Papers

We study the restless contextual multi-play multi-armed bandit (MP-MAB) problem for channel allocation in the opportunity spectrum access (OSA) scenario. Most existing MP-MAB methods are impractical for real-world OSA systems as they assume many ideal conditions, incur a heavy computational cost, and most importantly, ignore the impact of channel noise which is directly related to the quality of service. In this study, we embody this impact by modeling channel noise as a perturbation of the arm's reward function in MP-MAB. As there is an implicit correlation between channel state information and channel noise, we take the former as a context for MP-MAB to present the perturbation caused by the latter. We investigate two types of correlation between the context and the perturbation – linear and nonlinear, and derive two index policies, respectively. These policies learn the correlations through a linear model and a neural network, and use estimated noise value to adjust the upper confidence bound. Numerical experiments demonstrate that the proposed policies can achieve lower regret and select sub-optimal arms in a more reasonable way.

Low-dose computed tomography (LDCT) reconstruction faces a critical tradeoff between reconstruction quality and resource requirements. While recent deep learning methods achieve state-of-the-art performance, they typically rely on over 500,000 parameters trained on large-scale datasets exceeding 35,000 scans. This work investigates whether graph-based regularization can provide meaningful noise reduction under strict resource constraints. We propose Deep Graph Laplacian Regularization (Deep GLR), integrating quadratic graph regularization into a Proximal Forward-Backward Splitting optimization framework with three lightweight CNN modules. Evaluated on the LoDoPaB-CT benchmark, Deep GLR achieves 30.70 dB PSNR, representing a 6.33 dB improvement over filtered backprojection, while using only 91,848 parameters trained on 1000 samples (2.8% of standard training set). Compared to benchmark methods, this represents 5.8 times better parameter efficiency and 30 times better data efficiency per dB improvement. The learned graph bandwidth parameter ($\epsilon$=1.25) converges to interpretable values, suggesting the method captures meaningful image priors rather than overfitting. While a 13 dB gap remains versus state-of-the-art methods, results demonstrate that graph-based regularization provides a favorable efficiency-quality tradeoff for resource-constrained medical imaging scenarios.

Neural network (NN) dynamics models and control policies achieve strong performance in robotics, but providing sound guarantees under uncertainty remains difficult, especially for closed-loop NN systems. Existing reachability tools provide formal over-approximations, yet are often non-differentiable, overly conservative, or too slow for modern learning and online planning pipelines. To address this, we present a parallelizable, differentiable reachability framework in JAX for continuous- and discrete-time systems with analytical and NN-based dynamics and controllers. Our framework combines Taylor-model flowpipe construction with CROWN-style linear bound propagation through a unified representation that preserves affine dependencies while supporting GPU-batched computation and automatic differentiation. Building on this reachability primitive, we develop (i) a certified training method that encourages reachability-friendly dynamics models and controllers, and (ii) a reachability-aware sampling-based MPC scheme with gradient-based refinement. Experiments on non-prehensile manipulation and quadrotor tasks, including hardware and higher-dimensional evaluations (up to 72D), demonstrate practical online planning while maintaining certified reachable-set over-approximations under bounded uncertainty.

Heterogeneous Internet of Things (IoT) systems suffer from fragmentation across hardware architectures, networking stacks, and data serialization formats. Existing standards (such as MQTT, COAP, and DDS) rely on address-bound, imperative routing models that require hardcoded configurations and leave no flexibility for runtime schema translation. This paper presents TIP (The Intent Protocol), a decentralized, declarative network protocol. Instead of addressing specific physical endpoints, nodes submit abstract intents specifying desired capabilities, schemas, and Quality of Service (QoS) constraints. The TIP Engine resolves matching nodes using a hybrid discovery mechanism combining local multicast DNS (mDNS) with Kademlia Distributed Hash Tables (DHT). Selection is optimized via a multi-criteria scoring algorithm incorporating network latency, historical reputation, and contract compliance. Mismatched data representations are reconciled on-the-fly inside isolated WebAssembly (WASM) sandboxes compiled dynamically from TOML specifications. Security is enforced through Ed25519 signatures, X25519 key exchanges, and ChaCha20-Poly 1305 payload encryption. Evaluation of our reference implementation in Rust and C++ shows sub-millisecond translation overhead and robust resilience under industrial conditions.

In UAV-to-UAV communication, airborne UAVs need to detect the location and direction of ultra-high-speed millimeter-wave (mmWave) and Terahertz (THz) coverage areas, referred to as ultra-spots. This predictive capability allows UAVs to optimally adjust their flight paths, altitude, and velocity, thereby maximizing the utilization of ultra-spot services. A space-time synchronization technique employing multiple Wireless Two-way Interferometry devices (multi-Wi-Wi) is proposed in this paper to detect mmWave/THz ultra-spot locations during UAV operations. This paper proposes an algorithm that estimates the likelihood of nearby ultra-spots by considering the UAV flight route and ultra-spot direction, and by sharing location and pose information among UAVs in the network via a 920 MHz wireless communication link. For the first time, this work addresses the problem of optimizing UAV flight routes to maximize ultra-spot utilization. To address the inherent challenges of Wi-Wi, such as phase data unreliability, RSSI attenuation, or packet loss caused by obstructions from the UAV's own body, this study proposes the use of multiple Wi-Wi devices equipped with antennas positioned at different positions around the arms of the UAV to leverage spatial diversity effects. The proposed method's effectiveness is confirmed through experimental data derived from real-world UAV-to-UAV communication tests. An error of 37.16 cm was observed experimentally in ultra-spot location estimation, corresponding to 186 ms error in temporal prediction of ultra-spot entry from an in-flight UAV, demonstrating its effectiveness in addressing ultra-spot detection challenges in mmWave communication.

Power flow feasibility assessment is computationally challenging for unbalanced three-phase distribution networks. This paper develops a vectorized semidefinite program (SDP) based on the bus injection model (BIM) and reformulates its dual as an exact-penalty problem, enabling us to develop a scalable three-cut proximal bundle method for feasibility assessment. The proposed bundle method is numerically over 400 times faster than MOSEK with less than 1/2000 of its memory; on the decomposed BIM-SDP, approximately 2 times faster with 75% less memory.

This paper presents an efficient implementation of the extended object Poisson multi-Bernoulli (PMB) filter under the zero-inflated Poisson (ZIP) object measurement model using particle belief propagation (BP). The ZIP measurement model separates a Bernoulli object detection event from the conditional Poisson generation of object measurements, enabling principled handling of empty measurement sets. Building upon the PMB mixture posterior, we present a factorized joint posterior over set of objects with object detection variables and a dual representation of data association using both object-oriented and measurement-oriented association variables. Notably, this representation replaces the implicit high-order global hypothesis constraint by local consistency factors, yielding a factor graph amenable to BP. In addition, we present a particle-based implementation, where the single object densities of Bernoulli components are represented using particles. Simulation results show that the proposed method achieves filtering performance comparable to a sampling-based PMBM implementation, while having lower runtime. We also validate the efficacy of the proposed method using real-world lidar data for pedestrian tracking.

This letter studies distributed stochastic optimization over a peer-to-peer network when agents can query only zeroth-order function values. We propose ZOOM-PB, a coordinate-sampling method that blends each local ZO estimate with a fractional-power response while maintaining only a primal state. The raw estimate is retained as a linear anchor, and the nonlinear mixing weight is coupled to the optimization stepsize. This design is motivated by a basic obstruction: transforming heterogeneous or noisy local estimates before averaging can reverse the network direction. We bound that nonlinear residual directly from the raw oracle assumptions instead of imposing an aggregate-alignment condition. With a smooth stochastic-function oracle and a connected graph, ZOOM-PB attains the nonconvex stationarity order $\mathcal{O}(\sqrt{p/(nT)})$ and a Polyak–Łojasiewicz statistical term of order $\mathcal{O}(p/(nT))$, after an explicit initialization transient. Numerical examples compare ZOOM-PB with seven distributed ZO baselines under matched query and message budgets.

Convolutional neural receivers such as DeepRx outperform minimum mean-square error physical uplink shared channel detection on in distribution channel and waveform configurations, but their behavior under calibration drift when transmitter or channel parameters depart from the training envelope is poorly characterized.

Understanding the statistics of level crossings in stochastic processes is crucial across many scientific disciplines. The traditional Kac-Rice formula gives the mean rate of level crossings and has found broad use. However, that mean rate captures only a coarse summary of the crossing process. It depends entirely on local properties of the stochastic process at a given instant and is therefore blind to the correlation structure of the process over time. To understand whether crossing events, such as neuronal spikes, tend to cluster in time, spread apart, or exhibit more complex temporal organization, one must go beyond the mean rate and study higher-order crossing statistics. Here we go beyond the mean by deriving the exact analytical formulae for the variance and Fano factor of arbitrary level crossings in smooth stationary Gaussian processes. Our exact solution reveals how the full temporal correlation structure dictates whether crossings cluster or become regular. In systems with oscillatory correlations, such as a stochastic damped harmonic oscillator, a recent crossing suppresses an immediate subsequent one, producing sub-Poissonian statistics. However, as damping increases and oscillations disappear, a large and slow excursion above the threshold can produce multiple closely spaced crossings, yielding super-Poissonian statistics. In purely relaxational, non-oscillatory systems, such as a mean-reverting process driven by Ornstein-Uhlenbeck noise, the competition between the timescales of the driving noise and system relaxation produces a richer landscape, including reentrant transitions between sub- and super-Poissonian statistics as the threshold level is varied. Taken together, the exact variance and Fano factor derived here complement the Kac-Rice mean rate, enabling more robust parameter estimation and model selection across any setting where Gaussian processes are used.

We present FusionCore, an open-source ROS 2 sensor fusion package that fuses IMU, wheel encoder odometry, GPS, and Visual SLAM pose into a single 100 Hz odometry stream using a 23-state Unscented Kalman Filter (UKF). The 23rd state is an online estimate of the wheel encoder's systematic yaw rate bias, identified through GPS heading cross-covariance and subtracted during GPS blackouts to reduce heading drift in coast mode. FusionCore also estimates gyroscope and accelerometer biases as explicit filter states, handles GPS natively in ECEF without a separate coordinate projection node, applies per-sensor Mahalanobis chi-squared outlier gating calibrated to measurement degrees of freedom, and adapts sensor noise covariance automatically from the innovation sequence. VSLAM pose fusion enables GPS-denied operation with any visual odometry or SLAM system, including automatic recovery from map reinitialization. We evaluate against robot_localization on twelve full-length sequences (55-92 min each) from the NCLT public dataset. FusionCore achieves lower Absolute Trajectory Error (ATE) on ten of twelve sequences, with improvements ranging from 1.2x to 22.2x on winning sequences. The robot_localization UKF diverges numerically on all twelve sequences. FusionCore is available at https://github.com/manankharwar/fusioncore under the Apache 2.0 license.

This paper presents a backstepping approach for the boundary control of first-order hyperbolic equations with spatially varying coefficients posed on domains of arbitrary dimension. The method is based on a change of variables induced by the characteristic flow of the time-invariant transport operator, transforming the original multidimensional system into a continuum of decoupled one-dimensional hyperbolic equations evolving along individual characteristic curves. A backstepping controller is then designed for each equation in the decomposition, and the resulting control laws are reassembled in the original coordinates to achieve finite-time stabilization of the full system. The framework relies on the existence of characteristic curves foliating the spatial domain, with uniformly bounded transit times (non-trapping).

Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically dispersed FL systems, such as sensor networks in remote areas, unmanned aerial vehicles (UAVs) can flexibly establish high-quality communication links to support parameter exchange. However, device heterogeneity and the limited battery capacity of UAVs pose significant challenges. Specifically, data heterogeneity slows convergence, while scheduling all devices for global collaboration incurs excessive communication and energy costs. To overcome these challenges, we adopt a strict separation between a globally shared backbone and permanently local personalization heads, thereby mitigating the impact of data heterogeneity. Furthermore, we propose a gradient-based scheduling strategy that jointly considers energy efficiency and learning performance. In each communication round, the backbone is updated only by the top-$\alpha$ devices ranked by gradient $\ell_{2}$-norm, ensuring that optimization focuses on the most informative updates. Simulation results demonstrate that the proposed scheme achieves higher learning accuracy than state-of-the-art approaches while significantly reducing UAV energy consumption.

This study presents a methodology for constructing a clinically verified dataset of dermatoscopic images for medical informatics research. The relevance of the work is driven by the fact that the performance of automated diagnostic support systems depends not only on the volume of images, but also on the reproducibility of the image acquisition procedure, the completeness of structured metadata, and the reliability of diagnostic labels. International collections were primarily created under conditions that differ substantially from routine Russian outpatient practice and mobile dermatoscopy. The proposed methodology integrates three interconnected components: (1) a standard operating procedure (SOP) for acquiring images via mobile dermatoscopy, (2) an information model comprising 16 structured metadata fields organized into six clinically oriented blocks in ISIC-compatible notation, and (3) a multi-stage expert verification of diagnostic labels (initial clinical annotation, consensus review by three specialists, and histological confirmation of all malignant neoplasms). Using this methodology, a dataset of 1,026 unique dermatoscopic images from 443 patients was collected between June 2025 and May 2026. From 1,044 initial records, 18 duplicates were excluded. The dataset includes nine nosological categories; all 39 malignant lesions (18 melanomas, 15 basal cell carcinomas, and 6 squamous cell carcinomas) were histologically verified. Patient age ranged from 2 to 90 years (median 38), with 279 females (63%) and 164 males (37%). Each image is accompanied by expert-annotated dermatoscopic structures and an explicit verification_stage field indicating the level of diagnostic confirmation. The resulting dataset serves as a pilot clinically verified resource suitable for independent model evaluation, domain shift analysis, interpretability studies, and further expansion.

In this work, we study the interface of the Brazilian e-Voting Machine (BVM) in the context of electromagnetic side-channel threats commonly referred to as TEMPEST attacks. In a TEMPEST attack against video displays, an eavesdropper uses Software-Defined Radios (SDRs) to recover sensitive information by intercepting electromagnetic emanations generated during video signal transmission. We emulate the BVM using a VGA monitor by leveraging publicly available information disclosed by the electoral authority, including technical specifications, operational rules of the system, and the official BVM interface. Based on this setup, we investigate whether the BVM interface gives rise to a distinctive spectral signature observable through its unintended electromagnetic emissions. Our findings show that design characteristics relevant to a nationwide electoral process – such as high image contrast, minimal on-screen information, and the prohibition of other electronic devices within the polling station – result in a simple and highly distinctive spectral signature that can be observed even through a wall in our experiments. Although our experiments do not involve actual BVM hardware, the results raise concerns regarding the system's susceptibility to TEMPEST attacks and highlight the need for further research on protective countermeasures. In this context, our findings may support the design of automatic jammers capable of adaptively targeting compromising frequencies. To the best of our knowledge, this is the first study investigating TEMPEST attacks in the context of an electronic voting system officially adopted by a country.

Ultrasound computed tomography is emerging as a promising safe and accessible modality for soft-tissue medical imaging, with full waveform inversion playing a key role in unlocking its full potential for high-resolution, quantitative reconstructions. Frequency domain full waveform inversion (FDFWI) for reconstructing spatial maps of acoustic properties in the musculoskeletal system is highly sensitive to the quality of low-frequency signals, making the final imaging outcome vulnerable to issues such as inappropriate initial models and strong scatterings related to bones. To address these challenges, we propose a hybrid full waveform inversion (HFWI) algorithm that incorporates a traveltime inversion algorithm based on the generalized Rytov approximation into the FDFWI framework. This hybrid strategy enhances early-stage inversion quality and substantially reduces sensitivity to the initial model, all while maintaining computational efficiency. Importantly, HFWI achieves results comparable to those obtained using well-constructed initial models, without incurring extra computational cost, thus enabling accurate imaging under realistic, bandwidth-limited conditions. In addition, we introduce a near real-time strategy to update first-arrival traveltimes based on forward-scattered phase variations without requiring extra wavefield simulations. Numerical simulations, as well as in vitro and in vivo experiments confirm the robustness and efficiency of the proposed approach. HFWI also shows promise to extend to more complex scenarios of musculoskeletal parametric reconstruction.

The sub-terahertz frequency band offers extremely large bandwidth and enables ultra-high data rates for future wireless applications. However, severe propagation loss and blockage significantly limit coverage at these frequencies. Reconfigurable intelligent surfaces can dynamically shape EM wave propagation and provide a promising solution for coverage enhancement. Realizing such surfaces using standard printed circuit board technology is attractive due to its low cost and scalability, but it remains challenging around 100 GHz because of fabrication limits, limited switch availability, large switch size compared with the unit cell, switch parasitic effects, and high control complexity. In this work, we demonstrate a wideband PCB-based reconfigurable intelligent surface operating around 100 GHz. The design combines an orthogonal-polarization slot-coupled patch structure with subarray partitioning to mitigate switch-induced parasitic effects, reduce the required number of RF switches, and simplify the control architecture. The reconfigurability is achieved using AlGaAs SP3T bare-die switches integrated through optimized bond-wire interconnections. For proof of concept, a six-subarray structure with 4 by 4 elements per subarray is designed for different beamforming angles, and a 12 by 8 prototype is fabricated and experimentally characterized. The measured results show a gain enhancement of about 10 dB from 86 to 100 GHz and about 5 dB from 100 to 106 GHz, while maintaining a low power consumption of 0.165 W. These results validate the feasibility of practical wideband PCB-based reconfigurable intelligent surfaces for sub-terahertz wireless systems.

This work presents the experimental validation of a turbidostat strategy for biomass control in a semi-industrial outdoor raceway reactor. The proposed approach regulates biomass concentration by automatically triggering dilution when the online biomass estimate exceeds a predefined threshold. To ensure safe outdoor operation, dilution was restricted to daylight periods, avoiding biomass removal under low-radiation conditions. The strategy was implemented through an industrial control architecture using an optical monitoring system for online biomass estimation. Experiments were conducted over 14 consecutive days in an 80 m$^2$ (12000 L) raceway reactor. A second parallel reactor operated in chemostat mode, with a nominal dilution of 20 % of the total volume during operating days, provided contextual information under the same outdoor conditions. The analysis focuses on the ability of the sensor-based strategy to configure and maintain the desired biomass concentration, rather than on a direct reactor-to-reactor performance ranking. During the campaign, the biomass threshold in the turbidostat reactor was changed from 1.0 to 0.8 g L$^{-1}$, demonstrating the flexibility enabled by online biomass monitoring. Excluding initial adjustment and transition days, harvested areal productivity increased from 9.52 to 23.20 g m$^{-2}$ d$^{-1}$ after reducing the operating threshold. The overall biomass balance also showed higher net areal productivity in the turbidostat reactor, reaching 20.34 g m$^{-2}$ d$^{-1}$ compared with 11.16 g m$^{-2}$ d$^{-1}$ in the parallel chemostat reactor. These results demonstrate the feasibility of robust turbidostat-based biomass control in large-scale outdoor raceway photobioreactors.

Thin-layer photobioreactors (TLRs) exhibit fast hydrodynamic and thermal dynamics, strong nonlinear photosynthetic responses and significant time-variability due to irradiance fluctuations and biomass growth. These characteristics challenge conventional model-based control strategies, whose tuning degrades under rapidly changing operating conditions. This work presents the experimental implementation of a model-free control approach, Extremum Seeking Control (ESC), for performance optimization in a semi-industrial thin-layer photobioreactor. Unlike previous studies in raceway ponds, the reduced hydraulic inertia of TLR systems enables the adaptation of this control strategy to accelerate convergence while preserving gradient estimation accuracy. The proposed approach is experimentally compared against classical on-off control and ESC configurations with and without feedforward compensation of solar irradiance. Beyond control performance metrics, biological indicators such as biomass concentration and productivity are evaluated to assess the impact on process efficiency. Results show that the proposed ESC strategy reduced cumulative CO$_2$ consumption by approximately 39 % and decreased the accumulated pH tracking error by more than 60 % compared with conventional on-off control, while biomass- and irradiance-normalised indicators confirmed a more efficient use of injected carbon. These results demonstrate that high-frequency ESC can improve regulation performance and carbon utilisation efficiency in fast photobioreactor systems, highlighting its suitability for thin-layer cultivation under outdoor conditions.

In many industrial domains, the Functional Mock-up Interface (FMI) is used to exchange simulation models as Functional Mock-up Units (FMUs) across different partners using various modelling tools. This opens up the possibilities for simulation-based verification and validation using FMUs for ensuring reliable system behaviour. However, deriving effective test oracles for these simulation models remains challenging due to the absence of explicit expected outputs. This limits the applicability of conventional testing approaches, which require access to the internal workings of the systems. Metamorphic testing (MT) addresses this limitation by leveraging metamorphic relations (MRs), but extracting such relations from specifications remains largely a manual and error-prone process. To address this challenge, we propose an LLM-powered multi-agent workflow for specification-based metamorphic testing of FMU-based simulation models. The approach takes functional and interface specifications as input and orchestrates multiple agents to extract requirements and derive MRs. These MRs are expressed using Given-When-Then patterns to structure input conditions (Given), transformations (When), and expected output behaviours (Then). These relations are then used to generate metamorphic test cases, execute simulations, and evaluate output consistency across multiple sessions. We evaluate the approach on a Lube Oil Cooling system FMU, demonstrating its ability to automatically generate meaningful MRs and corresponding test cases. Preliminary results indicate that the proposed workflow can effectively support the systematic verification and validation of dynamic simulation models by reducing manual effort and improving test generation.

Automatic modulation classification (AMC) is an essential technique for noncooperative spectrum monitoring and intelligent wireless receivers. However, practical AMC models must identify modulation formats from short and noisy I/Q observations while maintaining low computational and storage overhead. Existing deep-learning approaches often improve recognition accuracy by expanding generic neural backbones, which increases deployment cost and weakens their suitability for resource-constrained receivers. To bridge the gap between recognition performance and model efficiency, this letter proposes a Complex Subband Phase-Motion Network, designated as CSPMNet, for lightweight AMC from raw I/Q samples. Specifically, learnable complex subband filters are introduced to adaptively extract frequency-selective baseband responses while preserving the algebraic coupling between in-phase and quadrature components. Then, an amplitude-preserving phase-motion module captures multi-lag temporal rotation dynamics within each subband, and a lightweight temporal classifier performs efficient sequence aggregation. Rigorous experimental evaluations on public RadioML benchmark datasets demonstrate that CSPMNet achieves highly competitive recognition accuracy while requiring substantially lower model complexity than many existing AMC models.

This paper considers a safe trajectory tracking of the Stefan problem with a second-order moving boundary dynamics. The model is given by a parabolic Partial Differential Equation (PDE) defined on a time-varying domain of moving boundary governed by a second-order Ordinary Differential Equation (ODE) associated with the Neumann boundary condition. A feedforward control is designed by a series expansion approach to solve the inverse Stefan problem under given reference trajectory of the moving boundary, and the convergence of infinite series is proven. A trajectory tracking controller is derived based on an energy-shaping, which ensures the safety of the model constraint in the closed-loop system. The closed-loop system is also shown to be globally exponentially stable with respect to the tracking error by performing PDE backstepping transformation and Lyapunov analysis. Numerical simulation illustrates an effective tracking performance of the proposed method under a sinusoidal reference trajectory. Code is released at https://github.com/shumon0423/StefanTracking_ACC2026.git.

We propose a semi-analytical design framework for amplitude phase shift keying (APSK) signaling for integrated sensing and communication (ISAC), focusing on i.i.d. uniform discrete input distributions for practicality and analytical tractability. First, we establish APSK design criteria in which communication performance is measured by the gap to capacity and linked to the minimum Euclidean distance, while sensing performance is characterized by the symbol-energy variance. Based on these criteria, we develop a structured APSK construction whose key parameters follow explicit scaling laws. Then we prove that this construction achieves a constant gap to capacity independent of the signal-to-noise ratio. Building upon this foundation, we further construct a parametric APSK family that bridges the communication-optimal and sensing-optimal designs, with the communication and sensing (C&S) tradeoff controlled by the number of rings and energy allocation among rings. Simulation results show that the resulting APSK family achieves C&S performance very close to the Pareto boundary achieved with time-independent, circularly symmetric, and otherwise unconstrained continuous input distributions.

Coordinating micro-robotic swarms in realistic, time-dependent fluid environments remains a major challenge for biomedical and environmental applications. We present a hybrid CFD-MO-MARL (Computational Fluid Dynamics-Multi Objective-Multi Agent Reinforcement Learning) framework that couples a high-fidelity incompressible Navier–Stokes solver with decentralized proximal policy optimization to learn swarm control policies in oscillatory flow. Sixteen magnetically actuated micro-robots were simulated to navigate a pulsatile arterial waveform within a 2 mm channel while jointly optimizing upstream progression, energy efficiency, and motion smoothness. Conflicting objectives are resolved using Projected Conflicting Gradient (PCGrad) surgery. Without PCGrad, energy and smoothness rewards collapse during training, demonstrating that gradient conflict resolution is essential for stable multi-objective learning. The converged policy achieves progress rewards of 6.5-7.0, energy efficiency of 0.63-0.65, and smoothness of 0.97-0.99, outperforming brute-force baselines by more than 8 reward units on the primary objective. Training reveals three emergent behaviors not encoded in the reward function: hydrodynamic throttling formations that reduce peak flow velocities, a cycle-synchronized ratchet mechanism that exploits flow reversals for upstream movement, and individualized final-approach strategies near the target boundary. These results demonstrate that physically realistic fluid–agent interactions can be integrated directly into multi-objective reinforcement learning, providing a scalable framework for micro-swarm control in biomedical navigation, environmental monitoring, and microfluidic systems.

While highway automation is advancing rapidly, road operators still lack practical methods to assess the readiness of their infrastructures for supporting automated driving systems. This work proposes a quantitative Highway Readiness Index (HRI) that maps static Operational Design Domain (ODD) infrastructure conditions into measurable attributes and weights them through an expert survey to evaluate readiness across Society of Automotive Engineers (SAE) automation levels. A real corridor case study shows how HRI scores can be computed, interpreted, and used to identify infrastructure gaps that limit higher automation. Finally, we outline how these indicators can be integrated into a standardized Cooperative Intelligent Transport System (C-ITS) message, i.e., Infrastructure-to-Vehicle Information Message (IVIM), to communicate segment-level automation guidance to connected vehicles.

This paper presents a comparative study of four potential operating configurations for distributed cell-free massive multiple-input multiple-output (CF-mMIMO) ISAC, spanning separated (SE) and shared (SH) access point (AP) deployment with half-duplex (HD) and full-duplex (FD) paradigms. The system comprises distributed APs serving multiple downlink (DL) and uplink (UL) users while simultaneously detecting radar targets. The configurations incorporate realistic impairments at the AP receivers: residual self-interference (SI) from transmit–receive leakage under FD operation, imperfect interference cancellation (IC) of the known radar and DL waveforms due to channel-estimation errors, and environmental clutter. To establish a common analytical scale for communication and sensing, the Kullback–Leibler divergence (KLD) is adopted as a unifying measure that represents both subsystems in comparable quantities, thereby enabling consistent comparison between error-rate and detection metrics. A generalised likelihood ratio test (GLRT) framework is developed, yielding closed-form expressions that link the KLD to the detection probability. Our results confirm the derived KLD-to-symbol error rate (SER) and KLD-to-detection links: with adequate SI suppression and IC quality, FD attains substantial communication gains over HD while preserving strong radar detection, and SH deployment raises both communication and radar performance through its larger effective aperture, though its radar gain then depends on cancellation quality, which SE deployment avoids by isolating the subsystems. These trends persist under imperfect channel state information (CSI) and sensing estimation, and a complexity analysis attributes the SH deployment and FD gains to a higher per-configuration processing cost, yielding deployment guidelines and quantitative design thresholds for next-generation CF-mMIMO ISAC systems.

Body area networks (BANs) require lightweight session key establishment, yet public key exchange imposes computation and energy costs that exceed the budgets of deeply constrained wearable nodes. This brief presents HHK, a hardware-oriented cross-location photoplethysmography (PPG) key generation architecture for BANs. The proposed datapath extracts inter-beat intervals (IBIs) from green-light PPG at multiple body sites, aligns beat timestamps across locations, applies Gray-coded equal-frequency quantization, and employs a rate-1/3 polar code fuzzy commitment (N=128, K=42) to reconcile residual timing mismatches. Post-implementation synthesis on a Xilinx XC7Z020 maps the complete datapath to 18,760 lookup tables and 20,971 flip-flops with no multipliers or embedded memories, giving 48 uJ per key generation event and 0.4 uW average power over a 120-second acquisition window. Validation across 16 participants from a real ambulatory dataset (216 hours; head, wrist, and ankle) yields 86.0-90.1% raw IBI bit agreement and 51.3-69.8% key agreement. To the best of our knowledge, HHK is the first synthesizable register-transfer level (RTL) key generation architecture for BANs validated across multiple body locations on ambulatory data.

We propose a lattice-theoretic framework for modulo sampling of multidimensional bandlimited signals. Standard modulo analog-to-digital converters (ADCs) fold the signal component-wise into a square domain, reducing the recovery problem to independent one-dimensional problems. We extend the recovery guarantees to any lattice, requiring the same sampling rate as in the standard component-wise modulo setting. We also extend existing recovery algorithms to the general highdimensional lattice setting. Selecting a lattice with a smaller normalized second moment reduces the reconstruction mean squared error (MSE) through two complementary mechanisms: it lowers the folded signal power, which reduces the absolute noise energy at a fixed signal-to-noise ratio (SNR), and it reduces the quantization error when a matched lattice quantizer is applied. Higher-dimensional lattices offer better second moment compared to the hypercube lattice, with gains that grow substantially with dimension. Instantiating the framework in two dimensions with the hexagonal lattice reduces the MSE relative to the square at the same inradius by 16.7%. Furthermore, simulations on 8-dimensional signals using the E8 lattice to achive 57% in both additive and quantization noise. A topological interpretation connects each folding geometry to a surface whose genus reflects the lattice complexity, and reveals a natural hardware implementation via comparator circuits.

Retinal imaging provides a non-invasive window into systemic microvascular health and has emerged as a potential biomarker for systemic diseases. However, whether retinal features encode biologically meaningful systemic signals that can be reliably interpreted using explainable artificial intelligence (XAI) remains unclear. An explainable multi-task deep learning framework was developed to investigate associations between retinal microvascular features and systemic abnormalities in Type 2 Diabetes Mellitus. A total of 11,011 fundus images from 2,719 individuals were analysed using a shared neural network with task-specific heads for glycaemic status, kidney abnormality, and multi-system involvement. Model interpretability was evaluated using Gradient-weighted Class Activation Mapping (Grad-CAM), anatomical masking, and vessel alignment analysis. The framework demonstrated task-dependent predictive performance, with the best discrimination observed for kidney abnormality (AUC up to 0.63), whereas glycaemic status prediction showed limited performance (AUC = 0.49-0.61). Explainability analyses consistently localized model attention to retinal vessels and peripapillary regions. Masking experiments showed that occlusion of vascular regions caused the greatest performance decline, indicating that retinal vessels were the primary predictive source. Different architectures exhibited heterogeneous attention patterns, suggesting multiple representational pathways for systemic signal encoding. This pilot study demonstrates that retinal microvascular features contain measurable signals associated with systemic abnormalities, particularly microvascular damage. By integrating multi-task learning with quantitative XAI validation, this framework advances retinal imaging toward interpretable digital biomarkers for systemic risk stratification in diabetes.

Fast-charging of lithium-ion batteries is essential for electric vehicle adoption, but aggressive charging can accelerate its degradation and create safety risks. This study investigates a control framework that coordinates charging current with active thermal management to minimise charging time, while respecting constraints on electrochemical degradation and thermal safety. A single particle model with electrolyte dynamics (SPMe), extended with a two-node thermal model, represents the battery dynamics and enables the prediction of internal states - used in the control strategy - including anode potential, core temperature, and cell voltage. Two multi-input multi-output control strategies are developed and compared: a classical approach using parallel proportional-integral-derivative (PID) controllers and an advanced model predictive control (MPC) with dual resolution prediction. Both controllers regulate the charging current and thermal resistance to minimise charging time while keeping within the limits of anode potential, core temperature, and cell voltage. The results demonstrate that coordinated thermal-electrochemical optimal control outperforms conventional approaches, achieving a 42.2% reduction in charging time compared to the manufacturer's charging recommendation, without increasing degradation. MPC reduces the charging time by 5.2% compared to PID control, but at a significant computational cost. This improvement demonstrates the untapped potential of integrated thermal management in fast-charging protocols.