arXane › Electrical Engineering and Systems Science › Electrical Engineering and Systems Science
Wednesday, 4 November 2026: 16 new papers, 11 cross-lists and 12 replacements in Signal Processing (eess.SP), in arXiv's order, with full abstracts. The same papers as arXiv's own listing, set as a newspaper; every title links to arXiv.
This letter presents a 65 nm neuroprosthetic system-on-chip (SoC) featuring a rapid feedback pathway from motor recording to sensory stimulation. To enable low-latency sensory mapping modulated by individual-neuron firing rates, the SoC integrates a mixed-signal unsupervised spike-sorting module with stimulation-artifact rejection, a programmable sliding-window firing-rate calculator, and a closed-loop controller for adapting stimulation parameters. The spike-sorting module combines event-driven analog feature extraction with Manhattan-distance-based digital clustering while consuming 1.6 $\mu$W/channel. On the Quiroga Difficult-1 benchmark, it achieves 94.58% three-class accuracy, with only a 0.4% reduction when stimulation artifacts are introduced at 20% of the spike count. The closed-loop controller supports polynomial and logarithmic mapping functions and incorporates Mitchell's approximation for power saving. The SoC is fully characterized on the bench and in vivo.
This paper proposes an artificial intelligence (AI) driven mission capability aware unmanned aerial vehicle (UAV) swarm coordination framework for autonomous post disaster search and rescue. An integrated sensing and communication enabled master high altitude platform station senses the disaster environment, detects victims and hazards, and constructs adaptive rescue regions based on spatially varying mission demands. A mission capability requirement (MCR) quantifies regional capability demand, while a normalized mission capability score (MCS) characterizes the real time capability of individual UAVs. A capability-aware assignment mechanism matches UAV capabilities to regional requirements while minimizing deployment distance. An MCS based reallocation mechanism dynamically transfers UAVs from capability surplus to capability deficient regions while preserving donor sufficiency. A hierarchical deep reinforcement learning framework with proximal policy optimization performs high-level region selection, while MCR MCS matching enables feasible UAV level reallocation. Finally, joint trajectory optimization considers travel time, distance, propulsion energy, operational capability, obstacle avoidance, and inter UAV collision avoidance. Theoretical analysis and simulations demonstrate improved mission capability satisfaction, resource efficiency, and disaster response performance
The surge in global mobile traffic, driven by 5G adoption and emerging applications, necessitates new spectrum allocations for 6G systems. With most major swaths of spectrum below 15 GHz already allocated to other services, co-existence between cellular and incumbent services such as satellite or radar systems is critical to make such spectrum accessible for 6G. At the same time, the advent of artificial intelligence offers a new opportunity for designing more efficient spectrum sharing techniques. This paper presents four novel data-driven spectrum access techniques to enable efficient use of spectrum for the 6G era: 1) co-existence technique for efficient protection of fixed incumbent receivers within an established protection area; 2) data-driven approach for protecting satellite receivers via control of radiated power above the horizon; 3) spectrum sensing-based fast-time-scale physical resource block blanking; and 4) base station-based spectrum occupancy detection to enable fast-time-scale spectrum sharing with satellite and non-terrestrial network incumbents. These techniques leverage artificial intelligence and extreme multiple-input multiple-output capabilities to enable efficient spectrum co-existence/sharing while maintaining cellular network performance.
As the 3rd Generation Partnership Project (3GPP) expands 6G non-terrestrial network (NTN) to S, Ku, and Ka bands for integration with existing terrestrial cellular networks, the necessary satellite channel model for link and network performance evaluation remains tied to TR 38.811, last revised in 2020. We identify issues on multiple fronts: inappropriate parameter specifications based on very limited site-specific environments considered, omission of satellite-induced Doppler spread and directional antenna effects and lack of a transparent channel model generation procedure. To address these limitations, we re-derive the channel parameters using ray tracing (RT) over urban and rural environments based on ITU-R building statistics. Our results show that TR 38.811 substantially overestimates the K-factor at low elevations and predicts a decreasing trend with elevation, which is inconsistent with RT. The Ka-band clutter loss (CL) also exceeds the RT estimates by more than 15 dB in urban cases. It also underestimates rural delay spread (DS) at low elevations and predicts an elevation trend inconsistent with RT. We further quantify the previously neglected satellite-induced Doppler spread. Finally, we demonstrate that the conventional TR 38.811 channel generator significantly underestimates the K-factor in the presence of directional antenna (beamforming), while our modified generator substantially reduces this discrepancy.
Achieving higher spectral efficiency (SE) in 5G and future 6G networks requires efficient massive multi-user multiple-input multiple-output (MU-MIMO) grouping under coupled physical-layer constraints and strict scheduling deadlines. Motivated by industry efforts in AI-native RAN, we propose Graph-Transformer Actor-Critic (GTAC), a deep reinforcement learning (DRL) architecture for carrier-aware MU-MIMO user grouping. The objective is to maximize the long-term proportional-fair (PF) utility of the cell subject to constraints from the practical stack protocol. GTAC comprises a shared actor--critic encoder with spatial-edge-biased attention mechanism, a pointer decoder actor that generates grouping decisions, and a multi-stage transformer critic that estimates the carrier-wide state-value during training. Training begins by cloning a teacher policy that cannot meet real-time deployment deadlines, followed by critic warmup and two-stage reinforcement learning using proximal policy optimization (PPO), first on a narrow, power-matched carrier and then on the full carrier with a Kullback--Leibler (KL) policy anchor. After two-stage PPO, the best GTAC policy outperforms the non-real-time teacher by 11.6% in carrier SE, while exceeding its PF utility and preserving the cell-edge throughput. A CUDA implementation of GTAC achieves a 69.6 us inference latency on an RTX PRO 4500 GPU, below the targeted 100 us inference budget in practical systems.
In wireless systems, foundation models have been proposed as alternative artificial intelligence models to replace task-specific models with a shared pretrained model that can be reused across many downstream applications (source separation, interference detection, localization, etc.). These wireless foundation models promise to reuse learned representations across diverse tasks, but choosing a foundation model also means choosing its input representation. For example, a model pretrained on spectrograms expects spectrograms, while one pretrained on in-phase/quadrature (IQ) samples expects IQ, limiting which pretrained model can be used for a given downstream problem. To remedy this, we present RFShape, a 7.4 M-parameter foundation model that breaks this coupling by adapting how a signal is presented to a shared pretrained encoder. RFShape is pretrained solely on synthetic IQ waveforms, without real captures, labels, or channel impulse responses (CIRs), and uses deterministic representation operators to support heterogeneous downstream inputs. Across ten tasks and nine datasets unseen during pretraining, the same encoder supports classification, ranging-error regression, and two-dimensional positioning. Representation selection alone increases 23-class radar recognition from 23.0% to 69.5% and short-range technology recognition from 70.8% to 97.1%. RFShape also outperforms CIR-pretrained ultra-wideband baselines by up to 12.7 percentage points for (N)LOS classification despite never observing CIRs during pretraining. These results show that foundation-model reuse need not be limited by the representation or modality seen during pretraining, and adapting how a signal is presented can extend a single pretrained encoder across heterogeneous wireless tasks.
In a pinching-antenna system (PASS), a single source feeds multiple pinches, resulting in a cascade that couples their radiated powers. A shared radiated-power limit, such as the interference power constraint in an underlay cognitive radio network, couples them again. We study such a network where PASS serves the secondary users. First, we formulate the joint optimization problem of the two degrees of freedom (DoF), pinch positions and radiation efficiencies, and characterize the single-link optimum analytically. Then, rather than proposing one method, we present the results for a grid of schemes whose two axes are the two DoF. Under an order-free attribution, positioning is worth 1.34 times radiation efficiency, and the two are near-perfect substitutes. We also show that substitutability is due to the constraint and not the cascade, since relaxing the constraint by 20 dB removes 97% of their interaction. At the joint reference, not knowing the primary receiver (PR) location costs 6.23 bit/s/Hz, more than twice the 2.87 that optimizing both DoF is worth. Instantaneous fading information adds a further 0.29 bit/s/Hz. Allocating efficiencies at equally spaced positions reaches 98% of the joint reference at about three orders of magnitude less computation.
Integrated sensing and communication (ISAC) enables sensing and communication (S&C) functions to share time, frequency, and hardware resources, offering an efficient paradigm for next-generation wireless systems. However, conventional fixed-configuration antenna (FCA) architectures provide limited flexibility in adapting the physical electromagnetic (EM) response of the end-to-end wireless link. This article develops a unified EM-adaptation perspective on reconfigurable antenna (RA)-enhanced ISAC systems. We distinguish transceiver-side (TSc-side) and environment-side (Env-side) RA deployments and identify five fundamental EM reconfiguration dimensions: position, orientation, radiation pattern, polarization, and frequency response. Building on this framework, we examine how these dimensions customize communication channels, actively control target information mapping for sensing, and reshape the interplay between S&C, particularly by improving compatibility between S&C requirements under shared resources. Two case studies illustrate how TSc-side and Env-side EM reconfiguration can improve spatial selectivity and the achievable S&C performance tradeoff. Finally, we discuss several promising directions for advancing RA-enhanced ISAC systems, including fundamental performance limits, low-overhead black-box optimization, and artificial intelligence (AI)-enabled semantic ISAC.
Accurate channel state information (CSI) prediction is pivotal for enhancing system capacity in low Earth orbit (LEO) satellite-terrestrial communications within the sixth-generation vision of global ubiquitous connectivity. However, the extreme mobility of LEO satellites, coupled with significant propagation delays, induces severe channel aging. Existing deep learning (DL) methods often struggle with non-stationary dynamics or generalize poorly across diverse global geographies. To address these challenges, we design the Evo-TFMamba, which is an evolutionary framework integrating time-frequency selective Mamba blocks with meta-learning for generalized CSI prediction. Experimental results demonstrate that the proposed Evo-TFMamba performs adaptive prediction according to the geographic coverage of LEO satellites. Meanwhile, it significantly enhances the model's generalization ability, particularly when faced with unseen channel environments in LEO satellite communication.
This paper investigates robust joint antenna positioning and precoding for multiuser movable antenna (MA) systems under imperfect channel state information (CSI). First, we identify the mismatch between the spatial statistics of densely sampled MA channels and the discrete Fourier transform (DFT) basis used for conventional robust precoding. To address this, we develop a novel discrete prolate spheroidal sequence (DPSS)-based a posteriori channel model. By exploiting the spatial covariance structure of MA channels, this model is better suited to modeling MA channel uncertainty. Building on this model, we develop an efficient iterative algorithm for robust joint antenna positioning and precoding to maximize the expected sum rate. By transforming the coupled optimization of antenna positioning and precoding at each iteration into direct comparisons of closed-form scores, we design a low-complexity position replacement scheme that effectively reuses matrix computations across candidate sets. To further improve efficiency and scalability, we exploit the inherent tensor equivariance (TE) of the problem to develop a reinforcement learning framework. To explicitly account for channel uncertainty, we develop novel pairwise user-interaction and CSI-conditioned equivariant attention mechanisms to encode channel statistics and adaptively fuse them with the available CSI. We further introduce distance-biased spatial attention to incorporate the geometry of candidate positions into attention weighting, thereby enhancing spatial feature learning. Simulation results show that the proposed methods improve sum-rate performance while reducing online runtime under imperfect CSI. These methods also achieve near-optimal performance under perfect CSI, closely matching the exhaustive-search method. Moreover, the learning framework generalizes across different numbers of users and MAs without retraining.
Many signal-processing objects are defined by periodicity, normalization, sign or global-phase ambiguity, basis invariance, or positive-semidefinite constraints and therefore cannot be modeled faithfully in ordinary Euclidean space. This paper develops a geometry driven framework for directional statistics in signal processing, connecting signal representations to their natural manifolds or quotient spaces and to probability models compatible with their invariances. After reviewing instances of directional statistics in the signal processing literature, we review circular, toroidal, spherical, projective, Stiefel, Grassmann, and covariance-valued distributions, emphasizing their statistical assumptions, computational requirements, and dimensional limitations relevant to signal processing. We describe various modeling and estimation strategies, including analytical and gradient-based maximum likelihood, structured low-rank parameterizations, mixtures and hidden Markov models (HMMs), score-based and contrastive estimation, and geometry-aware K-means. To exemplify the consequences of geometry-aware modeling, we study multivariate phase coherence in synthetic data and functional neuroimaging, comparing toroidal phase vectors to projective, Grassmann, and positive-semidefinite representations. We also study speaker separation in a car environment, showing that directional representations outperform a standard Euclidean model. These examples demonstrate that when the geometric representation, statistical distribution, inference method, and computational regime are considered together, they have the potential to lead to improved models across a broad range of signal processing applications.
In mobile wireless links, motion changes path directions and visibility, and blockage can shift communication to a different propagation path. Integrated sensing and communication (ISAC) allows a base station (BS) to use echoes of data transmissions to monitor these changes and guide subsequent beam selection. Illuminating objects that govern future path availability may reduce the beamforming gain on the current communication route. Existing sensing-communication tradeoffs and dynamic beam-control frameworks do not directly quantify the future communication gain from this current-rate sacrifice. We quantify sensing value by the future-rate gain enabled by echo-adaptive beam selection. We derive explicit expressions for the future communication gain and the net gain after accounting for the current-rate loss. The analysis uses a coupled communication-echo channel with binary-state Markov motion over a finite burst informed by one processed echo. We show that monitoring is worthwhile when its future-rate gain exceeds the current loss, while more informative observations yield zero additional future rate if they cannot change any future optimal beam. We derive interpretable gain bounds exposing the roles of improved scene discrimination, motion memory and future beam-rate differences. Reciprocal-channel tests demonstrate positive net accumulated-rate gains from monitoring a moving blocker during reflected-path service, including continuous position uncertainty.
Multiple-input multiple-output (MIMO) systems rely on spatial degrees of freedom, but fixed antenna geometries cannot adapt to propagation environments. Movable antenna (MA) systems address this by adapting antenna positions to the channel. In discrete MA architectures, active antennas are selected from candidate positions, requiring channel state information (CSI) at those positions. With limited radio-frequency (RF) chains, CSI is acquired through successive pilot rounds, or antenna scanning, whose overhead can offset reconfiguration gains. This paper studies discrete MA geometry optimization when only a fraction of candidate positions is scanned. We show that a geometry-aware (GA) steering-vector codebook, constructed from the actual antenna coordinates, reconstructs channels more accurately than a conventional discrete Fourier transform (DFT) codebook when the optimized array departs from a uniform grid. We then show that the scanning fraction required to approach full-scan sum-rate performance depends on the CSI acquisition method: least-squares (LS) estimation degrades sharply under sparse scanning, while codebook-based acquisition remains robust. We also propose an adaptive scanning procedure that probes candidates in batches and stops automatically using the acquired pilots, avoiding a preset scanning budget. Finally, we quantify sum-rate losses as users move from their initial positions and evaluate recovery through re-scanning and geometry re-selection, relative to fixed-aperture operation with outdated or fresh CSI. Numerical results show that adaptive scanning achieves about 99.5% of the full-scan sum rate while scanning only 11% of candidate positions.
Recent end-to-end learning frameworks jointly optimize pilot design, channel state information (CSI) feedback, and downlink precoding, achieving strong performance under limited feedback overhead in massive multiple-input multiple-output (MIMO) networks. However, the internal representations and decision-making strategies learned by these architectures remain largely unexplored. This paper presents an interpretability analysis of a precoding-oriented end-to-end CSI feedback framework using explainable artificial intelligence (xAI) techniques. Building on a validated learned architecture, we investigate the structure of the learned pilots, latent feedback representations, and precoding vectors through low-dimensional visualization, density-based clustering, and cross-block representation analysis. The results reveal that the learned system undergoes a transition as the feedback constraint is relaxed. Under stringent feedback budgets, the encoder develops clustered latent representations and quantized precoding behavior. As additional feedback resources become available, the learned representations evolve into smooth geometry-preserving manifolds that retain physically meaningful channel characteristics such as dominant angular information, while enabling more adaptive precoding decisions. Furthermore, the learned pilot signals naturally form complementary sensing patterns aligned with the underlying channel statistics. The analysis also reveals a shift from gain-driven beamforming strategies under severe compression to increasingly interference-aware precoding as the feedback budget increases. These findings provide new insight into how end-to-end learned CSI feedback systems balance compression efficiency and communication performance and establish a general framework for interpreting learned communication architectures.
The paper introduces a parameter identification framework for atomic clock ensembles, where individual clocks are represented by second-order linear stochastic state-space model. The proposed procedure relies exclusively on differential measurements, namely the pairwise phase differences between a designated pivot clock and the remaining ensemble members. The identification targets key parameters for each clock: white and random-walk frequency noise variances, constant frequency drift, and (co)variance of the measurement noise. To identify these parameters, two distinct identification methods are proposed. Their estimation accuracy is rigorously demonstrated via numerical simulations and validated using empirical data from atomic hydrogen maser (AHM) clocks at ESTEC Timing Laboratory.
Integrated sensing and communications (ISAC) enables mobile networks to detect passive targets such as drones at minimal additional cost. However, in ISAC, a small drone must be detected against strong ground clutter with the limited radio resources left by communications. In this paper, we propose two ISAC target detectors: a coherent detector, which combines all frames and beam dwells of a revisit, and a non-coherent detector, robust to inter-frame clock phase drift. The algorithms leverage per-dwell clutter whitening and the adaptive coherence estimator (ACE) detection statistic to improve performance. Both detectors estimate the range, radial velocity, and azimuth of targets in real time on a laptop graphics processing unit (GPU). Measurements with an FR1 ISAC proof-of-concept system based on a commercial base station show that the coherent detector outperforms the non-coherent one and recovers the full track.
Deep neural networks extract powerful latent representations from images, enabling fast and efficient downstream analysis. However, these latent spaces lack explicit geometric structure, leading to possibly poor interpolation fidelity and misleading extrapolation. Latent interpolation techniques assume symmetric transition costs which are often not the case for real world data. Their symmetric nature cannot capture directional processes, such as disease progression, where certain transitions are impossible (e.g. tumor growth dynamics or cognitive improvement in Alzheimer's disease). Although Riemannian metrics extend Euclidean geometry by incorporating curvature, they remain symmetric. We show that understanding asymmetry and not curvature alone directly addresses these problems. To do so we propose a new Finsler-Randers metric learning framework. It incorporates direction-dependent distances, thus enabling the computation of trajectories respecting monotonic sequential constraints. We demonstrate its potential for interpolation and extrapolation on controlled cross-sectional datasets.
Millimeter-wave (mmWave) links can lose tens of decibels within milliseconds when a person or vehicle crosses the line of sight, and reactive handover recovers only after the outage has begun. Integrated sensing and communication (ISAC) promises to let the network see blockers coming and move users to another cell in advance. This paper asks how much such foresight is worth relative to the best reactive handover, and what sensing accuracy is needed to harvest it. We formulate cost-aware cell selection with knowledge of the future signal-to- noise ratio as a sequential decision problem, define the value of foresight through a policy-independent bound, and develop an ISAC-assisted handover framework in which a radio unit senses blockers with its own communication waveform and a simulated Open RAN xApp plans handovers. Ray-traced experiments in a 28 GHz street canyon, reported on held-out scenarios, show that, with a short look-ahead, perfect foresight closes most of the gap between service-aware (Layer-3) reactive handover and an instantaneous oracle. Harvesting this value, however, requires the user and nearby blockers to be localized to about a decimeter, well beyond what our radar tracker and meter- level user positioning provide; with realistic errors, even an uncertainty-aware planner largely defers to reactive handover.
We consider a UAV-assisted status-update system in which a rotary-wing unmanned aerial vehicle (UAV) collects updates from multiple sensors, stores the newest update of each sensor, and forwards selected buffered updates to a ground station (GS). We minimize a weighted sum of the time-average GS-side age of information (AoI) and UAV energy consumption over a finite horizon. The optimization is subject to half-duplex operation, sensor and UAV energy-causality constraints, transmission-rate and power limits, and a terminal-location constraint. Because collection changes the information age at the UAV but does not reduce the GS-side AoI until the buffered update is forwarded, mobility, collection, and forwarding decisions are coupled over time. We use a hierarchical AoI-energy actor-critic (HAE-AC) controller in which a coarse-timescale actor selects return-feasible UAV movements, while a deterministic per-slot scheduler constructs feasible collection or forwarding sets and assigns the minimum transmit power required for each scheduled transmission. In a 100-sensor deployment, HAE-AC reduces the average GS-side AoI by about 22% relative to an adaptive staleness-gated benchmark. Compared with forward-upon-collection, selective buffered forwarding reduces the number of downlink bursts by roughly 30% while increasing the number of collections per sensor by more than 23%.
Prestress governs the stability, stiffness, and dynamic behavior of tensegrity structures, but it is not directly observable from sparse structural measurements, and it may decrease during service life. Under strong excitation, the cables may slacken and the dynamics become nonsmooth. Existing identification methods are limited to the taut regime, and physics-informed networks for tensegrities solve only the forward problem of predicting the response from known member parameters. This study formulates the inverse problem. Neural networks are trained on the equation-of-motion residual in constrained Cartesian coordinates, where the mass matrix is constant and the force densities enter linearly. The force densities, damping, and axial stiffness are trainable parameters, and the tension-only cable law is kept. A Fisher-information analysis shows, before inversion, which member parameters a record can determine. The method is tested on simulated planar tensegrity frames with up to five modules and a three-dimensional prism, and on measured records of a biomimetic leg and a full-scale tensegrity simplex. On the one-module frame, the identifiable force densities are recovered within 1.5% from noisy accelerations at half the free coordinates, on records with and without taut-slack transitions. Records with transitions determine members that taut records leave undetermined. On the five-module frame, a 16-cable two-span bridge, the median force-density error rises moderately, to 4.2%. On measured records, an identified spring stiffness is within 0.1% of its independently measured value on average, and the identified simplex prestress at 13 levels agrees with its cable force transducers to 2.9% root-mean-square.
The dielectric properties of biological tissues are used to investigate the interaction of electromagnetic (EM) fields with the human body. These properties are integrated into EM numerical simulations, such as the finite difference time domain (FDTD) method, using dielectric models such as Cole-Cole and Debye models. These computational tools are employed to study the propagation of EM waves within the human body. This paper has developed the one-pole and two-pole Cole-Cole and Debye models for the dielectric properties of normal and diseased human trabecular bone tissue at microwave frequencies (0.5-8.5 GHz). The dielectric properties of normal trabecular and cortical bone were derived based on the literature, while those of diseased human trabecular bones (osteoporotic and osteoarthritis) were acquired from a previous study conducted by the authors, which characterised the properties within the 0.5-8.5 GHz frequency range. This study has employed a weighted least squares method to optimise the one-pole and two-pole dielectric models' parameters. The accuracy of the developed dielectric models is validated by comparing the simulated results with the experimental data already published by the authors. The comparative analysis of the models demonstrated that the one-pole Cole-Cole model achieved a better fit compared to the one-pole Debye model across all bone types. Additionally, the two-pole Cole-Cole model exhibited a better fit than the two-pole Debye model. The proposed models can be used in numerical simulations to investigate the interaction of EM fields with bone tissue and develop and optimise microwave bone health monitoring and treatment techniques.
Movable antennas (MAs) improve wireless communications by adapting antenna positions to the propagation environment. However, antenna movement also changes the mutual coupling (MC) among elements of the transmit and receive arrays, which affects the performance of MA-enabled systems. In this paper, we investigate MC-aware joint precoding and antenna positioning for a downlink multiuser multiple-input multiple-output (MU-MIMO) system with MAs at both the base station and users. We establish an MC-aware system model by combining field-response propagation with a circuit-based representation of the transmit and receive arrays. Based on this model, we formulate a weighted sum-rate (WSR) maximization problem that jointly optimizes multi-stream precoders and antenna positions. The problem is challenging because the precoders and positions are coupled through the propagation channels and position-dependent MC matrices. To address this challenge, we reformulate the problem in the antenna-current domain to to efficiently handle the MC matrices and develop a current-domain weighted minimum mean square error (WMMSE) framework for alternating optimization. Furthermore, we handle the nonconvex position updates within the framework by using majorization--minimization (MM) and solve the resulting convex subproblems with a dedicated conic alternating direction method of multipliers (ADMM) algorithm. Simulation results demonstrate that the proposed design improves the WSR over both an MC-aware fixed array and a movable-array design that ignores MC during optimization.
Robust Principal Component Analysis (RPCA) is essential in signal processing, with applications in hyperspectral imaging, face recognition, and video background modeling. Traditional RPCA methods often suffer from insufficient utilization of data priors and struggle to capture complex image structures. Conversely, advanced deep denoisers like DnCNN, FFDNet, and DRUNet excel at leveraging image data priors but lack physical model constraints and demonstrate poor robustness against structured noise in RPCA tasks. This paper proposes a novel Plug-and-Play (PnP) method for multi-channel RPCA, integrating both the physical generative model and cutting-edge deep priors. Extensive experiments on RGB and hyperspectral datasets show that PnP-PDA achieves better quantitative performance than conventional RPCA methods and state-of-the-art methods, including deep denoisers and tensor RPCA approaches, while preserving visual details.
Footstep patterns, captured using pressure or force-sensitive walkways during natural walking, offer a convenient and passive approach to biometric recognition. However, footwear variability poses a major challenge to practical deployment, as it impacts both the foot-sensor interface and the user's underlying gait mechanics. This study considers the particularly difficult scenario where users enroll under one fixed footwear condition but must later be recognized in arbitrary, unseen footwear. Using the StepUP-P150 dataset, we show that footwear-induced shift, while substantial and heterogeneous across individuals, contains shared structure that can be learned from a training population and transferred, zero-shot, to previously unseen users and footwear styles. We do this using BiStepNet, a novel architecture that decomposes spatial and temporal identity cues into independently trainable streams and outperforms compact 3D spatiotemporal baselines for cross-footwear recognition. We demonstrate that cross-footwear recognition performance scales systematically with the volume and diversity of footwear representation in the training set, with gains transferring to footwear styles not directly observed during training. Moreover, we show that auxiliary gait datasets with only partial modality overlap (incorporated through the architecture's decomposed design) can be leveraged to further improve robustness to unseen footwear conditions.
Vertical forest structure influences fire behavior by regulating understory-to-canopy fuel connectivity, yet operational fuel-type models represent this complexity through discrete classes that only indirectly capture vertical continuity. High-density point clouds offer an opportunity to characterize vertical fuel connectivity in a more explicit and continuous manner, but specific methodological approaches are still required. We applied Gaussian decomposition to vertical height profiles derived from terrestrial laser scanning (TLS) point clouds across 25 permanent forest plots to characterize geometric vertical fuel continuity. A multiscale analysis spanning from the plot scale to ~0.5 $m^2$ units was used to evaluate geometric, probabilistic, and overlap metrics for characterizing fuel strata. The method reproduced the vertical transition between shrub and tree strata, with median Pearson correlations ranging from 0.83 to 0.96 across analysis levels. Probability density overlap metrics and separability indicators, such as the Jeffries-Matusita distance, provided complementary descriptors of vertical continuity. Intermediate spatial scales (3-6 m cells) provided a useful compromise between spatial detail and the consistent representation of shrub-canopy interaction patterns. Finer scales increased variability due to point density reduction and profile irregularity, and low mean squared error values were found insufficient as sole performance indicators. Gaussian decomposition applied to TLS point clouds enables explicit quantification of vertical fuel continuity, a limitation of current discrete classification systems. Continuous vertical connectivity metrics derived from this approach offer a pathway for improving ladder fuel characterization and strengthening decision-making support in wildfire risk assessment.
Channel estimators at a newly deployed base station usually start from 3GPP stochastic channel models, which describe no particular street. We ask whether a channel prior pooled from many ray-traced cities serves an unseen site better than the 3GPP CDL models, and whether learned estimators make the difference. With Sionna RT on 14 city scenes, LMMSE estimation from covariance priors, leave-one-city-out evaluation, and pass/fail bars written down before each main experiment, we find in simulation that the pooled prior sits about 0.6 dB from a site-trained estimator with no site measurements, about what CDL reaches after 50 measurements. Learned models added little: at most 0.65 dB in estimation, and in channel prediction a simple classical method beat CNN predictors by 1.8-12 dB from 2 ms ahead. On measured channels from the DICHASUS outdoor dataset (1.272 GHz, three 2x8 arrays on one building) the result reversed: the pooled ray-traced prior was 3.2-4.1 dB worse than CDL. The simulated channels were too clean; with users at the real distances, even a scattering level tuned from 50 site measurements left the prior about 2 dB behind CDL. A pre-registered follow-on on two more measured environments found the generic CDL prior 2.1-4.7 dB from a site-trained one: no further in a factory hall than on the street, furthest in a small lab room. Finally, a hallway model calibrated to measurements by differentiable ray tracing reproduced delay spread, but as a prior in an unmeasured part of the hallway it was 4.5 dB worse than CDL on the full array. All measured results come from one sounder.
Real-time phase estimation on stimulus-aligned transient EEG is critical for closed-loop neuromodulation systems targeting the theta-band, yet most real-time phase estimation methods have been developed and validated on resting-state, high-fidelity signals in the alpha band. Recent work has pursued deep learning architectures, while individualized classical bandpass filter tuning remains underexplored. This study characterizes the spectral and temporal properties of non-anticipative bandpass filtering and demonstrates the performance gains achieved through individualized tuning. We present a Bayesian-Optimized Biquad Filter-Burg (BOB) model evaluated on EEG recorded during peripheral vibrotactile stimulation of the left median nerve (theta, N=20 healthy subjects) and on resting-state recordings from the Max Planck Institute's LEMON dataset (alpha, N=20 healthy subjects). BOB was benchmarked against the Deep Dual-Branch Complex Neural Network (DBCNN), EEG Phase Prediction Network (EPN), Phastimate, and Phase Estimation with Autoregressive Padding (PEAP) under matched testing conditions: channel selection, individualized optimization, evaluation time points, and an offline reference phase obtained through zero-phase filtering and the Hilbert transform. Under these testing conditions, BOB achieved matched or better performance than these models at a fraction of the calibration time.