Early and accurate diagnosis of pulmonary hypertension (PH) is essential for optimal patient management. Differentiating between pre-capillary and post-capillary PH is critical for guiding treatment decisions. This study develops and validates a deep learning-based diagnostic model for PH, designed to classify patients as non-PH, pre-capillary PH, or post-capillary PH. This retrospective study analyzed data from 204 patients (112 with pre-capillary PH, 32 with post-capillary PH, and 60 non-PH controls) at the First Affiliated Hospital of Nanjing Medical University. Diagnoses were confirmed through right heart catheterization. We selected 6 samples from each category for the test set (18 samples, 10%), with the remaining 186 samples used for the training set. This process was repeated 35 times for testing. This paper proposes a deep learning model that combines Graph convolutional networks (GCN), Convolutional neural networks (CNN), and Transformers. The model was developed to process multimodal data, including short-axis (SAX) sequences, four-chamber (4CH) sequences, and clinical parameters. Our model achieved a performance of Area under the receiver operating characteristic curve (AUC) = 0.81 +- 0.06(standard deviation) and Accuracy (ACC) = 0.73 +- 0.06 on the test set. The discriminative abilities were as follows: non-PH subjects (AUC = 0.74 +- 0.11), pre-capillary PH (AUC = 0.86 +- 0.06), and post-capillary PH (AUC = 0.83 +- 0.10). It has the potential to support clinical decision-making by effectively integrating multimodal data to assist physicians in making accurate and timely diagnoses.

Face recognition is a crucial topic in data science and biometric security, with applications spanning military, finance, and retail industries. This paper explores the implementation of sparse Principal Component Analysis (PCA) using the Proximal Gradient method (also known as ISTA) and the Runge-Kutta numerical methods. To address the face recognition problem, we integrate sparse PCA with either the k-nearest neighbor method or the kernel ridge regression method. Experimental results demonstrate that combining sparse PCA-solved via the Proximal Gradient method or the Runge-Kutta numerical approach-with a classification system yields higher accuracy compared to standard PCA. Additionally, we observe that the Runge-Kutta-based sparse PCA computation consistently outperforms the Proximal Gradient method in terms of speed.

Early detection of gastric cancer, a leading cause of cancer-related mortality worldwide, remains hampered by the limitations of current diagnostic technologies, leading to high rates of misdiagnosis and missed diagnoses. To address these challenges, we propose an integrated system that synergizes advanced hardware and software technologies to balance speed-accuracy. Our study introduces the One Class Twin Cross Learning (OCT-X) algorithm. Leveraging a novel fast double-threshold grid search strategy (FDT-GS) and a patch-based deep fully convolutional network, OCT-X maximizes diagnostic accuracy through real-time data processing and seamless lesion surveillance. The hardware component includes an all-in-one point-of-care testing (POCT) device with high-resolution imaging sensors, real-time data processing, and wireless connectivity, facilitated by the NI CompactDAQ and LabVIEW software. Our integrated system achieved an unprecedented diagnostic accuracy of 99.70%, significantly outperforming existing models by up to 4.47%, and demonstrated a 10% improvement in multirate adaptability. These findings underscore the potential of OCT-X as well as the integrated system in clinical diagnostics, offering a path toward more accurate, efficient, and less invasive early gastric cancer detection. Future research will explore broader applications, further advancing oncological diagnostics. Code is available at https://github.com/liu37972/Multirate-Location-on-OCT-X-Learning.git.

We consider a heat equation with memory which is defined on a bounded domain in $\mathbb{R}^d$ and is driven by $m$ control inputs acting on the interior of the domain. Our objective is to numerically construct a state feedback controller for this equation such that, for each initial state, the solution of the closed-loop system decays exponentially to zero with a decay rate larger than a given rate $\omega>0$, i.e. we want to solve the $\omega$-stabilization problem for the heat equation with memory. We first show that the spectrum of the state operator $A$ associated with this equation has an accumulation point at $-\omega_0<0$. Given a $\omega\in(0,\omega_0)$, we show that the $\omega$-stabilization problem for the heat equation with memory is solvable provided certain verifiable conditions on the control operator $B$ associated with this equation hold. We then consider an appropriate LQR problem for the heat equation with memory. For each $n\in\mathbb{N}$, we construct finite-dimensional approximations $A_n$ and $B_n$ of $A$ and $B$, respectively, and then show that by solving a corresponding approximation of the LQR problem a feedback operator $K_n$ can be computed such that all the eigenvalues of $A_n + B_n K_n$ have real part less than $-\omega$. We prove that $K_n$ for $n$ sufficiently large solves the $\omega$-stabilization problem for the heat equation with memory. A crucial and nontrivial step in our proof is establishing the uniform (in $n$) stabilizability of the pair $(A_n+\omega I, B_n)$. We have validated our theoretical results numerically using two examples: an 1D example on a unit interval and a 2D example on a square domain.

The problem of incompressible fluid mixing arises in numerous engineering applications and has been well-studied over the years, yet many open questions remain. This paper aims to address the question "what do efficient flow fields for mixing look like, and how do they behave?" We approach this question by developing a framework which is inspired by the dynamic and geometric approach to optimal mass transport. Specifically, we formulate the fluid mixing problem as an optimal control problem where the dynamics are given by the continuity equation together with an incompressibility constraint. We show that within this framework, the set of reachable fluid configurations can formally be endowed with the structure of an infinite-dimensional Riemannian manifold, with a metric which is induced by the control effort, and that flow fields which are maximally efficient at mixing correspond to geodesics in this Riemannian space.

This article investigates the noise performance of a two-element phased array and interferometer containing a recently introduced self-interference canceler, which in the context of this work acts as a mutual-coupling canceler. To this end, a general framework is proposed to permit noise analysis of this network and a large variety of other networks. The framework-based numerical analysis for a two-element-phased array shows that the addition of the canceler significantly increases the beam-equivalent noise temperature. For a two-element interferometer used in cosmology, this increase in noise temperature is still acceptable as the sky noise temperature in the 20-to-200 MHz band is high. When used in an interferometer, the canceler provides the ability to null mutual coherence at the interferometer output. The ability to provide matching to reduce the sensitivity of the null in mutual coherence to the phase of the 90deg hybrids in the canceler is discussed.

Satellite rendezvous and docking (RvD) maneuvers are essential for satellite servicing and in-orbit assembly. Traditional approaches often treat translational and rotational motions independently, simplifying control design but potentially leading to inefficiencies in maneuver time and fuel consumption. To address these challenges, a novel cross-feedback sliding mode controller has been proposed, developing an interdependent regulation system for translational and rotational motion. This method decouples the relative translational and rotational motion of chaser satellite with respect to target satellite while incorporating cross-feedback mechanisms to account for their inherent coupling. By incorporating rotational state information into translational control laws and vice versa, the approach ensures coordinated adjustments, enhancing maneuver efficiency. The chaser satellite manages both translational and rotational adjustments to rendezvous and dock with the target satellite. The stability of the cross-feedback sliding mode controller is established within the Lyapunov framework, and simulation results substantiate the effectiveness of this strategy.

The identification of dermatological disease is an important problem in Mexico according with different studies. Several works in literature use the datasets of different repositories without applying a study of the data behavior, especially in medical images domain. In this work, we propose a methodology to preprocess dermaMNIST dataset in order to improve its quality for the classification stage, where we use lightweight convolutional neural networks. In our results, we reduce the number of instances for the neural network training obtaining a similar performance of models as ResNet.

Despite the massive costs and widespread harms of substance use, most individuals with substance use disorders (SUDs) receive no treatment at all. Digital therapeutics platforms are an emerging low-cost and low-barrier means of extending treatment to those who need it. While there is a growing body of research focused on how treatment providers can identify which patients need SUD support (or when they need it), there is very little work that addresses how providers should select treatments that are most appropriate for a given patient. Because SUD treatment involves months or years of voluntary compliance from the patient, treatment adherence is a critical consideration for the treatment provider. In this paper we focus on algorithms that a treatment provider can use to match the burden-level of proposed treatments to the time-varying engagement state of the patient to promote adherence. We propose structured models for a patient's engagement over time and their treatment adherence decisions. Using these models we pose a stochastic control formulation of the treatment-provider's burden selection problem. We propose an adaptive control approach that estimates unknown patient parameters as new data are observed. We show that these estimates are consistent and propose algorithms that use these estimates to make appropriate treatment recommendations.

The ability to predict motion in real time is fundamental to many maneuvering activities in animals, particularly those critical for survival, such as attack and escape responses. Given its significance, it is no surprise that motion prediction in animals begins in the retina. Similarly, autonomous systems utilizing computer vision could greatly benefit from the capability to predict motion in real time. Therefore, for computer vision applications, motion prediction should be integrated directly at the camera pixel level. Towards that end, we present a retina-inspired neuromorphic framework capable of performing real-time, energy-efficient MP directly within camera pixels. Our hardware-algorithm framework, implemented using GlobalFoundries 22nm FDSOI technology, integrates key retinal MP compute blocks, including a biphasic filter, spike adder, nonlinear circuit, and a 2D array for multi-directional motion prediction. Additionally, integrating the sensor and MP compute die using a 3D Cu-Cu hybrid bonding approach improves design compactness by minimizing area usage and simplifying routing complexity. Validated on real-world object stimuli, the model delivers efficient, low-latency MP for decision-making scenarios reliant on predictive visual computation, while consuming only 18.56 pJ/MP in our mixed-signal hardware implementation.

Although battery technology has advanced tremendously over the past decade, it continues to be a bottleneck for the mass adoption of electric aircraft in long-haul cargo and passenger delivery. The onboard energy is expected to be utilized in an efficient manner. Energy concumption modeling research offers increasingly accurate mathematical models, but there is scant research pertaining to real-time energy optimization at an operational level. Additionally, few publications include landing and take-off energy demands in their governing models. This work presents fundamental energy equations and proposes a proportional-integral-derivative (PID) controller. The proposed method demonstrates a unique approach to an energy consumption model that tracks real-time energy optimization along a predetermined path. The proposed PID controller was tested in simulation, and the results show its effectiveness and accuracy in driving the actual airspeed to converge to the optimal velocity without knowing the system dynamics. We also propose a model-predictive method to minimize the energy usage in landing and take-off by optimizing the flight trajectory.

Integrated sensing and communication (ISAC), assisted by reconfigurable intelligent surface (RIS) has emerged as a breakthrough technology to improve the capacity and reliability of 6G wireless network. However, a significant challenge in RIS-ISAC systems is the acquisition of channel state information (CSI), largely due to co-channel interference, which hinders meeting the required reliability standards. To address this issue, a minimax-concave penalty (MCP)-based CSI refinement scheme is proposed. This approach utilizes an element-grouping strategy to jointly estimate the ISAC channel and the RIS phase shift matrix. Unlike previous methods, our scheme exploits the inherent sparsity in RIS-assisted ISAC channels to reduce training overhead, and the near-optimal solution is derived for our studied RIS-ISAC scheme. The effectiveness of the element-grouping strategy is validated through simulation experiments, demonstrating superior channel estimation results when compared to existing benchmarks.

Reconfigurable distributed antenna and reflecting surface (RDARS) is a new architecture for the sixth-generation (6G) millimeter wave (mmWave) communications. In RDARS-aided mmWave systems, the active and passive beamforming design and working mode configuration for reconfigurable elements are crucial for system performance. In this paper, we aim to maximize the weighted sum rate (WSR) in the RDARS-aided mmWave system. To take advantage of RDARS, we first design a reconfigurable codebook (RCB) in which the number and dimension of the codeword can be flexibly adjusted. Then, a low overhead beam training scheme based on hierarchical search is proposed. Accordingly, the active and passive beamforming for data transmission is designed to achieve the maximum WSR for both space-division multiple access (SDMA) and time-division multiple access (TDMA) schemes. For the TDMA scheme, the optimal number of RDARS transmit elements and the allocated power budget for WSR maximization are derived in closed form. Besides, the superiority of the RDARS is verified and the conditions under which RDARS outperforms RIS and DAS are given. For the SDMA scheme, we characterize the relationship between the number of RDARS connected elements and the user distribution, followed by the derivation of the optimal placement positions of the RDARS transmit elements. High-quality beamforming design solutions are derived to minimize the inter-user interference (IUI) at the base station and RDARS side respectively, which nearly leads to the maximal WSR. Finally, simulation results confirm our theoretical findings and the superiority of the proposed schemes.

The increasing demand for reliable connectivity in industrial environments necessitates effective spectrum utilization strategies, especially in the context of shared spectrum bands. However, the dynamic spectrum-sharing mechanisms often lead to significant interference and critical failures, creating a trade-off between spectrum scarcity and under-utilization. This paper addresses these challenges by proposing a novel Intelligent Reflecting Surface (IRS)-assisted spectrum sensing framework integrated with decentralized deep learning. The proposed model overcomes partial observation constraints and minimizes communication overhead while leveraging IRS technology to enhance spectrum sensing accuracy. Through comprehensive simulations, the framework demonstrates its ability to monitor wideband spectrum occupancy effectively, even under challenging signal-to-noise ratio (SNR) conditions. This approach offers a scalable and robust solution for spectrum management in next-generation wireless networks.

We propose a pre-compensation scheme for bandwidth limitation and fiber dispersion (pre-BL-EDC) based on the modified Gerchberg-Saxton (GS) algorithm. Experimental results demonstrate 1.0/1.0/2.0 dB gains compared to modified GS pre-EDC for 20/28/32 Gbit/s bandwidth-limited systems.

The performance of deep learning-based multi-channel speech enhancement methods often deteriorates when the geometric parameters of the microphone array change. Traditional approaches to mitigate this issue typically involve training on multiple microphone arrays, which can be costly. To address this challenge, we focus on uniform circular arrays and propose the use of a spatial filter bank to extract features that are approximately invariant to geometric parameters. These features are then processed by a two-stage conformer-based model (TSCBM) to enhance speech quality. Experimental results demonstrate that our proposed method can be trained on a fixed microphone array while maintaining effective performance across uniform circular arrays with unseen geometric configurations during applications.

The integration of Maritime Autonomous Surface Ships (MASS) into global maritime operations represents a transformative shift in the shipping industry, promising enhanced safety, efficiency, and cost-effectiveness. However, the widespread adoption of autonomous ships necessitates a robust regulatory framework and rigorous certification processes to address the unique challenges posed by these advanced technologies. This paper proposes a gradual, multi-stage approach to the certification and integration of MASS, beginning with small-scale trials in controlled environments and progressing to large-scale international operations. Key considerations include the development of reliable control systems, cybersecurity measures, sensor technologies, and redundancy mechanisms to ensure safe and efficient navigation. Additionally, the paper explores the economic and environmental implications of autonomous shipping, as well as the evolving legal frameworks for liability and compensation in the event of collisions. By adopting a cautious and methodical approach, the maritime industry can mitigate risks and pave the way for the safe and sustainable integration of autonomous ships into global trade.

This paper presents an enhanced electric vehicle demand response system based on large language models, aimed at optimizing the application of vehicle-to-grid technology. By leveraging an large language models-driven multi-agent framework to construct user digital twins integrated with multidimensional user profile features, it enables deep simulation and precise prediction of users' charging and discharging decision-making patterns. Additionally, a data- and knowledge-driven dynamic incentive mechanism is proposed, combining a distributed optimization model under network constraints to optimize the grid-user interaction while ensuring both economic viability and security. Simulation results demonstrate that the approach significantly improves load peak-valley regulation and charging/discharging strategies. Experimental validation highlights the system's substantial advantages in load balancing, user satisfaction and grid stability, providing decision-makers with a scalable V2G management tool that promotes the sustainable, synergistic development of vehicle-grid integration.

We introduce behavioral inequalities as a way to model dynamical systems defined by inequalities among their variables of interest. We claim that such a formulation enables the representation of safety-aware dynamical systems, systems with bounds on disturbances, practical design limits and operational boundaries, etc. We develop a necessary and sufficient condition for the existence of solutions to such behavioral inequalities and provide a parametrization of solutions when they exist. Finally, we show the efficacy of the proposed method in two practical examples.

Achieving more powerful semantic representations and semantic understanding is one of the key problems in improving the performance of semantic communication systems. This work focuses on enhancing the semantic understanding of the text data to improve the effectiveness of semantic exchange. We propose a novel semantic communication system for text transmission, in which the semantic understanding is enhanced by coarse-to-fine processing. Especially, a dual attention mechanism is proposed to capture both the coarse and fine semantic information. Numerical experiments show the proposed system outperforms the benchmarks in terms of bilingual evaluation, sentence similarity, and robustness under various channel conditions.

While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging. The conventional approaches extended from optimization perspectives are usually quite involved, especially when jointly considering factors in different scales such as deployment and transmission in UAV-related scenarios. In this paper, we address the UAV-enabled multi-user secure communications by proposing a deep graph reinforcement learning framework. Specifically, we reinterpret the security beamforming as a graph neural network (GNN) learning task, where mutual interference among users is managed through the message-passing mechanism. Then, the UAV deployment is obtained through soft actor-critic reinforcement learning, where the GNN-based security beamforming is exploited to guide the deployment strategy update. Simulation results demonstrate that the proposed approach achieves near-optimal security performance and significantly enhances the efficiency of strategy determination. Moreover, the deep graph reinforcement learning framework offers a scalable solution, adaptable to various network scenarios and configurations, establishing a robust basis for information security in UAV-enabled communications.

In integrated sensing and communication (ISAC) systems, pilot signals play a crucial role in enhancing sensing performance due to their strong autocorrelation properties and high transmission power. However, conventional interleaved pilots inherently constrain the maximum unambiguous range and reduce the accuracy of channel impulse response (CIR) estimation compared to continuous orthogonal frequency-division multiple access (OFDMA) signals. To address this challenge, we propose a novel overlapped block-pilot structure for uplink OFDMA-based ISAC systems, called phase-shifted ISAC (PS-ISAC) pilot allocation. The proposed method leverages a cyclic prefix (CP)-based phase-shifted pilot design, enabling efficient multi-transmitter pilot separation at the receiver. Simulation results confirm that the proposed scheme enhances CIR separation, reduces computational complexity, and improves mean square error (MSE) performance under practical power constraints. Furthermore, we demonstrate that utilizing continuous pilot resources maximizes the unambiguous range.

Accurate segmentation of lesions plays a critical role in medical image analysis and diagnosis. Traditional segmentation approaches that rely solely on visual features often struggle with the inherent uncertainty in lesion distribution and size. To address these issues, we propose STPNet, a Scale-aware Text Prompt Network that leverages vision-language modeling to enhance medical image segmentation. Our approach utilizes multi-scale textual descriptions to guide lesion localization and employs retrieval-segmentation joint learning to bridge the semantic gap between visual and linguistic modalities. Crucially, STPNet retrieves relevant textual information from a specialized medical text repository during training, eliminating the need for text input during inference while retaining the benefits of cross-modal learning. We evaluate STPNet on three datasets: COVID-Xray, COVID-CT, and Kvasir-SEG. Experimental results show that our vision-language approach outperforms state-of-the-art segmentation methods, demonstrating the effectiveness of incorporating textual semantic knowledge into medical image analysis. The code has been made publicly on https://github.com/HUANGLIZI/STPNet.

Nuclear instance segmentation plays a vital role in disease diagnosis within digital pathology. However, limited labeled data in pathological images restricts the overall performance of nuclear instance segmentation. To tackle this challenge, we propose a novel data augmentation framework Instance Migration Diffusion Model (IM-Diffusion), IM-Diffusion designed to generate more varied pathological images by constructing diverse nuclear layouts and internuclear spatial relationships. In detail, we introduce a Nuclear Migration Module (NMM) which constructs diverse nuclear layouts by simulating the process of nuclear migration. Building on this, we further present an Internuclear-regions Inpainting Module (IIM) to generate diverse internuclear spatial relationships by structure-aware inpainting. On the basis of the above, IM-Diffusion generates more diverse pathological images with different layouts and internuclear spatial relationships, thereby facilitating downstream tasks. Evaluation on the CoNSeP and GLySAC datasets demonstrate that the images generated by IM-Diffusion effectively enhance overall instance segmentation performance. Code will be made public later.

Scaled Relative Graphs (SRGs) provide a novel graphical frequency domain method for the analysis of nonlinear systems. In this paper, we use the restriction of the SRG to particular input spaces to compute frequency-dependent gain bounds for incrementally stable nonlinear systems. This leads to a nonlinear (NL) generalization of the Bode diagram, where the sinusoidal, harmonic, and subharmonic inputs are considered separately. When applied to the analysis of the NL loop transfer and sensitivity, we define a notion of bandwidth for both the open-loop and closed-loop, compatible with the LTI definitions. We illustrate the power of our method on the analysis of a DC motor with a parasitic nonlinearity, verifying our results in simulations.

We establish mathematical bounds on the chain, ABCD and immittance matrices of a multiconductor transmission line, based on the Telegrapher's equation. Closed-form expressions for those matrices are also presented. Existing results that hold on the imaginary axis are extended to the complex plane, without reliance on a simultaneous diagonalizability assumption that is ubiquitous in the literature. Therefore, the results remain valid even when line symmetry breaks down, as in the case of electrical faults. The system-theoretic properties established here are of general relevance to control, power systems, and signal processing involving multiconductor transmission lines.

Spike sorting is a fundamental step in analyzing extracellular recordings, enabling the isolation of individual neuronal activity, yet it remains a challenging problem due to overlapping signals and recording instabilities, including electrode drift. While numerous algorithms have been developed to address these challenges, many struggle to balance accuracy and computational efficiency, limiting their applicability to largescale datasets. In response, we introduce SpikeSift, a novel spike sorting algorithm designed to mitigate drift by partitioning recordings into short, relatively stationary segments, with spikes subsequently sorted within each. To preserve neuronal identity across segment boundaries, a computationally efficient alignment process merges clusters without relying on continuous trajectory estimation. In contrast to conventional methods that separate spike detection from clustering, SpikeSift integrates these processes within an iterative detect-andsubtract framework, enhancing clustering accuracy while maintaining computational efficiency. Evaluations on intracellularly validated datasets and biophysically realistic MEArec simulations confirm that SpikeSift maintains high sorting accuracy even in the presence of electrode drift, providing a scalable and computationally efficient solution for large-scale extracellular recordings

Identifying controlled safety invariant sets (CSISs) is essential in safety-critical applications. This paper tackles the problem of identifying CSISs for black-box discrete-time systems, where the model is unknown and only limited simulation data is accessible. Traditionally, a CSIS is defined as a subset of a safe set, encompassing initial states for which a control input exists that keeps the system within the set at the next time step-this is referred to as the one-step invariance property. However, the requirement for one-step invariance can be equivalently translated into a stricter condition of ``always-invariance'', meaning that there exist control inputs capable of keeping the system within this set indefinitely. Such a condition may prove overly stringent or impractical for black-box systems, where predictions can become unreliable beyond a single time step or a limited number of finite time steps. To overcome the challenges posed by black-box systems, we reformulate the one-step invariance property in a ``Probably Approximately Correct'' (PAC) sense. This approach allows us to assess the probability that a control input exists to keep the system within the CSIS at the next time step, with a predefined level of confidence. If the system successfully remains within the set at the next time step, we can then reapply the invariance evaluation to the new state, thereby facilitating a recursive assurance of invariance. Our method employs barrier functions and scenario optimization, resulting in a linear programming method to estimate PAC CSISs. Finally, the effectiveness of our approach is demonstrated on several examples.

Multivariable parametric models are critical for designing, controlling, and optimizing the performance of engineered systems. The main objective of this paper is to develop a parametric identification strategy that delivers accurate and physically relevant models of multivariable systems using time-domain data. The introduced approach adopts an additive model structure, offering a parsimonious and interpretable representation of many physical systems, and employs a refined instrumental variable-based estimation algorithm. The developed identification method enables the estimation of parametric continuous-time additive models and is applicable to both open and closed-loop controlled systems. The performance of the estimator is demonstrated through numerical simulations and experimentally validated on a flexible beam system.

This paper presents a novel method to optimize thermal balance in parabolic trough collector (PTC) plants. It uses a market-based system to distribute flow among loops combined with an artificial neural network (ANN) to reduce computation and data requirements. This auction-based approach balances loop temperatures, accommodating varying thermal losses and collector efficiencies. Validation across different thermal losses, optical efficiencies, and irradiance conditions-sunny, partially cloudy, and cloudy-show improved thermal power output and intercept factors compared to a no-allocation system. It demonstrates scalability and practicality for large solar thermal plants, enhancing overall performance. The method was first validated through simulations on a realistic solar plant model, then adapted and successfully tested in a 50 MW solar trough plant, demonstrating its advantages. Furthermore, the algorithms have been implemented, commissioned, and are currently operating in 13 commercial solar trough plants.

There is an increasing need for effective control of systems with complex dynamics, particularly through data-driven approaches. System Level Synthesis (SLS) has emerged as a powerful framework that facilitates the control of large-scale systems while accounting for model uncertainties. SLS approaches are currently limited to linear systems and time-varying linear control policies, thus limiting the class of achievable control strategies. We introduce a novel closed-loop parameterization for time-varying affine control policies, extending the SLS framework to a broader class of systems and policies. We show that the closed-loop behavior under affine policies can be equivalently characterized using past system trajectories, enabling a fully data-driven formulation. This parameterization seamlessly integrates affine policies into optimal control problems, allowing for a closed-loop formulation of general Model Predictive Control (MPC) problems. To the best of our knowledge, this is the first work to extend SLS to affine policies in both model-based and data-driven settings, enabling an equivalent formulation of MPC problems using closed-loop maps. We validate our approach through numerical experiments, demonstrating that our model-based and data-driven affine SLS formulations achieve performance on par with traditional model-based MPC.

Hidden Markov Models (HMMs) provide a rigorous framework for inference in dynamic environments. In this work, we study the alpha-HMM algorithm motivated by the optimal online filtering formulation in settings where the true state evolves as a Markov chain with equal exit probabilities. We quantify the dynamics of the algorithm in stationary environments, revealing a trade-off between inference and adaptation, showing how key parameters and the quality of observations affect performance. Comprehensive theoretical analysis on the nonlinear dynamical system that governs the evolution of the log-belief ratio over time and numerical experiments demonstrate that the proposed approach effectively balances adaptation and inference performance.

Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation learning. One common approach to mitigate compounding error is to train multi-step predictors directly, rather than relying on autoregressive rollout of a single-step model. However, it is not well understood when the benefits of multi-step prediction outweigh the added complexity of learning a more complicated model. In this work, we provide a rigorous analysis of this trade-off in the context of linear dynamical systems. We show that when the model class is well-specified and accurately captures the system dynamics, single-step models achieve lower asymptotic prediction error. On the other hand, when the model class is misspecified due to partial observability, direct multi-step predictors can significantly reduce bias and thus outperform single-step approaches. These theoretical results are supported by numerical experiments, wherein we also (a) empirically evaluate an intermediate strategy which trains a single-step model using a multi-step loss and (b) evaluate performance of single step and multi-step predictors in a closed loop control setting.

The increasing global prevalence of mental disorders, such as depression and PTSD, requires objective and scalable diagnostic tools. Traditional clinical assessments often face limitations in accessibility, objectivity, and consistency. This paper investigates the potential of multimodal machine learning to address these challenges, leveraging the complementary information available in text, audio, and video data. Our approach involves a comprehensive analysis of various data preprocessing techniques, including novel chunking and utterance-based formatting strategies. We systematically evaluate a range of state-of-the-art embedding models for each modality and employ Convolutional Neural Networks (CNNs) and Bidirectional LSTM Networks (BiLSTMs) for feature extraction. We explore data-level, feature-level, and decision-level fusion techniques, including a novel integration of Large Language Model (LLM) predictions. We also investigate the impact of replacing Multilayer Perceptron classifiers with Support Vector Machines. We extend our analysis to severity prediction using PHQ-8 and PCL-C scores and multi-class classification (considering co-occurring conditions). Our results demonstrate that utterance-based chunking significantly improves performance, particularly for text and audio modalities. Decision-level fusion, incorporating LLM predictions, achieves the highest accuracy, with a balanced accuracy of 94.8% for depression and 96.2% for PTSD detection. The combination of CNN-BiLSTM architectures with utterance-level chunking, coupled with the integration of external LLM, provides a powerful and nuanced approach to the detection and assessment of mental health conditions. Our findings highlight the potential of MMML for developing more accurate, accessible, and personalized mental healthcare tools.

Real-time optimal control remains a fundamental challenge in robotics, especially for nonlinear systems with stringent performance requirements. As one of the representative trajectory optimization algorithms, the iterative Linear Quadratic Regulator (iLQR) faces limitations due to their inherently sequential computational nature, which restricts the efficiency and applicability of real-time control for robotic systems. While existing parallel implementations aim to overcome the above limitations, they typically demand additional computational iterations and high-performance hardware, leading to only modest practical improvements. In this paper, we introduce Quattro, a transformer-accelerated iLQR framework employing an algorithm-hardware co-design strategy to predict intermediate feedback and feedforward matrices. It facilitates effective parallel computations on resource-constrained devices without sacrificing accuracy. Experiments on cart-pole and quadrotor systems show an algorithm-level acceleration of up to 5.3$\times$ and 27$\times$ per iteration, respectively. When integrated into a Model Predictive Control (MPC) framework, Quattro achieves overall speedups of 2.8$\times$ for the cart-pole and 17.8$\times$ for the quadrotor compared to the one that applies traditional iLQR. Transformer inference is deployed on FPGA to maximize performance, achieving up to 27.3$\times$ speedup over commonly used computing devices, with around 2 to 4$\times$ power reduction and acceptable hardware overhead.

Certifying safety in dynamical systems is crucial, but barrier certificates - widely used to verify that system trajectories remain within a safe region - typically require explicit system models. When dynamics are unknown, data-driven methods can be used instead, yet obtaining a valid certificate requires rigorous uncertainty quantification. For this purpose, existing methods usually rely on full-state measurements, limiting their applicability. This paper proposes a novel approach for synthesizing barrier certificates for unknown systems with latent states and polynomial dynamics. A Bayesian framework is employed, where a prior in state-space representation is updated using input-output data via a targeted marginal Metropolis-Hastings sampler. The resulting samples are used to construct a candidate barrier certificate through a sum-of-squares program. It is shown that if the candidate satisfies the required conditions on a test set of additional samples, it is also valid for the true, unknown system with high probability. The approach and its probabilistic guarantees are illustrated through a numerical simulation.

Non-collocated vibration absorption (NCVA) concept using delayed resonator for in-situ tuning is analyzed and experimentally validated. There are two critical contributions of this work. One is on the scalable analytical pathway for verifying the concept of resonant substructure as the basis of the ideal vibration absorption. The second is to experimentally validate the spatial and spectral tunability of NCVA structures for the first time. For both novelties arbitrarily large dimensions of interconnected mass-spring-damper chains are considered. Following the state of the art on NCVA, control synthesis is performed over the resonant substructure comprising the delayed resonator and a part of the primary structure involved in the vibration absorption. The experimental validation of the proposed NCVA concept is performed on a mechatronic setup with three interconnected cart-bodies. Based on the spectral analysis, an excitation frequency is selected for which a stable vibration suppression can be achieved sequentially for all the three bodies, one collocated and two non-collocated. The experimental results closely match the simulations for complete vibration suppression at the targeted bodies, and thus validating the crucial spatial tunability characteristic as well as the traditional spectral tuning.

Radar-based vital sign monitoring (VSM) systems have become valuable for non-contact health monitoring by detecting physiological activities, such as respiration and heartbeat, remotely. However, the conventional phased array used in VSM is vulnerable to privacy breaches, as an eavesdropper can extract sensitive vital sign information by analyzing the reflected radar signals. In this paper, we propose a novel approach to protect privacy in radar-based VSM by modifying the radar transmitter hardware, specifically by strategically selecting the transmit antennas from the available antennas in the transmit array. By dynamically selecting which antennas connect or disconnect to the radio frequency chain, the transmitter introduces additional phase noise to the radar echoes, generating false frequencies in the power spectrum of the extracted phases at the eavesdropper's receiver. The antenna activation pattern is designed to maximize the variance of the phases introduced by antenna selection, which effectively makes the false frequencies dominate the spectrum, obscuring the actual vital sign frequencies. Meanwhile, the authorized receiver, having knowledge of the antenna selection pattern, can compensate for the phase noise and accurately extract the vital signs. Numerical experiments are conducted to validate the effectiveness of the proposed approach in enhancing privacy while maintaining vital sign monitoring.

Spiking Nonlinear Opinion Dynamics (S-NOD) is an excitable decision-making model inspired by the spiking dynamics of neurons. S-NOD enables the design of agile decision-making that can rapidly switch between decision options in response to a changing environment. In S-NOD, decisions are represented by continuous time, yet discrete, opinion spikes. Here, we extend previous analysis of S-NOD and explore its potential as a nonlinear controller with a tunable balance between robustness and responsiveness. We identify and provide necessary conditions for the bifurcation that determines the onset of periodic opinion spiking. We leverage this analysis to characterize the tunability of the input-output threshold for opinion spiking as a function of the model basal sensitivity and the modulation of opinion spiking frequency as a function of input magnitude past threshold. We conclude with a discussion on S-NOD as a new neuromorphic control block and its extension to distributed spiking controllers.

Mild traumatic brain injuries (mTBI) are a highly prevalent condition with heterogeneous outcomes between individuals. A key factor governing brain tissue deformation and the risk of mTBI is the rotational kinematics of the head. Instrumented mouthguards are a widely accepted method for measuring rotational head motions, owing to their robust sensor-skull coupling. However, wearing mouthguards is not feasible in all situations, especially for long-term data collection. Therefore, alternative wearable devices are needed. In this study, we present an improved design and data processing scheme for an instrumented headband. Our instrumented headband utilizes an array of inertial measurement units (IMUs) and a new data-processing scheme based on continuous wavelet transforms to address sources of error in the IMU measurements. The headband performance was evaluated in the laboratory on an anthropomorphic test device, which was impacted with a soccer ball to replicate soccer heading. When comparing the measured peak rotational velocities (PRV) and peak rotational accelerations (PRA) between the reference sensors and the headband for impacts to the front of the head, the correlation coefficients (r) were 0.80 and 0.63, and the normalized root mean square error (NRMSE) values were 0.20 and 0.28, respectively. However, when considering all impact locations, r dropped to 0.42 and 0.34 and NRMSE increased to 0.5 and 0.41 for PRV and PRA, respectively. This new instrumented headband improves upon previous headband designs in reconstructing the rotational head kinematics resulting from frontal soccer ball impacts, providing a potential alternative to instrumented mouthguards.

Compressed sensing with subsampled unitary matrices benefits from \emph{optimized} sampling schemes, which feature improved theoretical guarantees and empirical performance relative to uniform subsampling. We provide, in a first of its kind in compressed sensing, theoretical guarantees showing that the error caused by the measurement noise vanishes with an increasing number of measurements for optimized sampling schemes, assuming that the noise is Gaussian. We moreover provide similar guarantees for measurements sampled with-replacement with arbitrary probability weights. All our results hold on prior sets contained in a union of low-dimensional subspaces. Finally, we demonstrate that this denoising behavior appears in empirical experiments with a rate that closely matches our theoretical guarantees when the prior set is the range of a generative ReLU neural network and when it is the set of sparse vectors.

We introduce ShieldGemma 2, a 4B parameter image content moderation model built on Gemma 3. This model provides robust safety risk predictions across the following key harm categories: Sexually Explicit, Violence \& Gore, and Dangerous Content for synthetic images (e.g. output of any image generation model) and natural images (e.g. any image input to a Vision-Language Model). We evaluated on both internal and external benchmarks to demonstrate state-of-the-art performance compared to LlavaGuard \citep{helff2024llavaguard}, GPT-4o mini \citep{hurst2024gpt}, and the base Gemma 3 model \citep{gemma_2025} based on our policies. Additionally, we present a novel adversarial data generation pipeline which enables a controlled, diverse, and robust image generation. ShieldGemma 2 provides an open image moderation tool to advance multimodal safety and responsible AI development.

The reinforcement learning (RL) and model predictive control (MPC) communities have developed vast ecosystems of theoretical approaches and computational tools for solving optimal control problems. Given their conceptual similarities but differing strengths, there has been increasing interest in synergizing RL and MPC. However, existing approaches tend to be limited for various reasons, including computational cost of MPC in an RL algorithm and software hurdles towards seamless integration of MPC and RL tools. These challenges often result in the use of "simple" MPC schemes or RL algorithms, neglecting the state-of-the-art in both areas. This paper presents MPCritic, a machine learning-friendly architecture that interfaces seamlessly with MPC tools. MPCritic utilizes the loss landscape defined by a parameterized MPC problem, focusing on "soft" optimization over batched training steps; thereby updating the MPC parameters while avoiding costly minimization and parametric sensitivities. Since the MPC structure is preserved during training, an MPC agent can be readily used for online deployment, where robust constraint satisfaction is paramount. We demonstrate the versatility of MPCritic, in terms of MPC architectures and RL algorithms that it can accommodate, on classic control benchmarks.

Knee-less bipedal robots like SLIDER have the advantage of ultra-lightweight legs and improved walking energy efficiency compared to traditional humanoid robots. In this paper, we firstly introduce an improved hardware design of the bipedal robot SLIDER with new line-feet and more optimized mass distribution which enables higher locomotion speeds. Secondly, we propose an extended Hybrid Zero Dynamics (eHZD) method, which can be applied to prismatic joint robots like SLIDER. The eHZD method is then used to generate a library of gaits with varying reference velocities in an offline way. Thirdly, a Guided Deep Reinforcement Learning (DRL) algorithm is proposed to use the pre-generated library to create walking control policies in real-time. This approach allows us to combine the advantages of both HZD (for generating stable gaits with a full-dynamics model) and DRL (for real-time adaptive gait generation). The experimental results show that this approach achieves 150% higher walking velocity than the previous MPC-based approach.

Many modern robotic systems such as multi-robot systems and manipulators exhibit redundancy, a property owing to which they are capable of executing multiple tasks. This work proposes a novel method, based on the Reinforcement Learning (RL) paradigm, to train redundant robots to be able to execute multiple tasks concurrently. Our approach differs from typical multi-objective RL methods insofar as the learned tasks can be combined and executed in possibly time-varying prioritized stacks. We do so by first defining a notion of task independence between learned value functions. We then use our definition of task independence to propose a cost functional that encourages a policy, based on an approximated value function, to accomplish its control objective while minimally interfering with the execution of higher priority tasks. This allows us to train a set of control policies that can be executed simultaneously. We also introduce a version of fitted value iteration to learn to approximate our proposed cost functional efficiently. We demonstrate our approach on several scenarios and robotic systems.

We consider the problem of assigning tasks efficiently to a set of workers that can exhaust themselves as a result of processing tasks. If a worker is exhausted, it will take a longer time to recover. To model efficiency of workers with exhaustion, we use a continuous-time Markov chain (CTMC). By taking samples from the internal states of the workers, the source assigns tasks to the workers when they are found to be in their efficient states. We consider two different settings where (i) the source can assign tasks to the workers only when they are in their most efficient state, and (ii) it can assign tasks to workers when they are also moderately efficient in spite of a potentially reduced success probability. In the former case, we find the optimal policy to be a threshold-based sampling policy where the thresholds depend on the workers' recovery and exhaustion rates. In the latter case, we solve a non-convex sum-of-ratios problem using a branch-and-bound approach which performs well compared with the globally optimal solution.

This paper presents the Robust Recurrent Deep Network (R2DN), a scalable parameterization of robust recurrent neural networks for machine learning and data-driven control. We construct R2DNs as a feedback interconnection of a linear time-invariant system and a 1-Lipschitz deep feedforward network, and directly parameterize the weights so that our models are stable (contracting) and robust to small input perturbations (Lipschitz) by design. Our parameterization uses a structure similar to the previously-proposed recurrent equilibrium networks (RENs), but without the requirement to iteratively solve an equilibrium layer at each time-step. This speeds up model evaluation and backpropagation on GPUs, and makes it computationally feasible to scale up the network size, batch size, and input sequence length in comparison to RENs. We compare R2DNs to RENs on three representative problems in nonlinear system identification, observer design, and learning-based feedback control and find that training and inference are both up to an order of magnitude faster with similar test set performance, and that training/inference times scale more favorably with respect to model expressivity.

This study explores how human perceptions of a non-anthropomorphic robotic manipulator are shaped by two key dimensions of behaviour: arousal, defined as the robot's movement energy and expressiveness, and attention, defined as the robot's capacity to selectively orient toward and engage with a user. We introduce a novel control architecture that integrates a gaze-like attention engine with an arousal-modulated motion system to generate socially meaningful behaviours. In a user study, we find that robots exhibiting high attention -- actively directing their focus toward users -- are perceived as warmer and more competent, intentional, and lifelike. In contrast, high arousal -- characterized by fast, expansive, and energetic motions -- increases perceptions of discomfort and disturbance. Importantly, a combination of focused attention and moderate arousal yields the highest ratings of trust and sociability, while excessive arousal diminishes social engagement. These findings offer design insights for endowing non-humanoid robots with expressive, intuitive behaviours that support more natural human-robot interaction.

As a medium for cold data storage, DNA stands out as it promises significant gains in storage capacity and lifetime. However, it comes with its own data processing challenges to overcome. Constrained codes over the DNA alphabet $\{A,T,G,C\}$ have been used to design DNA sequences that are free of long homopolymers to increase stability, yet effective error detection and error correction are required to achieve reliability in data retrieval. Recently, we introduced lexicographically-ordered constrained (LOCO) codes, namely DNA LOCO (D-LOCO) codes, with error detection. In this paper, we equip our D-LOCO codes with error correction for substitution errors via syndrome-like decoding, designated as residue decoding. We only use D-LOCO codewords of indices divisible by a suitable redundancy metric $R(m) > 0$, where $m$ is the code length, for error correction. We provide the community with a construction of constrained codes forbidding runs of length higher than fixed $\ell \in \{1,2,3\}$ and $GC$-content in $\big [0.5-\frac{1}{2K},0.5+\frac{1}{2K}\big ]$ that correct $K$ segmented substitution errors, one per codeword. We call the proposed codes error-correction (EC) D-LOCO codes. We also give a list-decoding procedure with near-quadratic time-complexity in $m$ to correct double-substitution errors within EC D-LOCO codewords, which has $> 98.20\%$ average success rate. The redundancy metric is projected to require $2\log_2(m)+O(1)$-bit allocation for a length-$m$ codeword. Hence, our EC D-LOCO codes are projected to be capacity-approaching with respect to the error-free constrained system.

We present Acoustic Inertial Measurement (AIM), a one-of-a-kind technique for indoor drone localization and tracking. Indoor drone localization and tracking are arguably a crucial, yet unsolved challenge: in GPS-denied environments, existing approaches enjoy limited applicability, especially in Non-Line of Sight (NLoS), require extensive environment instrumentation, or demand considerable hardware/software changes on drones. In contrast, AIM exploits the acoustic characteristics of the drones to estimate their location and derive their motion, even in NLoS settings. We tame location estimation errors using a dedicated Kalman filter and the Interquartile Range rule (IQR). We implement AIM using an off-the-shelf microphone array and evaluate its performance with a commercial drone under varied settings. Results indicate that the mean localization error of AIM is 46% lower than commercial UWB-based systems in complex indoor scenarios, where state-of-the-art infrared systems would not even work because of NLoS settings. We further demonstrate that AIM can be extended to support indoor spaces with arbitrary ranges and layouts without loss of accuracy by deploying distributed microphone arrays.

Convex Hull (CH) pricing, used in US electricity markets and raising interest in Europe, is a pricing rule designed to handle markets with non-convexities such as startup costs and minimum up and down times. In such markets, the market operator makes side payments to generators to cover lost opportunity costs, and CH prices minimize the total "lost opportunity costs", which include both actual losses and missed profit opportunities. These prices can also be obtained by solving a (partial) Lagrangian dual of the original mixed-integer program, where power balance constraints are dualized. Computing CH prices then amounts to minimizing a sum of nonsmooth convex objective functions, where each term depends only on a single generator. The subgradient of each of those terms can be obtained independently by solving smaller mixed-integer programs. In this work, we benchmark a large panel of first-order methods to solve the above dual CH pricing problem. We test several dual methods, most of which not previously considered for CH pricing, namely a proximal variant of the bundle level method, subgradient methods with three different stepsize strategies, two recent parameter-free methods and an accelerated gradient method combined with smoothing. We compare those methods on two representative sets of real-world large-scale instances and complement the comparison with a (Dantzig-Wolfe) primal column generation method shown to be efficient at computing CH prices, for reference. Our numerical experiments show that the bundle proximal level method and two variants of the subgradient method perform the best among all dual methods and compare favorably with the Dantzig-Wolfe primal method.

Full-text error correction with Large Language Models (LLMs) for Automatic Speech Recognition (ASR) has gained increased attention due to its potential to correct errors across long contexts and address a broader spectrum of error types, including punctuation restoration and inverse text normalization. Nevertheless, many challenges persist, including issues related to stability, controllability, completeness, and fluency. To mitigate these challenges, this paper proposes the Chain of Correction (CoC) for full-text error correction with LLMs, which corrects errors segment by segment using pre-recognized text as guidance within a regular multi-turn chat format. The CoC also uses pre-recognized full text for context, allowing the model to better grasp global semantics and maintain a comprehensive overview of the entire content. Utilizing the open-sourced full-text error correction dataset ChFT, we fine-tune a pre-trained LLM to evaluate the performance of the CoC framework. Experimental results demonstrate that the CoC effectively corrects errors in full-text ASR outputs, significantly outperforming baseline and benchmark systems. We further analyze how to set the correction threshold to balance under-correction and over-rephrasing, extrapolate the CoC model on extremely long ASR outputs, and investigate whether other types of information can be employed to guide the error correction process.

Driven by the growing demand for intelligent remote sensing applications, large artificial intelligence (AI) models pre-trained on large-scale unlabeled datasets and fine-tuned for downstream tasks have significantly improved learning performance for various downstream tasks due to their generalization capabilities. However, many specific downstream tasks, such as extreme weather nowcasting (e.g., downburst and tornado), disaster monitoring, and battlefield surveillance, require real-time data processing. Traditional methods via transferring raw data to ground stations for processing often cause significant issues in terms of latency and trustworthiness. To address these challenges, satellite edge AI provides a paradigm shift from ground-based to on-board data processing by leveraging the integrated communication-and-computation capabilities in space computing power networks (Space-CPN), thereby enhancing the timeliness, effectiveness, and trustworthiness for remote sensing downstream tasks. Moreover, satellite edge large AI model (LAM) involves both the training (i.e., fine-tuning) and inference phases, where a key challenge lies in developing computation task decomposition principles to support scalable LAM deployment in resource-constrained space networks with time-varying topologies. In this article, we first propose a satellite federated fine-tuning architecture to split and deploy the modules of LAM over space and ground networks for efficient LAM fine-tuning. We then introduce a microservice-empowered satellite edge LAM inference architecture that virtualizes LAM components into lightweight microservices tailored for multi-task multimodal inference. Finally, we discuss the future directions for enhancing the efficiency and scalability of satellite edge LAM, including task-oriented communication, brain-inspired computing, and satellite edge AI network optimization.

In this paper, we propose an adaptive proximal inexact gradient (APIG) framework for solving a class of nonsmooth composite optimization problems involving function and gradient errors. Unlike existing inexact proximal gradient methods, the proposed framework introduces a new line search condition that jointly adapts to function and gradient errors, enabling adaptive stepsize selection while maintaining theoretical guarantees. Specifically, we prove that the proposed framework achieves an $\epsilon$-stationary point within $\mathcal{O}(\epsilon^{-2})$ iterations for nonconvex objectives and an $\epsilon$-optimal solution within $\mathcal{O}(\epsilon^{-1})$ iterations for convex cases, matching the best-known complexity in this context. We then custom-apply the APIG framework to an important signal processing problem: the joint beamforming and compression problem (JBCP) with per-antenna power constraints (PAPCs) in cooperative cellular networks. This customized application requires careful exploitation of the problem's special structure such as the tightness of the semidefinite relaxation (SDR) and the differentiability of the dual. Numerical experiments demonstrate the superior performance of our custom-application over state-of-the-art benchmarks for the JBCP.

Synthetic aperture radar (SAR) data processing is crucial for high-resolution Earth observation and remote sensing applications, one of the most commonly used algorithms for this task is the Range Doppler Algorithm (RDA). Using the Fast Fourier Transform (FFT), the collected signal is transformed to the frequency domain and then goes through the processing steps of this algorithm. However, when it comes to large datasets, this process can be computationally expensive. This paper explores the implementation of a Quantum Range Doppler Algorithm (QRDA), relying on the Quantum Fourier Transform (QFT) as a speedup tool over the classical FFT. Additionally, it proposes a quantum version of the Range Cell Migration Correction (RCMC) in the Fourier domain, one of the key correctional steps of the RDA algorithm, and compares it with its classical counterpart.

Trajectory prediction of other vehicles is crucial for autonomous vehicles, with applications from missile guidance to UAV collision avoidance. Typically, target trajectories are assumed deterministic, but real-world aerial vehicles exhibit stochastic behavior, such as evasive maneuvers or gliders circling in thermals. This paper uses Conditional Normalizing Flows, an unsupervised Machine Learning technique, to learn and predict the stochastic behavior of targets of guided missiles using trajectory data. The trained model predicts the distribution of future target positions based on initial conditions and parameters of the dynamics. Samples from this distribution are clustered using a time series k-means algorithm to generate representative trajectories, termed virtual targets. The method is fast and target-agnostic, requiring only training data in the form of target trajectories. Thus, it serves as a drop-in replacement for deterministic trajectory predictions in guidance laws and path planning. Simulated scenarios demonstrate the approach's effectiveness for aerial vehicles with random maneuvers, bridging the gap between deterministic predictions and stochastic reality, advancing guidance and control algorithms for autonomous vehicles.

We develop a novel source coding strategy for sampling and monitoring of a Wiener process. For the encoding process, we employ a four level ``quantization'' scheme, which employs monotone function thresholds as opposed to fixed constant thresholds. Leveraging the hitting times of the Wiener process with these thresholds, we devise a sampling and encoding strategy which does not incur any quantization errors. We give analytical expressions for the mean squared error (MSE) and find the optimal source code lengths to minimize the MSE under this monotone function threshold scheme, subject to a sampling rate constraint.

In telecommunications, Autonomous Networks (ANs) automatically adjust configurations based on specific requirements (e.g., bandwidth) and available resources. These networks rely on continuous monitoring and intelligent mechanisms for self-optimization, self-repair, and self-protection, nowadays enhanced by Neural Networks (NNs) to enable predictive modeling and pattern recognition. Here, Federated Learning (FL) allows multiple AN cells - each equipped with NNs - to collaboratively train models while preserving data privacy. However, FL requires frequent transmission of large neural data and thus an efficient, standardized compression strategy for reliable communication. To address this, we investigate NNCodec, a Fraunhofer implementation of the ISO/IEC Neural Network Coding (NNC) standard, within a novel FL framework that integrates tiny language models (TLMs) for various mobile network feature prediction (e.g., ping, SNR or band frequency). Our experimental results on the Berlin V2X dataset demonstrate that NNCodec achieves transparent compression (i.e., negligible performance loss) while reducing communication overhead to below 1%, showing the effectiveness of combining NNC with FL in collaboratively learned autonomous mobile networks.