Systems and Control · Cross-listed from cs.NI
Look Once, Beam Twice: Camera-Primed Real-Time Double-Directional mmWave Beam Management for Vehicular Connectivity
Avhishek Biswas, Apala Pramanik, Eylem Ekici et al. (+1 more)
Millimeter-wave (mmWave) frequencies promise multi-gigabit connectivity for vehicle-to-everything (V2X) networks, but face challenges in terms of severe path loss and mobility-related beam misalignment. Reliable V2X connectivity requires fast, double-directional beam
alignment. However, existing methods suffer from high training overhead and limited generalization to unseen scenarios. This paper presents
VIsion-based BEamforming(VIBE), a hybrid model-based, closed-loop, learning architecture for real-time double-directional mmWave beam management primed by camera sensing. VIBE fuses machine learning, model-based
reasoning, and closed-loop RF feedback to balance beam-pair establishment latency with link quality. VIBE bypasses exhaustive training overhead and accelerates link establishment by leveraging camera observations to reduce the beam-search space. Lightweight beam refinement and offset tracking mechanisms adaptively refine beams in response to dynamic application requirements. VIBE is implemented and evaluated across online indoor/outdoor testbeds, public
datasets, and real-time vehicular experiments, demonstrating strong generalization capabilities, making it suitable for real-time V2X communication. Comparisons with 5G NR hierarchical beamforming show that VIBE consistently maintains lower outage rates. Furthermore, VIBE outperforms state-of-the-art end-to-end ML models for beam selection when evaluated on public
datasets and achieves outage rates as low as 1.1-1.4 %. The results show that a hybrid model-based, closed-loop learning architecture is better suited for real-world mmWave vehicular connectivity than end-to-end trained ML models. For reproducibility, we publish our code to https://github.com/UNL-CPN-Lab/Look-Once-Beam-Twice.
Read the full abstract ▾
All authors Avhishek Biswas, Apala Pramanik, Eylem Ekici, Mehmet C. Vuran
Signal Processing · Cross-listed from cs.IT
A Comparison Between Co-Located and Distributed MIMO Deployments in OFDM-ISAC Networks
Maryam Darabi, Sergi Liesegang, Emanuele Grossi et al. (+1 more)
This paper investigates network-level integrated sensing and communication (
ISAC) under two fundamentally different
topology configurations:
cell-free massive
MIMO (CF-mMIMO) and multi-
cell massive
MIMO (MC-mMIMO). A unified OFDM-based waveform is adopted for both architectures as the key enabler for
ISAC functionalities. The CF system exploits distributed access points (APs) and a scalable user-target-centric operation, whereas the MC system relies on co-located transmit-receive arrays with conventional
cell-centric deployment. For both architectures, we derive a GLRT-based sensing detector and the corresponding sensing SNR expressions. We then examine a series of case studies investigating how the number of OFDM subcarriers, the transceiver allocation strategy, and the
antenna/node distribution across the network affect the sensing performance. The results consistently demonstrate that CF-mMIMO provides more robust and higher sensing performance across most tested scenarios, particularly when transmit resources or
antenna elements are spatially distributed. These findings highlight the inherent advantages of CF deployments for next-generation
ISAC networks.
Read the full abstract ▾
All authors Maryam Darabi, Sergi Liesegang, Emanuele Grossi, Stefano Buzzi
Signal Processing · Cross-listed from cs.LG
Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework
Bac Trinh-Nguyen, Sara Berri, Sin G. Teo et al. (+2 more)
Localization in 5G and 6G networks is essential for important use cases such as intelligent transportation, smart factories, and smart cities. Although deep learning has enabled improving localization accuracy, depending on the deployment scenario and the effort required for
dataset collection campaigns on a given infrastructure, the training process for localization models can vary significantly. Furthermore, with respect to feature selection, recent works have demonstrated the robustness of angle-of-arrival (AoA) based localization. In view of these two points, we propose an adaptive framework for AoA-based localization that consists of two alternative learning strategies, each suited either for large or small training
datasets. The proposed framework is evaluated on a real, massive multiple input multiple output (mMIMO) orthogonal frequency division multiplexing (OFDM) outdoor channel state information (CSI)
dataset. First, we investigate offline learning when large training
datasets are available; we propose a hierarchical framework that first distinguishes between line of sight (LoS) and non line of sight (NLoS) regions and then moves to more fine grained localization in the respective region. This approach provides high-performance localization through accumulated batch retraining and an integrated hyperparameter optimization mechanism. Second, when only a small training
dataset is available, an online learning framework is proposed, using incremental tree-based and ensemble-based models for handling streaming data and continuously updating mode, as well as an online few-shot learning model for rapidly initializing new classes from a limited labeled support set. These results showcase that highly accurate robust localization can be achieved incrementally during network operation by exploiting online learning, alleviating the need for large
dataset collection campaigns.
Read the full abstract ▾
All authors Bac Trinh-Nguyen, Sara Berri, Sin G. Teo, Tram Truong-Huu, Arsenia Chorti
Systems and Control
Kinematic Discriminants of Deceleration Behavior Modes in Car-Following: Evidence from NGSIM Trajectory Data
Eni Solomon Laughter
Gap-closing rate and visual looming swap discriminative dominance depending on deceleration intensity - a finding that reconciles a long-standing conflict in the car-following literature and challenges spacing-centered assumptions in traditional driver behavior models. This study presents a two-stage analytical framework that distinguishes between information availability (kinematic variables measurable in the environment) and information utilization (variables that demonstrably separate driver behavioral patterns), applied to 1,060,119 valid car-following observations from the NGSIM trajectory
dataset (2,932 vehicles). Six kinematic features are extracted, and deceleration events are detected under two threshold conditions (-0.5 m/s^2 and -0.3 m/s^2). K-means clustering identifies behavioral modes, and one-way ANOVA with eta-squared effect sizes ranks each feature's discriminative power. Three key findings emerge: (1) threshold selection fundamentally shapes behavioral inference - the stricter threshold yields three interpretable modes while the permissive threshold collapses these to two; (2) hard braking prioritizes gap-closing rate (eta^2 = 0.715) while moderate braking emphasizes visual looming (eta^2 = 0.574); and (3) spacing headway is negligible (eta^2 <= 0.014) across both thresholds. These findings provide empirically grounded candidates for perceptual cue prioritization and have direct implications for ADAS warning system design and autonomous vehicle control.
Read the full abstract ▾
Systems and Control
Quantized Probabilistic AI for Gear Fault Diagnosis in Motor Drives
Subham Sahoo, Huai Wang and Frede Blaabjerg
Deploying large artificial intelligence (AI) models in power electronics often demands high computational resources. Driven by the quantization paradigm, this digest proposes a quantization-aware training (QAT) principle to substantially minimize the number of bits required and simultaneously maximize the accuracy of computations in pre-trained AI models. Considering a pre-trained probabilistic
Bayesian Neural Network (BNN) for gear fault diagnosis in motor drives as an example, we quantize its weights and activation functions from floating-point FP32 to low-precision INT8 values, which enhances the computational efficiency by a significant margin of 30-45% (for different model versions) without any compromise in the accuracy and uncertainty estimates. This substantiates a sustainable mechanism of deploying most quantized light-weight AI models into low-cost edge processors for power electronic applications.
Read the full abstract ▾
Systems and Control
Unlocking Embodied Probabilistic Computational Features in Motor Drives
Subham Sahoo, Huai Wang and Frede Blaabjerg
Artificial intelligence (AI)-driven fault diagnosis in motor drives often requires significant computational efforts and time for re-training, in addition to the limited knowledge behind the model and suitability of training and learning mechanisms. This work bridges this gap by proposing a structured mechanism of transforming untapped labeled fault data into AI parameters to leverage probabilistic data-driven learning. This novel AI reservoir modeling framework for power electronics not only eliminates exogenous efforts behind learning data patterns and its optimization, but also provides intuitive guidelines for power electronics engineers behind sizing of AI models. This
alignment between data and system physics makes the proposed model transparent and interpretable, bridging practical understanding with data-driven learning. Its computational efficiency is demonstrated using experimental data that structured, physics-aware reservoirs achieve higher diagnostic accuracy and clearer explanations than conventional black-box AI methods.
Read the full abstract ▾
Systems and Control
Adaptive Contention-based Random Access for Uplink Reporting in 3GPP Ambient IoT Networks
David E. Ruiz-Guirola, Samer Nasser, Bikramjit Singh et al. (+6 more)
Ambient Internet of Things (A-IoT) targets energy harvesting (EH), battery-less devices as a simple connectivity solution for extensive ultra-low-power deployments. These devices typically face intermittent energy availability, making uplink reports increasingly susceptible to access collisions and energy outages. In this paper, we build upon the cellular standardization of A-IoT and examine the paging-triggered contention-based random access (CBRA) framework for uplink reporting. We analyze the effects of energy availability and collisions on these systems and introduce an EH-aware access control mechanism. In this mechanism, the reader broadcasts an access probability in the paging message, which helps regulate the number of devices attempting random access. Results show that, unlike the baselines, the proposed method scales well under dense deployments by keeping collisions nearly constant, improving access efficiency, and substantially reducing the number of paging rounds required for successful reporting. These results highlight the importance of lightweight reader-side access control for reliable and resource-efficient reporting in A-IoT environments.
Read the full abstract ▾
All authors David E. Ruiz-Guirola, Samer Nasser, Bikramjit Singh, Henrique Duarte Moura, Andrey Belogaev, Jeroen Famaey, Efstathios Katranaras, Mahdi Shahabi, Onel L. A. Lopez
Signal Processing
Fast Full-Wave Simulation of Indoor RSS Maps for Pre-Measurement Validation in Device-Free Localization
Federica Fieramosca, Anastasia Maiolli, Alexander H. Paulus et al. (+2 more)
Human localization is gaining momentum in security, healthcare, logistics, and smart spaces applications. While global
navigation systems are unreliable indoor, device-free (a.k.a. passive) localization methods that exploit human-induced perturbations of
radio propagation can be effectively used. This paper investigates the use of a compact full-wave electromagnetic (EM) setup as a fast and reliable tool to simulate indoor Wi-Fi propagation for human sensing. The goal is to provide a practical baseline for validating simplified propagation models, such as diffraction-based descriptions, and to reduce the need for costly measurement campaigns. Two-dimensional attenuation maps from received signal strength are generated and compared in controlled environments, focusing on attenuation statistics and interference patterns. The simulations reproduce the main spatial features, though discrepancies remain due to simplified material characterization. Diffraction-aware refinements are proposed to mitigate these effects. Overall, the approach provides an efficient pre-measurement reference to support device-free system design and to guide experimental planning.
Read the full abstract ▾
All authors Federica Fieramosca, Anastasia Maiolli, Alexander H. Paulus, Stefano Savazzi, Michele D'Amico
Signal Processing
423.7 + 426.5 Tb/s GMI Bi-Directional HCF Transmission
Jiaqian Yang, Romulo Aparecido, Eric Sillekens et al. (+28 more)
We demonstrate OESCL-band same-wavelength bi-directional transmission over 60 km HCF with 42.5 THz bandwidth, achieving GMIs comparable with the highest unidirectional SMF data-rates in both directions, with an aggregate of 423.7 + 426.5 Tb/s.
Read the full abstract ▾
All authors Jiaqian Yang, Romulo Aparecido, Eric Sillekens, Ronit Sohanpal, Mindaugas Jarmolovičius, Zelin Gan, Yang Hong, Morteza Kamalian-Kopae, Abdallah Ali, Shahab Bakhtiari Gorajoobi, Ruben S. Luís, Daniele Orsuti, Aleksandr Donodin, Vitaly Mikhailov, Jiawei Luo, David J. DiGiovanni, Nicolas Fontaine, Lauren Dallachiesa, Mikael Mazur, Roland Ryf, Haoshuo Chen, David Neilson, Ian D. Phillips, Wladek Forysiak, Sergei K. Turitsyn, Hideaki Furukawa, Jamie Gaudette, David J. Richardson, Benjamin J. Puttnam, Robert I. Killey, Polina Bayvel
Signal Processing
Phase-Time Array Enabled Multistatic Sensing with Multi-Level Fusion for UAV Localization
Ming Gao, Jianhua Mo and Meixia Tao
In multistatic collaborative sensing, existing parameter-level fusion methods suffer from severe error amplification in geometrically unfavorable regions. Conventional receiver architectures present an additional challenge: analog phased arrays incur substantial beam sweeping overhead, while fully digital arrays demand prohibitive hardware costs. This paper proposes a multistatic sensing framework based on a phase-time array (PTA), whose rainbow beamforming maps spatial directions to OFDM subcarriers, achieving wide-angle coverage with a single RF chain and a favorable accuracy-complexity trade-off relative to both phased array and fully digital receivers. To suppress geometry-induced error hotspots, two parameter-level fusion schemes are developed: a GDOP-weighted analytical
estimator (GDOP-WLS) and a lightweight multilayer perceptron (PF-MLP). An end-to-end signal-level convolutional neural network (SF-CNN) is further designed to directly regress target coordinates from raw received signals, bypassing cascaded parameter estimation. Simulation results show that the parameter-level schemes effectively mitigate localized error amplification with minimal computational overhead, while SF-CNN attains sub-meter positioning accuracy, at the cost of higher model complexity that can be offset by GPU acceleration. Power-matched training further extends both schemes' accuracy across a wide power range.
Read the full abstract ▾
Systems and Control
ADMM-based decomposed DNN+RLT Relaxations for Completely Positive Models in Electricity Market Clearing
Shudian Zhao, Mohammad Reza Karimi Gharigh, Jan Kronqvist et al. (+1 more)
The day-ahead electricity
market clearing with nonconvex order types can be formulated as a mixed-integer linear program (MILP), but its LP relaxation may provide weak bounds, and exact solutions can become computationally intractable in large-scale or extended
market settings. We study a welfare-maximizing clearing model with elementary hourly orders, block orders with logical acceptance constraints, and flexible hourly orders. Starting from a compact MILP formulation, we derive an equivalent completely positive programming (CPP) reformulation via
matrix lifting and propose relaxed CPP variants that further reduce the modeling burden while maintaining strong bounds. We then develop tractable doubly nonnegative (DNN) relaxations, including decomposed formulations that exploit the problem structure by using smaller positive semidefinite
matrices. To further strengthen these bounds, we introduce reformulation-linearization technique (RLT) inequalities tailored to the decomposed structure. To tackle the challenge of large-scale DNNs, we design an alternating direction method of multipliers (ADMM) with adaptive penalty updates and rigorous dual lower bounds, enabling certified early termination. Computational experiments on synthetic instances show that the proposed DNN+RLT relaxations substantially tighten LP bounds, while decomposition and first-order methods significantly reduce computational effort.
Read the full abstract ▾
All authors Shudian Zhao, Mohammad Reza Karimi Gharigh, Jan Kronqvist, Mohammad Reza Hesamzadeh
Image and Video Processing · Cross-listed from cs.CV
FairEnc: A Fair Vision-Language Model with Fair Vision and Text Encoders for Glaucoma Detection
Mohamed Elhabebe, Ayman El-Baz and Qing Liu
Automated glaucoma detection is critical for preventing irreversible
vision loss and reducing the burden on healthcare systems. However, ensuring
fairness across diverse patient populations remains a significant challenge. In this paper, we propose FairEnc, a fair pretraining method for
vision-
language models (VLMs) that enables simultaneous debiasing across multiple sensitive attributes. FairEnc jointly mitigates biases in both textual and visual modalities with respect to multiple sensitive attributes, including race, gender, ethnicity, and
language. Specifically, for the textual encoder, we leverage a large
language model to generate synthetic clinical descriptions with varied sensitive attributes while preserving disease semantics, and employ a contrastive
alignment objective to encourage demographic-invariant representations. For the visual encoder, we propose a dual-level
fairness strategy that combines mutual information regularization to reduce statistical dependence between learned features and demographic groups, with multi-discriminator
adversarial debiasing. Comprehensive experiments on the publicly available Harvard-FairVLMed
dataset demonstrate that FairEnc effectively reduces demographic disparity as measured by DPD and DEOdds while achieving strong diagnostic performance under both zero-shot and linear probing evaluations. Additional experiments on the private FairFundus
dataset show that FairEnc consistently preserves
fairness advantages under cross-domain and cross-modality settings and maintains diagnostic performance within a competitive range. These results highlight FairEnc's ability to generalize
fairness under distribution shifts, supporting its potential for more equitable deployment in real-world clinical settings. Our codebase and synthetic clinical notes are available at https://github.com/Mohamed-Elhabebe/FairEnc
Read the full abstract ▾
Signal Processing · Cross-listed from cs.IT
Phased Ultra Massive Array (PUMA)
Hanjiang Hong, Kai-Kit Wong, Xusheng Zhu et al. (+3 more)
This paper proposes a novel multiple-access framework, termed the phased ultra massive
antenna array (PUMA), which exploits the distinctive spatial flexibility of fluid
antenna systems (FAS) at the user equipment (UE). Building upon fluid
antenna multiple access (FAMA) and compact ultra-massive
antenna array (CUMA), PUMA incorporates a phased array for signal aggregation. This architecture enables the UE to inherently mitigate co-user interference within the spatial domain without necessitating channel state information (CSI) for precoding at the base station (BS) or complex interference cancellation at each UE. A primary advantage of PUMA lies in its hardware efficiency: by implementing phase shifting and signal combining in the analog domain, it achieves high
antenna gain while requiring only a minimal number of
radio-frequency (RF) chains, potentially a single RF chain. Comprehensive theoretical analysis of the achievable data rate is provided, complemented by extensive simulations that validate the framework. The results demonstrate that PUMA markedly outperforms FAMA and CUMA architectures, particularly for UEs with a single RF chain, offering a robust and scalable solution for interference-insensitive massive connectivity in sixth-generation (6G) systems.
Read the full abstract ▾
All authors Hanjiang Hong, Kai-Kit Wong, Xusheng Zhu, Chenguang Rao, Dazhi He, Hyundong Shin
Systems and Control
Toward less conservative distributed stability analysis of power systems via matrix-valued differential passivity indices
Xi Ru, Cong Fu, Zhongze Li et al. (+2 more)
Passivity indices have been widely adopted to derive distributed stability certificates for power systems. Nevertheless, conventional passivity indices remain scalar-valued even for multi-input-multi-output (
MIMO) systems, which can introduce excessive conservatism and compromise analysis accuracy. To overcome these limitations, this paper extends the differential passivity index to a
matrix-valued formulation that captures both channel-wise passivity properties and inter-channel coupling effects in
MIMO subsystems. On this basis, semi-distributed and fully distributed stability criteria are developed for power systems with heterogeneous nonlinear devices. It is shown that system stability is guaranteed when the aggregate passivity excess of devices compensates for the passivity shortage imposed by the network. Furthermore, analytical passivity
matrix expressions for typical power system components are derived, facilitating compositional stability analysis. Case studies on a three-bus system and a modified IEEE 118-bus system validate the effectiveness of the proposed framework.
Read the full abstract ▾
All authors Xi Ru, Cong Fu, Zhongze Li, Xiaoyu Peng, Feng Liu
Systems and Control
Negative Imaginary and Passivity Properties of Synchronous Machine Systems
Maryam Khodabakhshloo, Elizabeth L. Ratnam and Ian R. Petersen
The recent rapid proliferation of renewable energy is fundamentally changing the dynamic operations of power systems, necessitating new approaches to assess stability for these highly nonlinear systems. In this paper, we prove that synchronous machine systems, modeled in the nonlinear dq-frame, possess fundamental dissipativity properties. Specifically, we show passivity from current input to voltage output and a nonlinear negative imaginary property from torque input to rotor angle output. For the nonlinear system shifted around an
equilibrium point, we derive explicit conditions for both passivity and the NI property to hold. Finally, we demonstrate that interconnection with passive droop controllers preserves these dissipativity properties with identical supply rates, thereby ensuring closed-loop stability.
Read the full abstract ▾
Signal Processing · Cross-listed from cs.IT
Distance Distributions Between Nodes in Concentric Disk-Annulus or Sphere-Shell Regions
Nicholas Vaiopoulos, Alexander Vavoulas, Harilaos G. Sandalidis et al. (+1 more)
This letter derives closed-form expressions for the probability density function of the distance between two nodes located in heterogeneous concentric geometries, namely a disk or sphere and a surrounding annulus or spherical shell. Two scenarios are considered: (i) both nodes are independently distributed in different regions, disk or sphere and annulus or shell, and (ii) one node is static in the outer region while the other follows the stationary distribution of the random waypoint model in the inner region. The resulting expressions provide a tractable analytical tool for performance evaluation in concentric wireless regions.
Read the full abstract ▾
All authors Nicholas Vaiopoulos, Alexander Vavoulas, Harilaos G. Sandalidis, Konstantinos K. Delibasis
Systems and Control
Equilibrium points and stability of synchronous machine systems
Maryam Khodabakhshloo, Elizabeth L. Ratnam and Ian R. Petersen
This paper investigates
equilibrium points and stability in two synchronous machine configurations: (i) a single generator with an impedance load and (ii) two interconnected machines with co-located loads. We consider both abc and dq reference frames to show that the
equilibrium condition reduces to a cubic
polynomial in the single-machine case and to an 18th- degree
polynomial in the two-machine case. For the single-machine system, Lyapunov stability analysis and linearization based stability analysis are carried out. For the two-machine system, local stability is assessed through linearization and
eigenvalue analysis. Illustrative examples confirm the existence of multiple
equilibria and illustrate the impact of parameter variation on stability. Our results provide insight into the stability of synchronous machine systems.
Read the full abstract ▾
Signal Processing
Two-Timescale Design for Rotatable-Antenna Systems With Imperfect CSI: Rate Analysis and Orientation Optimization
Ziyuan Zheng, Qingqing Wu and Wen Chen
This paper studies uplink multiuser
MIMO with a rotatable
antenna (RA) array under imperfect channel state information (CSI), where each base-station
antenna can adjust its boresight direction within an angular region. To balance performance and control overhead, we propose a two-timescale design: RA orientations are optimized from statistical CSI on a large timescale, while linear receive combiners are updated per coherence block from linear minimum-mean-squared-error (LMMSE) channel estimates. Under this framework, we derive a closed-form use-and-then-forget (UatF)-based rate expression for maximum-ratio combining (MRC) and a closed-form statistical rate surrogate for weighted zero-forcing (wZF) under imperfect CSI, revealing how RA rotation influences useful signal strength, estimation-error-induced self-interference, and multiuser interference. The analysis shows that the orientation minimizing channel-estimation error differs from the rate-maximizing one, and that MRC and wZF prefer different rotation configurations due to their distinct mechanisms of signal aggregation and error-aware user separation. For the resulting non-convex rotation design problems, we develop a projected-gradient
algorithm over a product of spherical caps with explicit derivatives of the required channel statistics and rate metrics. Numerical results verify the accuracy of the large-timescale surrogates and show substantial performance gains from RA optimization.
Read the full abstract ▾
Systems and Control
From open-loop representations to closed-loop feedback implementations in differential games: A numerical case study
Philipp Braun, Timothy L. Molloy, Gal Barkai et al. (+1 more)
Solutions to pursuit-evasion and surveillance-evasion differential games are typically computed and expressed using open-loop representations, with the synthesis of feedback strategies significantly less common. We propose a numerical scheme for obtaining feedback strategies for the recently introduced prying-pedestrian surveillance-evasion differential game. The scheme involves computing feedback strategies as input-output maps approximated via neural networks trained using data obtained from open-loop representations of solutions. Simulations show the effectiveness of neural networks trained with an appropriate learning-loss function. Since optimal feedback strategies are discontinuous, as a second contribution, the potential loss/gain of individual players is subsequently studied for players using sample-and-hold feedback compared to continuous-time feedback.
Read the full abstract ▾
All authors Philipp Braun, Timothy L. Molloy, Gal Barkai, Iman Shames
Systems and Control
Sequential Monte Carlo for Resilient Networks: Assessment, Mitigation, and Generative Modeling
Onel L. A. López and Amirhossein Azarbahram
Resilience is becoming crucial for future wireless networks, which must withstand, adapt to, and recover from rare but potentially cascading disruptions. This paper develops a sequential Monte Carlo (SMC) simulation framework for such systems, in which resilience failures are formulated as path-dependent rare events arising from staged degradation and delayed recovery, and are decomposed into semantically interpretable levels defined by a reaction coordinate. Building on this structure, we present a fixed-level splitting approach with budget-aware population control, enabling efficient estimation of rare non-recovery probabilities. We discuss the potential reuse of SMC checkpoints as representative near-critical states for policy evaluation and simulation-based selection. We further extend the methodology to learned
stochastic simulation by using generative sequence models as restartable surrogates within data-driven digital twins. We showcase the framework in a delay-critical wireless network use case, where SMC substantially improves over standard Monte Carlo in rare-event regimes with both physical and learned simulators.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.CV
VC-FeS: Viewpoint-Conditioned Feature Selection for Vehicle Re-identification in Thermal Vision
Yasod Ginige, Ransika Gunasekara, Darsha Hewavitharana et al. (+3 more)
Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance. However, in this domain, existing methods show poor performance due to high similarity among objects of the same category in the absence of color information (overlooking shape information) and de-emphasized texture information. Furthermore, variability in viewpoint adds more complexity as the features vary from side to side. We address these issues by constructing viewpoint-conditioned feature vectors and area-specific feature comparisons in separate feature spaces. These interventions enable leveraging the advancements of existing RGB-pre-trained ViT feature extractors while effectively adapting them to address the challenges specific to the thermal domain. We test our system with RGBNT100 (IR) vehicle
dataset and a thermal maritime
dataset acquired by us. Our results surpass the state-of-the-art methods by 19.7% and 12.8% for the above
datasets in mAP scores, respectively. We also plan to make our thermal
dataset available, the first of its kind for maritime vessel identification.
Read the full abstract ▾
All authors Yasod Ginige, Ransika Gunasekara, Darsha Hewavitharana, Manjula Ariyarathne, Peshala Jayasekara, Ranga Rodrigo
Audio and Speech Processing
Spatial-Magnifier: Spatial upsampling for multichannel speech enhancement
Dongheon Lee, Ashutosh Pandey, Sanjeel Parekh et al. (+4 more)
While the spatial directivity of multichannel
speech enhancement
algorithms improves with the number of microphones, fitting large capture arrays into real-world edge devices is typically limited by physical constraints. To overcome this limitation, we propose Spatial-Magnifier, a neural network designed to generate virtual microphone (VM) signals from a limited set of real microphone (RM) measurements. Moreover, we introduce the Spatial Audio Representation Learning (SARL) framework, which leverages estimated VM signals and features to condition a downstream
speech enhancement system. Experimental results demonstrate that the proposed framework outperforms existing spatial upsampling baselines across various
speech extraction systems, including end-to-end multichannel
speech enhancement and neural beamforming. The proposed method nearly recovers the oracle performance achieved when all microphones are available.
Read the full abstract ▾
All authors Dongheon Lee, Ashutosh Pandey, Sanjeel Parekh, Daniel Wong, Jacob Donley, Buye Xu, Juan Azcarreta
Signal Processing
SEI-SHIELD: Robust Specific Emitter Identification Under Label Noise Via Self-Supervised Filtering and Iterative Rescue
Ruixiang Zhang, Zinan Zhou, Yezhuo Zhang et al. (+2 more)
Specific Emitter Identification (SEI) provides physical-layer device authentication for wireless communications and Internet of Things (IoT) systems. While deep learning (DL) has significantly advanced SEI performance, label noise severely degrades system reliability in non-cooperative environments. Label noise originates from channel-induced ambiguities, annotation errors, and deliberate data poisoning by intelligent jammers injecting misleading signals. While recent SEI methods attempt to mitigate label noise, they fundamentally rely on corrupted supervised signals to guide sample selection, inevitably leading to confirmation bias and suboptimal feature spaces. To address this challenge, we propose SEI-SHIELD, a robust SEI framework that integrates self-supervised contrastive pre-training with iterative sample selection. Specifically, SEI-SHIELD employs Momentum Contrast (MoCo) with RF-tailored augmentations to extract intrinsically robust, label-independent representations directly from complex-valued I/Q signals. In addition, K-nearest neighbors (KNN)-based noise filtering identifies corrupted samples through neighborhood label consistency analysis in the learned feature space. Furthermore, an iterative rescue mechanism using prediction confidence and prototype cosine similarity progressively recovers correctly labeled hard samples inadvertently discarded during filtering. Comprehensive experiments on the POWDER and ORACLE
datasets demonstrate that SEI-SHIELD achieves state-of-the-art (SOTA) accuracy under various noise rates, substantially outperforming existing noise-robust paradigms, including advanced regularization techniques and sample selection frameworks.
Read the full abstract ▾
All authors Ruixiang Zhang, Zinan Zhou, Yezhuo Zhang, Guangyu Li, Xuanpeng Li
Signal Processing
Multiuser OTFS Channel Parameter Estimation Toward Grid-Independent Regime
Hanning Wang, Rong-Rong Chen and Arman Farhang
We study channel parameter estimation for multiuser orthogonal time frequency space (OTFS) systems in the delay-Doppler (DD) domain. To enable structured parametric estimation, we adopt a multi-user pilot cyclic prefix (MU-PCP) design, which multiplexes users along the Doppler dimension while preserving a separable exponential structure. This structure facilitates high-resolution estimation of fractional delay and Doppler parameters in the multiuser setting. Building on this framework, we extend weighted MUSIC (W-MUSIC) to multiuser OTFS, providing a computationally efficient approach with mild grid dependency, and develop a
matrix pencil (MP)-based method that achieves fully grid-independent delay-Doppler parameter estimation. Numerical results demonstrate the effectiveness of the proposed methods and reveal a robustness-complexity tradeoff: W-MUSIC performs better at low SNR, while MP achieves higher estimation accuracy at moderate-to-high SNR with significantly lower computational complexity.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.LG
ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC
Yurui Du, Pinhao Song, Yutong Hu et al. (+1 more)
A central challenge of visual control with model-based reinforcement learning (RL) is reliable long-horizon planning: long rollouts with learned latent dynamics exhibit branching futures and multi-modal action-value distributions. In addition, compounding model errors amplified by visual occlusions make deep imagination brittle. We present ELVIS, a latent model predictive controller (MPC) designed to make long-horizon planning practical. ELVIS plans in a Dreamer-style recurrent state space model (RSSM) and replaces standard unimodal model predictive path integral (MPPI) with a Gaussian-mixture MPPI that maintains multiple coherent hypotheses over long horizons, avoiding mode averaging under branching rollouts. In parallel, ELVIS stabilizes deep imagination with a shared uncertainty-aware lambda-return: an ensemble of latent critics defines an upper-confidence-bound (UCB) score that gates a time-varying lambda, adaptively trading off bootstrapping versus look-ahead to limit compounding error during planning. The same return is used both to train an actor-critic prior from imagined rollouts and to score candidate trajectories inside GMM-MPPI, aligning RL objectives with the planner's long-horizon optimization. On fourteen DeepMind Control Suite visual tasks, ELVIS establishes state-of-the-art performance compared with TD-MPC2 and DreamerV3. Finally, ELVIS transfers zero-shot to a real-world sand-spraying task with severe occlusions, improving surface-quality metrics and demonstrating robustness beyond simulation.
Read the full abstract ▾
All authors Yurui Du, Pinhao Song, Yutong Hu, Renaud Detry
Systems and Control
Towards Lag Consensus with Noisy Digital Twins Perception in Second-order Multi-agent Cyber-physical Systems
Zhicheng Zhang, Fausto Lizzio, Zhongjun Ma et al. (+1 more)
In this paper, we study second-order lag consensus in multi-
agent cyber-physical networks subject to random noise and input failures, within a framework modeling the interactions and perceptions between physical twins and digital twins. We propose a lag consensus protocol and establish sufficient conditions for the mean-square (exponential) stability of the resulting
stochastic lag error dynamics. The consensus criteria are derived via Lyapunov analysis using the Itô formula, ensuring robustness to random perturbations and intermittent input failures. Numerical examples illustrate the effectiveness of the proposed method.
Read the full abstract ▾
All authors Zhicheng Zhang, Fausto Lizzio, Zhongjun Ma, Masaaki Nagahara
Signal Processing
RF-Analyzer: Can Vision-Language Models Learn RF Understanding from Synthetic Data?
Anis Bara, Lina Bariah, Hang Zou et al. (+2 more)
Understanding the wireless spectrum is a fundamen- tal requirement for intelligent communication systems, however, interpreting spectrograms requires extracting multiple physical attributes and
reasoning about signal structure, which is a capability that is not achieved by traditional ML approaches. Recent advances in
vision-
language models (VLMs) demonstrated the possibility of learning such interpretation capabilities directly from data. This paper investigates whether VLMs can learn this capability from synthetic data alone, and more importantly, whether such learned representations generalize to real over-the- air RF environments. To address this question, we introduce RF-Analyzer, an SDR-to-AI analysis platform that integrates live spectrum captures associated with the corresponding VLM- based interpretation, enabling direct evaluation of VLMs outputs on live over-the-air signals. Using this platform, we assess a model trained exclusively on synthetic spectrogram data with general-purpose baselines. To enable systematic analysis, we establish a
benchmark framework comprising three metrics, Physical Attribute Extraction Score (PAES),
Prompt Leakage Rate (PLR), and
hallucination count, to assess signal understanding and grounding. The obtained results demonstrate that VLMs trained on synthetic spectrogram data can generalize to real RF environments, particularly for extracting physical signal attributes such as spectral occupancy, temporal behavior, and SNR. This indicates that synthetic data is sufficient for learning transferable representations of RF signal structure. However, this generalization is limited due to the fact that synthetic training does not provide reliable semantic grounding without contextual priors. In particular, generalization breaks under conditions that are not covered in the synthetic distribution, particularly low-SNR regimes
Read the full abstract ▾
All authors Anis Bara, Lina Bariah, Hang Zou, Brahim Mefgouda, Merouane Debbah
Systems and Control
Adaptive MPC for Constrained Trajectory Tracking of Uncertain LTI System with Input-Rate Limits
Bishal Dey, Abhishek Dhar, Sumit kr. Pandey et al. (+1 more)
This paper addresses the trajectory-tracking problem for discrete-time linear time-invariant systems with bounded parametric uncertainty, subject to hard constraints on system states, control inputs, and input rates. Unlike existing methods, which often consider only partial uncertainty, omit input-rate or state constraints, or focus on regulation problems, this work provides a systematic adaptive model predictive control (MPC) solution for constrained trajectory tracking under full parametric uncertainty. Determining the control input required to achieve zero tracking error under unknown parameters is challenging. Simultaneously, trajectory tracking under uncertainty with input-rate constraints induces temporal coupling in the control sequence, resulting in a time-varying admissible control set and rendering standard recursive feasibility arguments inapplicable. These challenges are overcome by systematically utilizing the estimated system parameters, coupled with a suitably designed adaptive learning process within a reformulated MPC framework. The recursive feasibility of the proposed MPC optimization routine is then rigorously established despite the time-varying admissible control set induced by input-rate constraints. Closed-loop stability is guaranteed via Lyapunov-based analysis, ensuring convergence of the tracking error and boundedness of system states. Simulation results validate the effectiveness of the pr
Read the full abstract ▾
All authors Bishal Dey, Abhishek Dhar, Sumit kr. Pandey, Anindita Sengupta
Signal Processing
Coupling-Aware Pinching-Antenna Radiation for Heterogeneous NOMA Users
Ishtiaque Ahmed, Leila Musavian and Haris Pervaiz
Pinching-
antennas systems (PASS) offer reconfigurable wireless channels via low-cost dielectric mediums by creating line-of-sight (LoS) communication links. Most of the existing PASS cover mechanisms of equal power pinching
antennas for conventional bit-based communication, whereas flexible radiation control remains largely unexplored, particularly for heterogeneous semantic and bit users. In this paper, we investigate the performance of semantic communication (SC) using an adjustable radiation model over PASS, where the coupling strength between the dielectric waveguide and each pinching
antenna is determined by the
antenna-waveguide spacing. Specifically, the non-orthogonal multiple access (NOMA)-assisted heterogeneous users are served by multiple pinching
antennas using spacing-controlled adjustable radiation ratios. Uunder this setting, we maximize the semantic spectral efficiency (SE) subject to the bit-user quality of service (QoS) requirement, successive interference cancellation (SIC) feasibility, and the minimum adjacent
antennas spacing constraint. An alternating optimization (AO) approach optimizes users power allocation and positions of pinching
antennas. Simulations demonstrate the effectiveness of the proportional power PASS model in providing higher semantic SE in different geometrical and numerical settings compared to conventional
benchmark schemes.
Read the full abstract ▾
Signal Processing
Multi-AP Cooperative Beamforming for Cell-Free ISAC Networks: Balancing Communication SINR and Sensing SCNR
Jijin Guo, Lixin Li, Yufeng Zheng et al. (+3 more)
Cell-free integrated sensing and communication (
ISAC) systems are facing the resource allocation challenges due to the deployment of access points (APs) and conflicting beamforming requirements between the communication and sensing functions. Unlike traditional
ISAC architectures, the geographic distribution of APs introduces coordination complexity and resource-sharing conflicts that existing single-objective methods cannot adequately address. To address this challenge, we formulate an optimization problem for multi-AP cooperative beamforming that maximizes the sensing signal-to-clutter-plus-noise ratio (SCNR) under the communication rate constraints. The non-convex quadratically constrained quadratic program is transformed into a tractable convex semidefinite program via semidefinite relaxation, enabling efficient
polynomial-time solutions and overcoming the local convergence limitations of traditional alternating optimization approaches. Simulation results demonstrate that the proposed approach achieves superior performance in both communication signal-to-interference-plus-noise ratio (SINR) and SCNR compared to existing schemes, confirming its effectiveness for balancing dual-functional objectives.
Read the full abstract ▾
All authors Jijin Guo, Lixin Li, Yufeng Zheng, Dongwei Zhao, Wensheng Lin, Zhu Han