation Coefficient (PCC), Phase Locking Value (PLV), and Magnitude Squared Coherence (MSC), while effective connectivity was evaluated using directed Directed Transfer Function (dDTF) and generalized Partial Directed Coherence (gPDC). Our findings reveal increased functional connectivity in frontal regions during higher MWL conditions (3-back compared to 0-back). Furthermore, effective connectivity analysis demonstrates a significant directional information flow from EEG to fNIRS, indicating a dominant influence of neural activity on hemodynamic responses. Statistical tests confirm significant differences in connectivity patterns between low and high MWL states. These results underscore the utility of EEG-fNIRS integration for characterizing brain network dynamics under varying cognitive demands and provide insights into neurovascular coupling mechanisms during mental workload.

Machine learning methods are increasingly applied in medical imaging, yet many reported improvements lack statistical robustness: recent works have highlighted that small but significant performance gains are highly likely to be false positives. However, these analyses do not take underspecification into account – the fact that models achieving similar validation scores may behave differently on unseen data due to random initialization or training dynamics. Here, we extend a recent statistical framework modeling false outperformance claims to include underspecification as an additional variance component. Our simulations demonstrate that even modest seed variability ($\sim1\%$) substantially increases the evidence required to support superiority claims. Our findings underscore the need for explicit modeling of training variance when validating medical imaging systems.

Integrate-and-Fire Time Encoding Machine (IF-TEM) is a power-efficient asynchronous sampler that converts analog signals into non-uniform time-domain samples. Adaptive IF-TEM (AIF-TEM) improves this machine by adapting its process to the characteristics of the input signal, thereby reducing the sampling rate. Compressed IF-TEM (CIF-TEM) reduces bit usage by performing analog compression before quantization. In this paper, we introduce a combined Adaptive Compressed IF-TEM (ACIF-TEM) – a new sampler that leverages the two machines, AIF-TEM and CIF-TEM, where each reinforces the effectiveness of the other. We propose an efficient adaptive clockless time-to-digital converter (TDC) architecture for the novel sampler that integrates the compression stage within the TDC, facilitating the realization of the intended integrated system. \ifconf \else We analyze the total bit usage, and contrast its performance with that of IF-TEM, AIF-TEM, and CIF-TEM.\fi Via an evaluation study, we demonstrate that the proposed ACIF-TEM sampler achieves lower Mean Square Error (MSE) with fewer bits, offering compression gains of at least 3-bit out of 9-bits over AIF-TEM and 60% compression over IF-TEM, for fixed recovery MSE with real audio signals.

This paper proposes a novel nonlinear decentralized voltage controller for constrained regulation of meshed AC Microgrid networks with high penetration of time-varying constant power loads. Modelling the load demand as a constantly evolving unknown disturbance, the network model is reformulated in a cascaded structure composed of a nominal, \ie uncertainty-free, and an error subsystem. By adopting a suitable control barrier function, we formulate a continuous-time control law and derive analytic conditions on the tuning parameters, such that the distance between the true and the nominal state trajectories is bounded. Under sufficient conditions, we prove asymptotic stability of the cascaded dynamics with respect to an equilibrium set and also provide an estimate of the region of attraction. In addition, it is rigorously shown that the proposed nonlinear control law enforces constrained regulation around a rated voltage value, without the need of saturation devices. The operation of the closed-loop system is illustrated both via simulation and real-time HIL scenarios, demonstrating bounded operation and convergence to a neighbourhood of the desired reference vector.

Solving the explicit Model Predictive Control (MPC) problem requires enumerating all critical regions and their associated feedback laws, a task that scales exponentially with the system dimension and the prediction horizon, as well. When the problem's constraints are boxes or zonotopes, the feasible domain admits a compact constrained-zonotope representation. Building on this insight, we exploit the geometric properties of the equivalent constrained-zonotope reformulation to accelerate the computation of the explicit solution. Specifically, we formulate the multi-parametric problem in the lifted generator space and solve it using second-order optimality conditions, employ low-rank matrix updates to reduce computation time, and introduce an analytic enumeration of candidate active sets that yields the explicit solution in tree form.

The capability of a novel Kullback-Leibler divergence method is examined herein within the Kalman filter framework to select the input-parameter-state estimation execution with the most plausible results. This identification suffers from the uncertainty related to obtaining different results from different initial parameter set guesses, and the examined approach uses the information gained from the data in going from the prior to the posterior distribution to address the issue. Firstly, the Kalman filter is performed for a number of different initial parameter sets providing the system input-parameter-state estimation. Secondly, the resulting posterior distributions are compared simultaneously to the initial prior distributions using the Kullback-Leibler divergence. Finally, the identification with the least Kullback-Leibler divergence is selected as the one with the most plausible results. Importantly, the method is shown to select the better performed identification in linear, nonlinear, and limited information applications, providing a powerful tool for system monitoring.

In this paper, a novel large language model (LLM)-based pathloss map generation model, termed LLM4PG, is proposed for sixth-generation (6G) AI-native communication systems via Synesthesia of Machines (SoM). To explore the mapping mechanism between sensing images and pathloss maps, a new synthetic intelligent multi-modal sensing-communication dataset, SynthSoM-U2G, is constructed, covering multiple scenarios, frequency bands, and flight altitudes. By adapting the LLM for cross-modal pathloss map generation for the first time, LLM4PG establishes an effective cross-domain alignment between the multi-modal sensing-communication and natural language domains. A task-specific fine-tuning strategy with a tailored layer selection and activation scheme is designed to meet the demands of massive-scale, high-quality generation. Compared with conventional deep learning artificial intelligence generated content (AIGC) models, LLM4PG achieves more accurate pathloss map generation and stronger generalization across diverse conditions. Results show that LLM4PG attains an NMSE of 0.0454, outperforming the conventional AIGC model by over 2.90 dB, while its cross-condition generalization achieves an NMSE of 0.0492, exceeding the baseline by 4.52 dB.

The development of clinically reliable artificial intelligence (AI) systems for mammography is hindered by profound heterogeneity in data quality, metadata standards, and population distributions across public datasets. This heterogeneity introduces dataset-specific biases that severely compromise the generalizability of the model, a fundamental barrier to clinical deployment. We present MammoClean, a public framework for standardization and bias quantification in mammography datasets. MammoClean standardizes case selection, image processing (including laterality and intensity correction), and unifies metadata into a consistent multi-view structure. We provide a comprehensive review of breast anatomy, imaging characteristics, and public mammography datasets to systematically identify key sources of bias. Applying MammoClean to three heterogeneous datasets (CBIS-DDSM, TOMPEI-CMMD, VinDr-Mammo), we quantify substantial distributional shifts in breast density and abnormality prevalence. Critically, we demonstrate the direct impact of data corruption: AI models trained on corrupted datasets exhibit significant performance degradation compared to their curated counterparts. By using MammoClean to identify and mitigate bias sources, researchers can construct unified multi-dataset training corpora that enable development of robust models with superior cross-domain generalization. MammoClean provides an essential, reproducible pipeline for bias-aware AI development in mammography, facilitating fairer comparisons and advancing the creation of safe, effective systems that perform equitably across diverse patient populations and clinical settings. The open-source code is publicly available from: https://github.com/Minds-R-Lab/MammoClean.

We present the Alternating Direction Method of Multipliers (ADMM) for Performance Boosting (PB), an approach for designing neural controllers for stable nonlinear systems subject to state and input constraints. The method builds on an internal model control formulation of PB. In this setting, the controller is parametrized as a stable neural operator, so closed-loop stability is guaranteed by construction, and its weights are trained offline to improve performance. To provide a systematic procedure for promoting constraint satisfaction during training, we reformulate the finite-horizon problem of the PB formulation by introducing auxiliary state and input trajectories. This augmentation allows us to cast an ADMM-based algorithm that alternates between two steps: a gradient-descent-based update of the controller parameters, having the same structure as the PB training problem without explicit constraints, and a projection step that promotes the trajectory feasibility. As a result, this procedure handles constraints during training without altering the controller architecture or compromising its stability-by-design guarantees. Indeed, the stability guarantee follows from the chosen stable controller parametrization, which is not changed in our framework with respect to the foundational PB formulation, and is independent of ADMM convergence. At the same time, this closed-loop stability guarantee does not imply performance optimality or closed-loop constraint satisfaction, which depend on the convergence of ADMM-PB, which is not yet guaranteed in this work. Our numerical results show that, compared with a baseline based on barrier-inspired soft penalties in the loss, ADMM-PB achieves lower constraint violations, at the price of more conservative closed-loop behavior.

Early detection of heart arrhythmia can prevent severe future complications in cardiac patients. While manual diagnosis still remains the clinical standard, it relies heavily on visual interpretation and is inherently subjective. In recent years, deep learning has emerged as a powerful tool to automate arrhythmia detection, offering improved accuracy, consistency, and efficiency. Several variants of convolutional and recurrent neural network architectures have been widely explored to capture spatial and temporal patterns in physiological signals. However, despite these advancements, current models often struggle to generalize well in real-world scenarios, especially when dealing with small or noisy datasets, which are common challenges in biomedical applications. In this paper, a novel CNN-H-Infinity-LSTM architecture is proposed to identify arrhythmic heart signals from heart sound recordings. This architecture introduces trainable parameters inspired by the H-Infinity filter from control theory, enhancing robustness and generalization. Extensive experimentation on the PhysioNet CinC Challenge 2016 dataset, a public benchmark of heart audio recordings, demonstrates that the proposed model achieves stable convergence and outperforms existing benchmarks, with a test accuracy of 99.42% and an F1 score of 98.85%.

This work addresses the problem of efficient sampling of Markov random fields (MRF). The sampling of Potts or Ising MRF is most often based on Gibbs sampling, and is thus computationally expensive. We consider in this work how to circumvent this bottleneck through a link with Gaussian Markov Random fields. The latter can be sampled in several cost-effective ways, and we introduce a mapping from real-valued GMRF to discrete-valued MRF. The resulting new class of MRF benefits from a few theoretical properties that validate the new model. Numerical results show the drastic performance gain in terms of computational efficiency, as we sample at least 35x faster than Gibbs sampling using at least 37x less energy, all the while exhibiting empirical properties close to classical MRFs.

The increasing spectral reuse can cause significant performance degradation due to interference from neighboring cells. In such scenarios, developing effective interference suppression schemes is necessary to improve overall system performance. To tackle this issue, we propose a novel user equipment-centric interference suppression scheme, which effectively detects inter-cell interference (ICI) and subsequently applies interference whitening to mitigate ICI. The proposed scheme, named Z-refined deep support vector data description, exploits a one-class classification-based anomaly detection technique. Numerical results verify that the proposed scheme outperforms various baselines in terms of interference detection performance with limited time or frequency resources for training and is comparable to the performance based on an ideal genie-aided interference suppression scheme. Furthermore, we demonstrate through test equipment experiments using a commercial fifth-generation modem chipset that the proposed scheme shows performance improvements across various 3rd generation partnership project standard channel environments, including tapped delay line-A, -B, and -C models.

This paper presents the ZJUNlict team's work over the past year, covering both hardware and software advancements. In the hardware domain, the integration of an IMU into the v2023 robot was completed to enhance posture accuracy and angular velocity planning. On the software side, key modules were optimized, including the strategy and CUDA modules, with significant improvements in decision making efficiency, ball pursuit prediction, and ball possession prediction to adapt to high-tempo game dynamics.

In this paper, we investigate a channel estimation problem in a downlink millimeter-wave (mmWave) multiple-input multiple-output (MIMO) system, which suffers from impulsive interference caused by hardware non-idealities or external disruptions. Specifically, impulsive interference presents a significant challenge to channel estimation due to its sporadic, unpredictable, and high-power nature. To tackle this issue, we develop a Bayesian channel estimation technique based on variational inference (VI) that leverages the sparsity of the mmWave channel in the angular domain and the intermittent nature of impulsive interference to minimize channel estimation errors. The proposed technique employs mean-field approximation to approximate posterior inference and integrates VI into the sparse Bayesian learning (SBL) framework. Simulation results demonstrate that the proposed technique outperforms baselines in terms of channel estimation accuracy.

This paper studies the performance of optical orthogonal frequency-division multiplexing (OFDM)-based multi-user integrated sensing and communication (ISAC) systems employing non-orthogonal multiple access (NOMA). Due to their inherent high peak-to-average power ratio (PAPR), OFDM waveforms are clipped to fit the limited dynamic range of the optical transmitters (e.g., light-emitting diodes (LEDs)), resulting in clipping distortion. To alleviate the impact of the distortion, we propose a novel transmitter architecture where the clipping processes are performed before NOMA superposition coding. We then analyze the performance of the proposed optical ISAC systems considering the effects of power allocation and clipping distortion. For the communication subsystem, we analyze the effect of NOMA on the achievable sum rate and bit error rate (BER). For the sensing subsystem, the root mean square error (RMSE) and Cramér-Rao bound (CRB) of estimating the transmission distance accuracy are obtained. Simulation results reveal that allocating more power to the strong user yields a higher sum rate, lower BER, and better sensing performance, whereas a more balanced power allocation among users results in degraded BER and sensing performance.

Audio watermarking supports speech authenticity verification. We study whether combining heterogeneous watermarks can retain at least one detectable provenance signal when their failure modes differ. This Any-survival objective concerns complementary evidence retention, not simultaneous survival of all constituent marks or recovery of all payloads. To our knowledge, this is the first systematic study of neural audio watermark multiplexing, with a scoped benchmark covering five released systems, parallel and sequential baselines, and 14 evaluation conditions. The benchmark shows complementary failure modes, but naive composition does not reliably turn them into system-level robustness under the Any-survival objective. We therefore formulate multiplexing as watermark allocation and study perceptual-adaptive time-frequency multiplexing (PA-TFM), a training-free routing method, and MaskNet, a learned time-domain router for separately trained systems with native detectors. We use the five-system scoped benchmark to characterize multiplexing behavior and the AudioSeal-PerTh pair as a representative heterogeneous pair for adaptive watermark routing. Compared with direct parallel composition, MaskNet improves average TPR@1%FPR from 0.75 to 0.88 and SNR from 15.20 dB to 25.36 dB; compared with PA-TFM, it gives a clear system-level robustness gain under the Any-survival objective while retaining similar high-fidelity behavior. A SpeechTokenizer-aware case study further improves average TPR@1%FPR to 0.91 and SpeechTokenizer robustness from 0.20 to 0.60, showing that channel-adapted constituents can enter the same routing framework.

Dysarthria is a speech disorder characterized by impaired intelligibility and reduced communicative effectiveness. Automatic dysarthria assessment provides a scalable, cost-effective approach for supporting the diagnosis and treatment of neurological conditions such as Parkinson's disease, Alzheimer's disease, and stroke. This study investigates leveraging human perceptual annotations from speech synthesis assessment as reliable out-of-domain knowledge for dysarthric speech assessment. Experimental results suggest that such supervision can yield consistent and substantial performance improvements in self-supervised learning pre-trained models. These findings suggest that perceptual ratings aligned with human judgments from speech synthesis evaluations represent valuable resources for dysarthric speech modeling, enabling effective cross-domain knowledge transfer.

Millimeter wave communications are essential for modern wireless networks. It supports high data rates but suffers from severe path loss, which requires precise beam alignment to maintain reliable links. This beam management is particularly challenging in highly dynamic scenarios such as vehicle-to-infrastructure, and several methods have been presented. In this work, we propose a deep learning-based beam tracking framework that combines a position-aware beam pre-selection strategy with sequential prediction using recurrent neural networks. The proposed architecture can support deep learning models trained for both classification and regression. In contrast to many existing studies that evaluate beam tracking under predominantly line-of-sight (LOS) conditions, our work explicitly includes highly challenging non-LOS scenarios - with up to 50% non-LOS incidence in certain datasets - to rigorously assess model robustness. Experimental results demonstrate that our approach maintains high top-K accuracy, even under adverse conditions, while reducing the beam measurement overhead by up to 50%.

Speech quality is one of the main foci of speech-related research, where it is frequently studied with speech intelligibility, another essential measurement. Band-level perceptual speech intelligibility, however, has been studied frequently, whereas speech quality has not been thoroughly analyzed. In this paper, a Multiple Stimuli With Hidden Reference and Anchor (MUSHRA) inspired approach was proposed to study the individual robustness of frequency bands to noise with perceptual speech quality as the measure. Speech signals were filtered into thirty-two frequency bands with compromising real-world noise employed at different signal-to-noise ratios. Robustness to noise indices of individual frequency bands was calculated based on the human-rated perceptual quality scores assigned to the reconstructed noisy speech signals. Trends in the results suggest the mid-frequency region appeared less robust to noise in terms of perceptual speech quality. These findings suggest future research aiming at improving speech quality should pay more attention to the mid-frequency region of the speech signals accordingly.

The rapid growth of electric vehicle (EV) adoption poses operational and economic challenges for distribution systems, including increased line loading and network congestion. As a practical near-term alternative to infrastructure reinforcement, distribution network topology reconfiguration (DNTR) can redistribute power flows, reduce operating costs, and improve operational flexibility. This paper presents a data driven operational feasibility framework for evaluating EV integration under increasing demand levels across four configurations: standard distribution network (SDN), SDN with DNTR (SDNTR), SDN with distributed energy resources (SDN-DER), and SDNTR with DERs (SDNTR-DER). Smart meter derived EV charging behavior is used to construct nodal EV demand profiles, which are incorporated into a mixed integer linear programming based active power screening model for a modified IEEE 33 bus distribution system. Feasibility is assessed with respect to nodal active power balance, line thermal limits, radiality and connectivity, DER limits, and BESS intertemporal operation. A bisection search identifies maximum active power thermal feasible EV demand levels of 51%, 68%, 85%, and 102% for SDN, SDN-DER, SDNTR, and SDNTR-DER, respectively. The 102% result represents full residential EV adoption with a 2% additional charging demand margin. At 0% EV penetration, SDNTR-DER reduces operating cost by 54% relative to SDN, representing the baseline economic value of coordinated DER scheduling and DNTR. The reported limits represent active power thermal feasibility boundaries rather than full AC hosting capacity limits.

This study presents a hybrid deep learning framework, the Vision Transformer with Residual Feature Network (VRF-Net), for recovering high-resolution system matrices in Magnetic Particle Imaging (MPI). MPI resolution often suffers from downsampling and coil sensitivity variations. VRF-Net addresses these challenges by combining transformer-based global attention with residual convolutional refinement, enabling recovery of both large-scale structures and fine details. To reflect realistic MPI conditions, the system matrix is degraded using a dual-stage downsampling strategy. Training employed paired-image super-resolution on the public Open MPI dataset and a simulated dataset incorporating variable coil sensitivity profiles. For system matrix recovery on the Open MPI dataset, VRF-Net achieved nRMSE = 0.403, pSNR = 39.08 dB, and SSIM = 0.835 at 2x scaling, and maintained strong performance even at challenging scale 8x (pSNR = 31.06 dB, SSIM = 0.717). For the simulated dataset, VRF-Net achieved nRMSE = 4.44, pSNR = 28.52 dB, and SSIM = 0.771 at 2x scaling, with stable performance at higher scales. On average, it reduced nRMSE by 88.2%, increased pSNR by 44.7%, and improved SSIM by 34.3% over interpolation and CNN-based methods. In image reconstruction of Open MPI phantoms, VRF-Net further reduced reconstruction error to nRMSE = 1.79 at 2x scaling, while preserving structural fidelity (pSNR = 41.58 dB, SSIM = 0.960), outperforming existing methods. These findings demonstrate that VRF-Net enables sharper, artifact-free system matrix recovery and robust image reconstruction across multiple scales, offering a promising direction for future in vivo applications.

Segmental longitudinal strain (SLS) of the left ventricle (LV) is an important prognostic indicator for evaluating regional LV dysfunction, in particular for diagnosing and managing myocardial ischemia. Current techniques for strain estimation require significant manual intervention and expertise, limiting their efficiency and making them too resource-intensive for monitoring purposes. This study introduces the first automated pipeline, autoStrain, for SLS estimation in transesophageal echocardiography (TEE) using deep learning (DL) methods for motion estimation. We present a comparative analysis of two DL approaches: TeeFlow, based on the RAFT optical flow model for dense frame-to-frame predictions, and TeeTracker, based on the CoTracker point trajectory model for sparse long-sequence predictions. As ground truth motion data from real echocardiographic sequences are hardly accessible, we took advantage of a unique simulation pipeline (SIMUS) to generate a highly realistic synthetic TEE (synTEE) dataset of 80 patients with ground truth myocardial motion to train and evaluate both models. Our evaluation shows that TeeTracker outperforms TeeFlow in accuracy, achieving a mean distance error in motion estimation of 0.65 mm on a synTEE test dataset. Clinical validation on 16 patients further demonstrated that SLS estimation with our autoStrain pipeline aligned with clinical references, achieving a mean difference (95% limits of agreement) of 1.09% (-8.90% to 11.09%). Incorporation of simulated ischemia in the synTEE data improved the accuracy of the models in quantifying abnormal deformation. Our findings indicate that integrating AI-driven motion estimation with TEE can significantly enhance the precision and efficiency of cardiac function assessment in clinical settings.

Free-space optical (FSO) communication has emerged as a promising technology for inter-satellite links (ISLs) due to its high data rate, low power consumption, and reduced interference. However, the performance of inter-satellite FSO systems is highly sensitive to beam misalignment. While pointing-ahead angle (PAA) compensation is commonly employed, the effectiveness of PAA compensation depends on precise orbital knowledge and advanced alignment hardware, which are not always feasible in practice. To address this challenge, this paper investigates the impact of beam misalignment on inter-satellite FSO communication. We derive a closed-form expression for the cumulative distribution function (CDF) of the FSO channel under the joint jitter and misalignment-induced pointing error, and introduce a truncated CDF formulation with a bisection algorithm to efficiently compute outage probabilities with guaranteed convergence and minimal computational overhead. To make the analysis more practical, we quantify displacement based on orbital dynamics. Numerical results demonstrate that the proposed model closely matches Monte Carlo simulations, making the proposed model highly useful to design inter-satellite FSO systems in practice.

In this paper, the problem of online distributed zeroth-order optimization subject to a set constraint is studied via a multi-agent network, where each agent can communicate with its immediate neighbors via a time-varying directed graph. Different from the existing works on online distributed zeroth- order optimization, we consider the case where the estimate on the gradients are influenced by some non-zero-mean adverse noises. To handle this problem, we propose a new online dis- tributed zeroth-order mirror descent algorithm involving a kernel function-based estimator and a clipped strategy. Particularly, in the estimator, the kernel function-based strategy is provided to deal with the adverse noises, and eliminate the low-order terms in the Taylor expansions of the objective functions. Furthermore, the performance of the presented algorithm is measured by employing the dynamic regrets, where the offline benchmarks are to find the optimal point at each time. Under the mild assumptions on the graph and the objective functions, we prove that if the variation in the optimal point sequence grows at a certain rate, then the high probability bound of the dynamic regrets increases sublinearly. Finally, a simulation experiment is worked out to demonstrate the effectiveness of our theoretical results.