Signal Processing
Near-Field Multiuser Beam Training for XL-MIMO: An End-to-End Interference-Aware Approach with Pilot Limitations
Xinyang Li, Songjie Yang, Xiang Ling et al. (+3 more)
Near-field propagation in extremely large-scale
MIMO (XL-
MIMO) enlarges the beam training (BT) search space by introducing an additional range dimension, which makes conventional codebook-based beam sweeping prohibitively expensive under limited pilot resources, especially for multiuser sub-connected hybrid architectures. This letter proposes a deep-learning-based interference-aware multiuser BT framework (DL-IABT) that directly predicts analog beam indices from a small number of uplink sensing measurements. By exploiting a subarray-level approximation, a far-field codebook is adopted to represent each subarray response with negligible mismatch. To enable end-to-end (E2E) learning, we derive a variant-MSE surrogate loss by eliminating the digital precoder through a closed-form MMSE solution from KKT conditions, which implicitly accounts for multiuser interference (MUI). The proposed network integrates a complex-valued sensing front-end, a shared complex-valued encoder, a
Transformer-based multiuser predictor, and a scalable Gumbel–Softmax beam selection head. Simulation results show that DL-IABT achieves near-optimal sum-rate performance while providing markedly higher effective throughput under pilot overhead constraints.
Read the full abstract ▾
All authors Xinyang Li, Songjie Yang, Xiang Ling, Jianhui Song, Yibo Wang, Hua Chen
Audio and Speech Processing · Cross-listed from cs.SD
Resurfacing Paralinguistic Awareness in Large Audio Language Models
Hao Yang, Minghan Wang, Tongtong Wu et al. (+3 more)
Large Audio
Language Models (LALMs) have expanded the interaction with human to
speech modality, which introduces great interactive potential, due to the paralinguistic cues implicitly indicating the user context. However, building on the current content-centred paradigm, LALMs usually neglect such paralinguistic cues and respond solely based on query content. In this work, to resurface the paralinguistic awareness in LALMs, we introduce five diverse layer-wise analyses to jointly identify paralinguistic layers and semantic understanding layers. Based on these insights, we propose a paralinguistic-enhanced fine-tuning (PE-FT) protocol accordingly to equip LALMs with paralinguistic-aware capabilities, including (1) selective-layer fine-tuning, and (2) an auxiliary dual-level classification head. Our experiments demonstrate that PE-FT protocol efficiently and effectively resurfaces the paralinguistic awareness, even surpassing the performance of the all-layer fine-tuning strategy.
Read the full abstract ▾
All authors Hao Yang, Minghan Wang, Tongtong Wu, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari
Systems and Control
Emergency-Aware and Frequency-Constrained HVDC Planning for A Multi-Area Asynchronously Interconnected Grid
Yiliu He, Haiwang Zhong, Grant Ruan et al. (+2 more)
High-voltage direct current (HVDC) technology has played a crucial role for long-distance transmission of renewable power generation. However, the integration of large-capacity HVDC lines introduces significant frequency security challenges during HVDC fault emergencies. This paper proposes an emergency-aware and frequency-constrained HVDC planning method to optimize the capacity of inter-area HVDC tie-lines in a multi-area asynchronously interconnected grid. Firstly, a coordinated emergency frequency control scheme is proposed to allocate the emergency control resources during HVDC faults. Then, an enhanced system frequency response model integrating event-driven emergency frequency control is developed and a weighted oblique decision tree approach is employed to extract frequency nadir security constraints. The proposed planning model considers all potential HVDC fault emergencies while treating candidate HVDC capacities as decision variables. Simulation results demonstrate superior performance in balancing economic efficiency with frequency security requirements, providing a practical solution for inter-area HVDC planning.
Read the full abstract ▾
All authors Yiliu He, Haiwang Zhong, Grant Ruan, Yan Xu, Chongqing Kang
Signal Processing
Indirect and Direct Multiuser Hybrid Beamforming for Far-Field and Near-Field Communications: A Deep Learning Approach
Xinyang Li, Songjie Yang, Boyu Ning et al. (+3 more)
Hybrid beamforming for extremely large-scale multiple-input multiple-output (XL-
MIMO) systems is challenging in the near field because the channel depends jointly on angle and distance, and the multiuser interference (MUI) is strong. Existing deep learning methods typically follow either a decoupled design that optimizes analog beamforming without explicitly accounting for MUI, or an end-to-end (E2E) joint analog-digital optimization that can be unstable under nonconvex constant-modulus (CM), pronounced analog-digital coupling, and gradient pattern of sum-rate loss. To address both issues, we develop a complex-valued E2E framework based on a variant minimum mean square error (variant-MMSE) criterion, where the digital precoder is eliminated in closed form via Karush-Kuhn-Tucker (KKT) conditions so that analog learning is trained with a stable objective. The network employs a grouped complex-convolution sensing front-end for uplink (UL) measurements, a shared complex multi-layer perceptron (MLP) for per-user feature extraction, and a merged constant-modulus head to output the analog precoder. In the indirect mode, the network designs hybrid beamformers from estimated channel state information (CSI). In the direct mode where explicit CSI is unavailable, the network learns the sensing operator and the analog mapping from short pilots, after which additional pilots estimate the equivalent channel and enable a KKT closed-form digital precoder. Simulations show that the indirect mode approaches the performance of iterative variant-MMSE optimization with a complexity reduction proportional to the
antenna number. In the direct mode, the proposed method improves spectral efficiency over sparse-recovery pipelines and recent deep learning baselines under the same pilot budget.
Read the full abstract ▾
All authors Xinyang Li, Songjie Yang, Boyu Ning, Zongmiao He, Xiang Ling, Chau Yuen
Systems and Control
Risk-Based Dynamic Thermal Rating in Distribution Transformers via Probabilistic Forecasting
Scott Angus, Jethro Browell, David Greenwood et al. (+1 more)
Low voltage (LV) distribution
transformers face accelerating demand growth while replacement lead times and costs continue to rise, making improved utilisation of existing assets essential. Static and conservative protection devices (PDs) in distribution
transformers are inflexible and limit the available headroom of the
transformer. This paper presents a probabilistic framework for dynamically
forecasting optimal thermal protection settings. The proposed approach directly predicts the day-ahead scale factor which maximises the dynamic thermal rating of the
transformer from historical load, temperature, and metadata using clustered
quantile regression models trained on 644 UK LV
transformers. Probabilistic
forecasting quantifies overheating risk directly through the prediction percentile, enabling risk-informed operational decisions. Results show a 10–12% additional capacity gain compared to static settings, with hotspot temperature risk matching the selected percentile, including under realistic temperature forecast errors. These results demonstrate a practical approach for distribution network operators to take advantage of PDs with adaptive settings to maximise capacity and manage risk on operational time scales.
Read the full abstract ▾
All authors Scott Angus, Jethro Browell, David Greenwood, Matthew Deakin
Signal Processing
Beyond the Limits of Rigid Arrays: Flexible Intelligent Metasurfaces for Next-Generation Wireless Networks
Ahmed Magbool, Vaibhav Kumar, Marco Di Renzo et al. (+1 more)
Following recent advances in flexible electronics and programmable metasurfaces, flexible intelligent metasurfaces (FIMs) have emerged as a promising enabling technology for next-generation wireless networks. A FIM is a morphable electromagnetic surface capable of dynamically adjusting its physical geometry to influence the radiation and propagation of electromagnetic waves. Unlike conventional rigid arrays, FIMs introduce an additional spatial degree of design freedom enabled by mechanical flexibility, which can enhance beamforming, spatial focusing, and adaptation to dynamic wireless environments. This added capability enables wireless systems to shape the propagation environment not only through electromagnetic tuning but also through controllable
geometric reconfiguration. This article explores the potential of FIMs for next-generation wireless networks. We first introduce the main hardware architectures of FIMs and explain how they can be integrated into wireless communication systems. We then present representative application scenarios, highlighting the advantages of FIMs for future wireless networks and comparing them with other emerging flexible wireless technologies. To illustrate their potential impact, we present case studies comparing FIM-enabled architectures with conventional rigid-array systems, demonstrating the performance gains enabled by surface flexibility for both communication and sensing applications. Finally, we discuss key opportunities, practical challenges, and open research directions that must be addressed to fully realize the potential of FIM technology in future wireless communication systems.
Read the full abstract ▾
All authors Ahmed Magbool, Vaibhav Kumar, Marco Di Renzo, Mark F. Flanagan
Audio and Speech Processing
Silent Speech Interfaces in the Era of Large Language Models: A Comprehensive Taxonomy and Systematic Review
Kele Xu, Yifan Wang, Ming Feng et al. (+5 more)
Human-computer interaction has traditionally relied on the acoustic channel, a dependency that introduces systemic vulnerabilities to environmental noise,
privacy constraints, and physiological
speech impairments. Silent
Speech Interfaces (SSIs) emerge as a transformative paradigm that bypasses the acoustic stage by decoding linguistic intent directly from the neuro-muscular-articulatory continuum. This review provides a high-level synthesis of the SSI landscape, transitioning from traditional transducer-centric analysis to a holistic intent-to-execution taxonomy. We systematically evaluate sensing modalities across four critical physiological interception points: neural oscillations, neuromuscular activation, articulatory kinematics (ultrasound/magnetometry), and pervasive active probing via acoustic or
radio-frequency sensing. Critically, we analyze the current paradigm shift from heuristic signal processing to Latent Semantic
Alignment. In this new era, Large
Language Models (LLMs) and deep generative architectures serve as high-level linguistic priors to resolve the “informational sparsity” and non-stationarity of biosignals. By mapping fragmented physiological gestures into structured semantic latent spaces, modern SSI frameworks have, for the first time, approached the Word Error Rate usability threshold required for real-world deployment. We further examine the transition of SSIs from bulky laboratory instrumentation to “invisible interfaces” integrated into commodity-grade wearables, such as earables and smart glasses. Finally, we outline a strategic roadmap addressing the “user-dependency paradox” through self-supervised foundation models and define the ethical boundaries of “neuro-security” to protect cognitive liberty in an increasingly interfaced world.
Read the full abstract ▾
All authors Kele Xu, Yifan Wang, Ming Feng, Qisheng Xu, Wuyang Chen, Yutao Dou, Cheng Yang, Huaimin Wang
Image and Video Processing · Cross-listed from cs.CR
On the Possible Detectability of Image-in-Image Steganography
Antoine Mallet and Patrick Bas
This paper investigates the detectability of popular imagein-image steganography schemes [1, 2, 3, 4, 5]. In this paradigm, the payload is usually an image of the same size as the Cover image, leading to very high
embedding rates. We first show that the
embedding yields a mixing process that is easily identifiable by independent component analysis. We then propose a simple, interpretable steganalysis method based on the first four moments of the independent components estimated from the wavelet decomposition of the images, which are used to distinguish between the distributions of Cover and Stego components. Experimental results demonstrate the efficiency of the proposed method, with eight-dimensional input vectors attaining up to 84.6% accuracy. This vulnerability analysis is supported by two other facts: the use of keyless extraction networks and the high detectability w.r.t. classical steganalysis methods, such as the SRM combined with support vector machines, which attains over 99% accuracy.
Read the full abstract ▾
Image and Video Processing
Deep Learning-based Assessment of the Relation Between the Third Molar and Mandibular Canal on Panoramic Radiographs using Local, Centralized, and Federated Learning
Johan Andreas Balle Rubak, Sara Haghighat, Sanyam Jain et al. (+9 more)
Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar-canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while
federated learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy = 0.782), FL showed intermediate performance (AUC 0.757; accuracy = 0.703), and LL generalized poorly across clients (AUC range = 0.619-0.734; mean = 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused
attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a
privacy-preserving alternative that outperforms LL.
Read the full abstract ▾
All authors Johan Andreas Balle Rubak, Sara Haghighat, Sanyam Jain, Mostafa Aldesoki, Akhilanand Chaurasia, Sarah Sadat Ehsani, Faezeh Dehghan Ghanatkaman, Ahmad Badruddin Ghazali, Julien Issa, Basel Khalil, Rishi Ramani, Ruben Pauwels
Audio and Speech Processing
Reconstruction of the Vocal Tract from Speech via Phonetic Representations Using MRI Data
Sofiane Azzouz, Pierre-André Vuissoz and Yves Laprie
Articulatory acoustic inversion aims to reconstruct the complete geometry of the vocal tract from the
speech signal. In this paper, we present a comparative study of several levels of phonetic
segmentation accuracy, together with a comparison to the baseline introduced in our previous work, which is based on Mel-Frequency Cepstral Coefficients (MFCCs). All the approaches considered are based on a denoised
speech signal and aim to investigate the impact of incorporating phonetic information through three successive levels: an uncorrected automatic transcription, a temporally aligned phonetic
segmentation, and an expert manual correction following
alignment. The models are trained to predict articulatory contours extracted from vocal tract MRI images using an automatic contour tracking method. The results show that, among the models relying on phonetic representations, manual correction after
alignment yields the best performance, approaching that of the baseline.
Read the full abstract ▾
Audio and Speech Processing
Acoustic-to-Articulatory Inversion of Clean Speech Using an MRI-Trained Model
Sofiane Azzouz, Pierre-André Vuissoz and Yves Laprie
Articulatory acoustic inversion reconstructs vocal tract shapes from
speech. Real-time
magnetic resonance imaging (rt-MRI) allows simultaneous acquisition of both the acoustic
speech signal and articulatory information. Besides the complexity of rt-MRI acquisition, the recorded audio is heavily corrupted by scanner noise and requires denoising to be usable. For practical use, it must be possible to invert
speech recorded without MRI noise. In this study, we investigate the use of
speech recorded in a clean acoustic environment as an alternative to denoised MRI
speech. To this end we compare two signals from the same speaker with identical sentences which are aligned using phonetic
segmentation. A model trained on denoised MRI
speech is evaluated on both denoised MRI and clean
speech. We also assess a model trained and tested only on clean
speech. Results show that clean
speech supports articulatory inversion effectively, achieving an RMSE of 1.56 mm, close to MRI-based performance.
Read the full abstract ▾
Audio and Speech Processing
ReDimNet2: Scaling Speaker Verification via Time-Pooled Dimension Reshaping
Ivan Yakovlev and Anton Okhotnikov
We present ReDimNet2, an improved neural network architecture for extracting utterance-level speaker representations that builds upon the ReDimNet dimension-reshaping framework. The key modification in ReDimNet2 is the introduction of pooling over the time dimension within the 1D processing pathway. This operation preserves the nature of the 1D feature space, since 1D features remain a reshaped version of 2D features regardless of temporal resolution, while enabling significantly more aggressive scaling of the channel dimension without proportional compute increase. We introduce a family of seven model configurations (B0-B6) ranging from 1.1M to 12.3M parameters and 0.33 to 13 GMACS. Experimental results on VoxCeleb1
benchmarks demonstrate that ReDimNet2 improves the Pareto front of computational cost versus accuracy at every scale point compared to ReDimNet, achieving 0.287% EER on Vox1-O with 12.3M parameters and 13 GMACS.
Read the full abstract ▾
Signal Processing
On the Distribution of Matched Filtering with Continuous Aperture Arrays
Amy S. Inwood, Abdulla Firag, Peter J. Smith et al. (+1 more)
Continuous aperture arrays (CAPAs) provide a theoretical upper bound on the performance of densely packed
antenna arrays, but their analysis is limited by the lack of closed-form signal-to-noise ratio (SNR) distributions under realistic fading conditions. This paper derives accurate analytical expressions for the matched-filter SNR distribution of one-dimensional CAPAs in correlated Rayleigh environments under both the sinc and Jakes correlation models using the Karhunen-Loeve expansion. By applying a truncated hypoexponential model, we obtain accurate approximations for the probability density function and cumulative distribution function of the SNR that closely match simulations, including the outage probability region where precise characterization is critical. Compared to a standard gamma approximation, our approach provides significantly improved accuracy in this regime. Additionally, the CAPA system considered is shown to outperform discrete
antenna arrays. The derived expressions enable tractable and accurate evaluation of CAPAs under practical channel models.
Read the full abstract ▾
All authors Amy S. Inwood, Abdulla Firag, Peter J. Smith, Michail Matthaiou
Signal Processing
BER Analysis and Optimization for Continuous RIS-Enabled NOMA
Mahmoud AlaaEldin, Amy S. Inwood, Peter J. Smith et al. (+1 more)
This letter investigates a novel uplink (UL) system that integrates power-domain non-orthogonal multiple access (PD-NOMA) with a continuous reconfigurable intelligent surface (CRIS). We analyze the effective CRIS-assisted channels under spatially correlated fading to accurately approximate the characteristic function of the cascaded channel. This allows the derivation of an expression for the bit error rate (BER), a key performance metric for UL PD-NOMA. We further utilize the derived BER expressions to introduce a joint optimization framework that minimizes the average BER via UL power allocation and dynamic RIS partitioning among the users. The analytical results are validated by simulations, and show that the proposed optimization scheme eliminates the BER floors that are associated with UL NOMA. The results also confirm the superiority of the optimized CRIS-NOMA scheme over conventional orthogonal multiple access (OMA) and non-optimized UL NOMA schemes.
Read the full abstract ▾
All authors Mahmoud AlaaEldin, Amy S. Inwood, Peter J. Smith, Michail Matthaiou
Signal Processing
Dimensional Scaling Laws for Continuous Fluid Antenna Systems
Peter J. Smith, Amy S. Inwood, Michail Matthaiou et al. (+1 more)
Consider the signal-to-noise ratio (SNR) of a continuous fluid
antenna system (CFAS) operating over a Rayleigh fading channel. In this paper, we extend traditional system assumptions and consider spatially coherent isotropic correlation, continuous positioning of the
antenna rather than discrete, and the use of multi-dimensional space (1D, 2D and 3D). By focusing on the upper tail of the received SNR distribution (the high SNR probability (HSP)), we are able to derive asymptotically exact closed-form formulas for the HSP. Finally, these results lead to scaling laws which describe the increase in the HSP as we employ more dimensions and the optimal CFAS dimensions.
Read the full abstract ▾
All authors Peter J. Smith, Amy S. Inwood, Michail Matthaiou, Rajitha Senanayake
Systems and Control · Cross-listed from math.OC
Exploiting Parallelism in a QPALM-based Solver for Optimal Control
Pieter Pas, Kristoffer Fink Løwenstein, Daniele Bernardini et al. (+1 more)
We discuss the opportunities for parallelization in the recently proposed QPALM-OCP
algorithm, a solver tailored to quadratic programs arising in optimal control. A significant part of the computational work can be carried out independently for the different stages in the optimal control problem. We exploit this specific structure to apply parallelization and vectorization techniques in an optimized C++ implementation of the method. Results for optimal control
benchmark problems and comparisons to the original QPALM method are provided.
Read the full abstract ▾
All authors Pieter Pas, Kristoffer Fink Løwenstein, Daniele Bernardini, Panagiotis Patrinos
Systems and Control
Rotatable Antenna Enabled Covert Communication
Qi Dai, Beixiong Zheng, Yanhua Tan et al. (+4 more)
Unlike conventional fixed-
antenna architectures, rotatable
antenna (RA) has shown great potential in enhancing wireless communication performance by exploiting additional spatial degrees of freedom (DoFs) in a cost-effective manner. In this letter, we propose a novel RA-enabled covert communication system, where an RA array-based transmitter (Alice) sends covert information to a legitimate user (Bob) in the presence of multiple wardens (Willies). To maximize the covert rate, we optimize the transmit beamforming vector and the rotational angles of individual RAs, subject to the constraints on covertness, transmit power, and
antenna rotational range. To address the non-convex formulated problem, we decompose it into two subproblems and propose an efficient alternating optimization (AO)
algorithm to solve the two subproblems iteratively, where the second-order cone programming (SOCP) method and successive convex approximation (SCA) approach are applied separately. Simulation results demonstrate that the proposed RA-enabled covert communication system can provide significantly superior covertness performance to other
benchmark schemes.
Read the full abstract ▾
All authors Qi Dai, Beixiong Zheng, Yanhua Tan, Weidong Mei, Shiqi Gong, Jie Tang, Chengwen Xing
Audio and Speech Processing
Affect Decoding in Phonated and Silent Speech Production from Surface EMG
Simon Pistrosch, Kleanthis Avramidis, Zhao Ren et al. (+7 more)
The expression of affect is integral to spoken communication, yet, its link to underlying articulatory execution remains unclear. Measures of articulatory muscle activity such as EMG could reveal how
speech production is modulated by
emotion alongside acoustic
speech analyses. We investigate affect decoding from facial and neck surface electromyography (sEMG) during phonated and silent
speech production. For this purpose, we introduce a
dataset comprising 2,780 utterances from 12 participants across 3 tasks, on which we evaluate both intra- and inter-subject decoding using a range of features and model
embeddings. Our results reveal that EMG representations reliably discriminate frustration with up to 0.845 AUC, and generalize well across articulation modes. Our ablation study further demonstrates that affective signatures are embedded in facial motor activity and persist in the absence of phonation, highlighting the potential of EMG sensing for affect-aware silent
speech interfaces.
Read the full abstract ▾
All authors Simon Pistrosch, Kleanthis Avramidis, Zhao Ren, Tiantian Feng, Jihwan Lee, Monica Gonzalez-Machorro, Anton Batliner, Tanja Schultz, Shrikanth Narayanan, Björn W. Schuller
Audio and Speech Processing
RAF: Relativistic Adversarial Feedback For Universal Speech Synthesis
Yongjoon Lee and Jung-Woo Choi
We propose Relativistic
Adversarial Feedback (RAF), a novel training objective for GAN vocoders that improves in-domain fidelity and generalization to unseen scenarios. Although modern GAN vocoders employ advanced architectures, their training objectives often fail to promote generalizable representations. RAF addresses this problem by leveraging
speech self-supervised learning models to assist discriminators in evaluating sample quality, encouraging the generator to learn richer representations. Furthermore, we utilize relativistic pairing for real and fake waveforms to improve the modeling of the training data distribution. Experiments across multiple
datasets show consistent gains in both objective and subjective metrics on GAN-based vocoders. Importantly, the RAF-trained BigVGAN-base outperforms the LSGAN-trained BigVGAN in perceptual quality using only 12% of the parameters. Comparative studies further confirm the effectiveness of RAF as a training framework for GAN vocoders.
Read the full abstract ▾
Audio and Speech Processing
SEMamba++: A General Speech Restoration Framework Leveraging Global, Local, and Periodic Spectral Patterns
Yongjoon Lee and Jung-Woo Choi
General
speech restoration demands techniques that can interpret complex
speech structures under various distortions. While State-Space Models like SEMamba have advanced the state-of-the-art in
speech denoising, they are not inherently optimized for critical
speech characteristics, such as spectral periodicity or multi-resolution frequency analysis. In this work, we introduce an architecture tailored to incorporate
speech-specific features as inductive biases. In particular, we propose the Global, Local, and Periodic (GLP) module, a frequency feature extraction block that effectively and efficiently leverages the properties of frequency bins. Then, we design a multi-resolution parallel time-frequency dual-processing block to capture diverse spectral patterns, and a learnable mapping to further enhance model performance. With all our ideas combined, the proposed SEMamba++ achieves the best performance among multiple baseline models while remaining computationally efficient.
Read the full abstract ▾
Signal Processing
Machine Learning-Based Analysis of Critical Process Parameters Influencing Product Quality Defects: A Real-World Case Study in Manufacturing
Sukumaran Rajasekaran, Ebru Turanoglu Bekar, Kanika Gandhi et al. (+2 more)
Quality control is an essential operation in manufacturing, ensuring products meet the necessary standards of quality, safety, and reliability. Traditional methods, such as visual inspections, measurements, and statistical techniques, help meet these standards but are often time-consuming, costly, and reactive. With the advent of AI/ML, manufacturers can shift from reactive to proactive approaches in quality control. This study applies ML-based models for predictive quality control in a real-world manufacturing setting. The case company produces castings for powertrain components in heavy vehicles, where poor control of core-making process parameters leads to costly defects. ML models were developed by analyzing data from two core-making machines, their processes, and maintenance logs to identify parameters associated with casting defects, enabling the prediction and prevention of potential defects before they occur. The results demonstrated good accuracy rates, helping quality and production teams identify and eliminate defective cores and thereby improving product quality and production efficiency.
Read the full abstract ▾
All authors Sukumaran Rajasekaran, Ebru Turanoglu Bekar, Kanika Gandhi, Sabino Francesco Roselli, Mohan Rajashekarappa
Signal Processing
Learnable Template Matching Approach for Micro-Deformation Monitoring based on Integrated Sensing and Communication Platform
Zhuoyang Liu, Yixiang Luomei and Feng Xu
Existing integrated sensing and communication (
ISAC) platforms fail to fully utilize the shared spectrum and aperture resources for sensing, resulting in poor sensing performance. Specifically, weak target sensing on the
ISAC platform, such as micro-deformation monitoring (mDM), suffers from inaccurate measurements due to poor sensing quality. In this paper, we propose an AI-assisted approach to alleviate the effect of poor sensing quality in the
ISAC system by effectively removing the clutter. We begin by modeling the environment clutter model as a combination of the deterministic and
stochastic signals to represent urban coverage scenarios around the base station (BS). A clutter suppression optimization problem is formulated to extract the micro-deformation displacement (mDD) from the original
ISAC signals. We then propose a learnable template-matching (LTM) approach to mitigate the influences of clutters, thereby enhancing sensing quality. In particular, the electromagnetic (EM) signal feature of the mDD is embedded into the network to strengthen the mDM signal, and clutter filters are incorporated to suppress environmental clutter. Numerical results illustrate the superiority of our proposed approach concerning convergence speed and accuracy in mDD prediction. By deploying our approach to the BS measurement, the simulation-only trained LTM exhibits impressive performance in environment clutter separation and mDD estimation.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.LG
Hybrid Energy-Aware Reward Shaping: A Unified Lightweight Physics-Guided Methodology for Policy Optimization
Qijun Liao, Jue Yang, Yiting Kang et al. (+3 more)
Deep reinforcement learning for continuous control often suffers from high variance, low energy efficiency, and poor generalization under distribution shift, as purely data-driven exploration ignores available physical structure. This paper proposes Hybrid Energy-Aware Reward Shaping (H-EARS), which encodes dominant energy terms – assumed known a priori – directly as reward potentials at O(n) per-step computation. H-EARS decomposes the shaping potential into task-oriented and energy-based components, supplemented by an action regularization term that deliberately modifies the optimization objective to enforce energy-efficient control. A complete theoretical foundation is established: functional independence of shaping and regularization, energy-based gradient enrichment under positive-definite Hessian conditions, convergence guarantees under function approximation, and approximate potential error bounds. Across four continuous control
benchmarks and four baseline
algorithms, H-EARS achieves consistent gains in convergence speed, policy stability, and final performance. High-fidelity vehicle simulations validate applicability in safety-critical settings under extreme road conditions.
Read the full abstract ▾
All authors Qijun Liao, Jue Yang, Yiting Kang, Xinxin Zhao, Yong Zhang, Mingan Zhao
Systems and Control
Multi-Agent Reinforcement Learning for UAV-Based Chemical Plume Source Localization
Zhirun Li, Derek Hollenbeck, Ruikun Wu et al. (+4 more)
Undocumented orphaned wells pose significant health and environmental risks to nearby communities by releasing toxic gases and contaminating water sources, with methane emissions being a primary concern. Traditional survey methods such as magnetometry often fail to detect older wells effectively. In contrast, aerial in-situ sensing using unmanned aerial vehicles (
UAVs) offers a promising alternative for methane emission detection and source localization. This study presents a robust and efficient framework based on a multi-
agent deep reinforcement learning (MARL)
algorithm for the chemical plume source localization (CPSL) problem. The proposed approach leverages virtual anchor nodes to coordinate
UAV navigation, enabling collaborative sensing of gas concentrations and wind velocities through onboard and shared measurements. Source identification is achieved by analyzing the historical trajectory of anchor node placements within the plume. Comparative evaluations against the fluxotaxis method demonstrate that the MARL framework achieves superior performance in both localization accuracy and operational efficiency.
Read the full abstract ▾
All authors Zhirun Li, Derek Hollenbeck, Ruikun Wu, Michelle Sherman, Sihua Shao, Xiang Sun, Mostafa Hassanalian
Signal Processing
Exploiting Skyrmions in Free-Space Optical Communication
Ryosuke Hara, Satoshi Iwamoto and Shinya Sugiura
In this paper, we propose a novel free-space optical (FSO) communication system utilizing optical skyrmions. We introduce a scheme referred to as skyrmion number modulation (SkM), which employs index modulation by encoding information onto the skyrmion number, a topological invariant preserved during free-space propagation. This topological nature offers the potential for inherent robustness against atmospheric
turbulence-induced wavefront distortions, which limit the performance of conventional FSO systems. More specifically, we demonstrate that the fluctuation of the received skyrmion number is mitigated by a proposed intensity-based masking technique. Finally, our performance analysis based on a discrete memoryless channel framework confirms that the proposed system exhibits near-ideal robustness under weak
turbulence and supports high-order modulation in moderate regimes.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Forward and Backward Reachability Analysis of Closed-loop Recurrent Neural Networks via Hybrid Zonotopes
Yuhao Zhang and Xiangru Xu
Recurrent neural networks (RNNs) are widely employed to model complex dynamical systems due to their hidden-state structure, which inherently captures temporal dependencies. This work presents a hybrid zonotope-based approach for computing exact forward and backward reachable sets of closed-loop RNN systems with ReLU activation functions. The method formulates state-pair sets to compute reachable sets as hybrid zonotopes without requiring unrolling. To improve scalability, a tunable relaxation scheme is proposed that ranks unstable ReLU units across all layers using a triangle-area score and selectively applies convex relaxations within a fixed binary limit in the hybrid zonotopes. This scheme enables an explicit tradeoff between computational complexity and approximation accuracy, with exact reachability as a special case. In addition, a sufficient condition is derived to certify the safety of closed-loop RNN systems. Numerical examples demonstrate the effectiveness of the proposed approach.
Read the full abstract ▾
Signal Processing
Standard Condition Number-Based Detection for MIMO ISAC Systems under Noise Uncertainty
Alex Obando, Tharindu Udupitiya, Saman Atapattu et al. (+1 more)
This paper presents a unified analytical and optimization framework for Standard Condition Number (SCN)-based detection in
MIMO Integrated Sensing and Communication (
ISAC) systems operating under noise uncertainty. Conventional detectors such as the Likelihood Ratio Test (LRT) and Energy Detector (ED) suffer from false-alarm inflation when interference or jamming alters the noise covariance. To overcome this limitation, the SCN detector, defined as the ratio of the largest to smallest
eigenvalues of the sample covariance
matrix is analytically characterized for the first time in an
ISAC setting. Closed-form expressions for the false-alarm and detection probabilities are derived using random
matrix theory for a two-
antenna sensing receiver and generalized to arbitrary
MIMO dimensions. The analysis proves that the SCN maintains a constant false alarm rate (CFAR) property and remains resilient to covariance mismatch, providing theoretical justification for its robustness in dynamic environments. Leveraging these results, a tractable
ISAC power-allocation problem is formulated to minimize total detection error subject to communication rate and power constraints, yielding an interpretable sequential solution. Numerical evaluations verify the theory and demonstrate that the proposed SCN detector consistently outperforms LRT and
eigenvalue-based
benchmarks, particularly under strong interference and jamming typical of modern multiuser networks.
Read the full abstract ▾
All authors Alex Obando, Tharindu Udupitiya, Saman Atapattu, Kandeepan Sithamparanathan
Systems and Control
ISAC-Enabled Multi-UAV Collaborative Target Sensing for Low-Altitude Economy
Rui Wang, Kaitao Meng, Deshi Li et al. (+1 more)
Integrated sensing and communication (
ISAC) has attracted growing research interests to facilitate the large-scale development of the low-altitude economy (LAE). However, the high dynamics of low-altitude targets may overwhelm fixed
ISAC systems, particularly at the edge of their coverage or in blind zones. Driven by high flexibility, unmanned aerial vehicle (
UAV)-assisted
ISAC can provide more freedom of design to enhance communication and sensing abilities. In this paper, we propose an
ISAC-enabled multi-
UAV dynamic collaborative target sensing scheme, where
UAVs can dynamically adjust their flight and resource allocation for cooperative sensing of mobile target through communicating with the terrestrial cellular network with
ISAC signals. To achieve the precise sensing of the dynamic target, the posterior Cramer-Rao bound (PCRB) for the target state is derived. Subsequently, the PCRB minimization problem is formulated by jointly optimizing the
UAV-BS association,
UAVs' trajectories and bandwidth allocation, subject to the communication requirements for the
UAVs. However, the problem is challenging since it involves non-convex and implicit objective function with coupled optimization variables. For a fast implementation of sensing and tracking, we propose a low-complexity iterative
algorithm that can efficiently obtain a sub-optimal solution to the problem. Specifically, the
UAV-BS association is first determined by the communication-optimal solution. Then the
UAVs' trajectories and bandwidth allocation are alternatively optimized based on the descent direction search
algorithm. Finally, numerical results are provided to validate the superiority of our proposed designs as compared to various
benchmarks.
Read the full abstract ▾
All authors Rui Wang, Kaitao Meng, Deshi Li, Liang Xu
Audio and Speech Processing · Cross-listed from cs.SD
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
Joonyong Park and Jerry Li
Evaluating 'anime-like' voices currently relies on costly subjective judgments, yet no standardized objective metric exists. A key challenge is that anime-likeness, unlike naturalness, lacks a shared absolute scale, making conventional Mean Opinion Score (MOS) protocols unreliable. To address this gap, we propose AnimeScore, a preference-based framework for automatic anime-likeness evaluation via pairwise ranking. We collect 15,000 pairwise judgments from 187 evaluators with free-form descriptions, and acoustic analysis reveals that perceived anime-likeness is driven by controlled resonance shaping, prosodic continuity, and deliberate articulation rather than simple heuristics such as high pitch. We show that handcrafted acoustic features reach a 69.3% AUC ceiling, while SSL-based ranking models achieve up to 90.8% AUC, providing a practical metric that can also serve as a reward signal for preference-based optimization of generative
speech models.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.LG
Slack More, Predict Better: Proximal Relaxation for Probabilistic Latent Variable Model-based Soft Sensors
Zehua Zou, Yiran Ma, Yulong Zhang et al. (+5 more)
Nonlinear Probabilistic Latent Variable Models (NPLVMs) are a cornerstone of soft sensor modeling due to their capacity for uncertainty delineation. However, conventional NPLVMs are trained using amortized variational inference, where neural networks parameterize the variational posterior. While facilitating model implementation, this parameterization converts the distributional optimization problem within an infinite-dimensional function space to parameter optimization within a finite-dimensional parameter space, which introduces an approximation error gap, thereby degrading soft sensor modeling accuracy. To alleviate this issue, we introduce KProxNPLVM, a novel NPLVM that pivots to relaxing the objective itself and improving the NPLVM's performance. Specifically, we first prove the approximation error induced by the conventional approach. Based on this, we design the Wasserstein distance as the proximal operator to relax the learning objective, yielding a new variational inference strategy derived from solving this relaxed optimization problem. Based on this foundation, we provide a rigorous derivation of KProxNPLVM's optimization implementation, prove the convergence of our
algorithm can finally sidestep the approximation error, and propose the KProxNPLVM by summarizing the abovementioned content. Finally, extensive experiments on synthetic and real-world industrial
datasets are conducted to demonstrate the efficacy of the proposed KProxNPLVM.
Read the full abstract ▾
All authors Zehua Zou, Yiran Ma, Yulong Zhang, Zhengnan Li, Zeyu Yang, Jinhao Xie, Xiaoyu Jiang, Zhichao Chen