arXiv EE and SS @arxiv_eess@qoto.org

Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech systems are insufficient. While previous research has largely addressed audio disruptions, few studies have dealt with visual corruptions, e.g., lip occlusions or blurred videos, which are also detrimental. To address this real-world challenge, we propose CAV2vec, a novel self-supervised speech representation learning framework particularly designed to handle audio-visual joint corruption. CAV2vec employs a self-distillation approach with a corrupted prediction task, where the student model learns to predict clean targets, generated by the teacher model, with corrupted input frames. Specifically, we suggest a unimodal multi-task learning, which distills cross-modal knowledge and aligns the corrupted modalities, by predicting clean audio targets with corrupted videos, and clean video targets with corrupted audios. This strategy mitigates the dispersion in the representation space caused by corrupted modalities, leading to more reliable and robust audio-visual fusion. Our experiments on robust AVSR benchmarks demonstrate that the corrupted representation learning method significantly enhances recognition accuracy across generalized environments involving various types of corruption.

The growing burden of myopia and retinal diseases necessitates more accessible and efficient eye screening solutions. This study presents a compact, dual-function optical device that integrates fundus photography and refractive error detection into a unified platform. The system features a coaxial optical design using dichroic mirrors to separate wavelength-dependent imaging paths, enabling simultaneous alignment of fundus and refraction modules. A Dense-U-Net-based algorithm with customized loss functions is employed for accurate pupil segmentation, facilitating automated alignment and focusing. Experimental evaluations demonstrate the system's capability to achieve high-precision pupil localization (EDE = 2.8 px, mIoU = 0.931) and reliable refractive estimation with a mean absolute error below 5%. Despite limitations due to commercial lens components, the proposed framework offers a promising solution for rapid, intelligent, and scalable ophthalmic screening, particularly suitable for community health settings.

Koopman analysis of a general dynamics system provides a linear Koopman operator and an embedded eigenfunction space, enabling the application of standard techniques from linear analysis. However, in practice, deriving exact operators and mappings for the observable space is intractable, and deriving an approximation or expressive subset of these functions is challenging. Programmatic methods often rely on system-specific parameters and may scale poorly in both time and space, while learning-based approaches depend heavily on difficult-to-know hyperparameters, such as the dimension of the observable space. To address the limitations of both methods, we propose a hybrid framework that uses semidefinite programming to find a representation of the linear operator, then learns an approximate mapping into and out of the space that the operator propagates. This approach enables efficient learning of the operator and explicit mappings while reducing the need for specifying the unknown structure ahead of time.

This paper fills a gap in the literature by considering a joint sensor and actuator configuration problem under the linear quadratic Gaussian (LQG) performance without assuming a predefined set of candidate components. Different from the existing research, which primarily focuses on selecting or placing sensors and actuators from a fixed group, we consider a more flexible formulation where these components must be designed from scratch, subject to general-form configuration costs and constraints. To address this challenge, we first analytically characterize the gradients of the LQG performance with respect to the sensor and actuator matrices using algebraic Riccati equations. Subsequently, we derive first-order optimality conditions based on the Karush-Kuhn-Tucker (KKT) analysis and develop a unified alternating direction method of multipliers (ADMM)-based alternating optimization framework to address the general-form sensor and actuator configuration problem. Furthermore, we investigate three representative scenarios: sparsity promoting configuration, low-rank promoting configuration, and structure-constrained configuration. For each scenario, we provide in-depth analysis and develop tailored computational schemes. The proposed framework ensures numerical efficiency and adaptability to various design constraints and configuration costs, making it well-suited for integration into numerical solvers.

Low-order linear System IDentification (SysID) addresses the challenge of estimating the parameters of a linear dynamical system from finite samples of observations and control inputs with minimal state representation. Traditional approaches often utilize Hankel-rank minimization, which relies on convex relaxations that can require numerous, costly singular value decompositions (SVDs) to optimize. In this work, we propose two nonconvex reformulations to tackle low-order SysID (i) Burer-Monterio (BM) factorization of the Hankel matrix for efficient nuclear norm minimization, and (ii) optimizing directly over system parameters for real, diagonalizable systems with an atomic norm style decomposition. These reformulations circumvent the need for repeated heavy SVD computations, significantly improving computational efficiency. Moreover, we prove that optimizing directly over the system parameters yields lower statistical error rates, and lower sample complexities that do not scale linearly with trajectory length like in Hankel-nuclear norm minimization. Additionally, while our proposed formulations are nonconvex, we provide theoretical guarantees of achieving global optimality in polynomial time. Finally, we demonstrate algorithms that solve these nonconvex programs and validate our theoretical claims on synthetic data.

Urban roads and infrastructure, vital to city operations, face growing threats from subsurface anomalies like cracks and cavities. Ground Penetrating Radar (GPR) effectively visualizes underground conditions employing electromagnetic (EM) waves; however, accurate anomaly detection via GPR remains challenging due to limited labeled data, varying subsurface conditions, and indistinct target boundaries. Although visually image-like, GPR data fundamentally represent EM waves, with variations within and between waves critical for identifying anomalies. Addressing these, we propose the Reservoir-enhanced Segment Anything Model (Res-SAM), an innovative framework exploiting both visual discernibility and wave-changing properties of GPR data. Res-SAM initially identifies apparent candidate anomaly regions given minimal prompts, and further refines them by analyzing anomaly-induced changing information within and between EM waves in local GPR data, enabling precise and complete anomaly region extraction and category determination. Real-world experiments demonstrate that Res-SAM achieves high detection accuracy (>85%) and outperforms state-of-the-art. Notably, Res-SAM requires only minimal accessible non-target data, avoids intensive training, and incorporates simple human interaction to enhance reliability. Our research provides a scalable, resource-efficient solution for rapid subsurface anomaly detection across diverse environments, improving urban safety monitoring while reducing manual effort and computational cost.

The recent surge in deploying extremely large antenna arrays is expected to play a vital role in future sixth generation wireless networks, enabling advanced radar target localization with enhanced angular and range resolution. This paper focuses on the promising technology of Dynamic Metasurface Antennas (DMAs), integrating numerous sub-wavelength-spaced metamaterials within a single aperture, and presents a novel framework for designing its analog reception beamforming weights with the goal to optimize sensing performance within a spatial Area of Interest (AoI), while simultaneously guaranteeing desired multi-user uplink communication performance. We derive the Cramer-Rao Bound (CRB) with DMA-based reception for both passive and active radar targets lying inside the AoI, which is then used as the optimization objective for configuring the discrete tunable phases of the metamaterials. Capitalizing on the DMA partially-connected architecture, we formulate the design problem as convex optimization and present both direct CRB minimization approaches and low complexity alternatives using a lower-bound approximation. Simulation results across various scenarios validate the effectiveness of the proposed framework, showing it consistently outperforms existing state-of-the-art methods.

Hybrid Reconfigurable Intelligent Surfaces (HRISs) constitute a new paradigm that redefines smart metasurfaces, not only offering tunable reflections of incoming signals, but also incorporating signal reception and processing capabilities. In this paper, leveraging the simultaneous dual-functionality of HRISs, we propose a novel framework for tracking-aided multi-user Multiple-Input Multiple-Output (MIMO) communications. In particular, a joint design of the transmit multi-user precoding matrix together with the HRIS reflection and analog combining configurations is presented, with the objective to maximize the accuracy of position estimation of multiple mobile users while meeting their individual quality-of-service constraints for sensing-aided communications. The Cramer-Rao bound for the users' positioning parameters is derived together with a prediction approach based on the extended Kalman filter. Our simulation results showcase the efficacy of the proposed Integrated Sensing And Communications (ISAC) framework over various system configuration parameters.

In this paper, we propose a low-complexity channel estimation scheme of affine frequency division multiplexing (AFDM) based on generalized complex exponential basis expansion model (GCE-BEM) over doubly selective channels. The GCE-BEM is used to solve fractional Doppler dispersion while significantly reducing the computational complexity of exhaustive search. Then, the closed-form expression of channel estimation error is derived for the minimum mean square error (MMSE) estimation algorithm. Based on the estimated channel, the MMSE detection is adopt to characterize the impacts of estimated channel on bit error rate (BER) by deriving the theoretical lower bound. Finally, numerical results demonstrate that the proposed scheme effectively mitigates severe inter-Doppler interference (IDoI). Our theoretical performance an alysis can perfectly match the Monte-Carlo results, validating the effectiveness of our proposed channel estimation based on GCE-BEM.

Rapid deployment of distributed energy resources (DERs), such as solar photovoltaics (PV), poses a risk to the distribution grid under high penetration. Therefore, studying hosting capacity (HC) limits considering grid physics and demand variability is crucial. This paper introduces an improved framework for determining the HC of radial distribution networks by enhancing an existing convex inner approximation (CIA) approach. The proposed method achieves a more accurate and larger inner approximation, resulting in better HC limits. We also consider time-varying demand and the design of objective functions to ensure equitable access to grid resources. A case study with solar PV integration is conducted using a modified IEEE-37 radial network to examine the impact of increased PV capacity, demonstrating that with no more than 5% annual solar PV energy curtailed, it is possible to increase solar PV hosting capacity by at least 50% with no negative grid impacts and a net positive economic impact when accounted for the cost of carbon. Results show that fair allocation methods can lead to higher net profits and reduced PV curtailment and CO2.

The Computer_Aided Diagnosis (CAD) systems facilitate accurate diagnosis of diseases. The development of CADs by leveraging third generation neural network, namely, Spiking Neural Network (SNN), is essential to utilize of the benefits of SNNs, such as their event_driven processing, parallelism, low power consumption, and the ability to process sparse temporal_spatial information. However, Deep SNN as a deep learning model faces challenges with unreliability. To deal with unreliability challenges due to inability to quantify the uncertainty of the predictions, we proposed a deep Bayesian Convolutional Spiking Neural Network based_CADs with uncertainty_aware module. In this study, the Monte Carlo Dropout method as Bayesian approximation is used as an uncertainty quantification method. This method was applied to several medical image classification tasks. Our experimental results demonstrate that our proposed model is accurate and reliable and will be a proper alternative to conventional deep learning for medical image classification.

We propose a novel low-complexity three-dimensional (3D) localization algorithm for wireless sensor networks, termed quaternion-domain super multidimensional scaling (QD-SMDS). This algorithm reformulates the conventional SMDS, which was originally developed in the real domain, into the quaternion domain. By representing 3D coordinates as quaternions, the method enables the construction of a rank-1 Gram edge kernel (GEK) matrix that integrates both relative distance and angular (phase) information between nodes, maximizing the noise reduction effect achieved through low-rank truncation via singular value decomposition (SVD). The simulation results indicate that the proposed method demonstrates a notable enhancement in localization accuracy relative to the conventional SMDS algorithm, particularly in scenarios characterized by substantial measurement errors.

Cashierless stores rely on computer vision and RFID tags to associate shoppers with items, but concealed items placed in backpacks, pockets, or bags create challenges for theft prevention. We introduce a system that turns existing RFID tagged items into material sensors by exploiting how different containers attenuate and scatter RF signals. Using RSSI and phase angle, we trained a neural network to classify seven common containers. In a simulated retail environment, the model achieves 89% accuracy with one second samples and 74% accuracy from single reads. Incorporating distance measurements, our system achieves 82% accuracy across 0.3-2m tag to reader separations. When deployed at aisle or doorway choke points, the system can flag suspicious events in real time, prompting camera screening or staff intervention. By combining material identification with computer vision tracking, our system provides proactive loss prevention for cashierless retail while utilizing existing infrastructure.

Online system identification algorithms are widely used for monitoring, diagnostics and control by continuously adapting to time-varying dynamics. Typically, these algorithms consider a model structure that lacks parsimony and offers limited physical interpretability. The objective of this paper is to develop a real-time parameter estimation algorithm aimed at identifying time-varying dynamics within an interpretable model structure. An additive model structure is adopted for this purpose, which offers enhanced parsimony and is shown to be particularly suitable for mechanical systems. The proposed approach integrates the recursive simplified refined instrumental variable method with block-coordinate descent to minimize an exponentially-weighted output error cost function. This novel recursive identification method delivers parametric continuous-time additive models and is applicable in both open-loop and closed-loop controlled systems. Its efficacy is shown using numerical simulations and is further validated using experimental data to detect the time-varying resonance dynamics of a flexible beam system. These results demonstrate the effectiveness of the proposed approach for online and interpretable estimation for advanced monitoring and control applications.

Monitoring calf body weight (BW) before weaning is essential for assessing growth, feed efficiency, health, and weaning readiness. However, labor, time, and facility constraints limit BW collection. Additionally, Holstein calf coat patterns complicate image-based BW estimation, and few studies have explored non-contact measurements taken at early time points for predicting later BW. The objectives of this study were to (1) develop deep learning-based segmentation models for extracting calf body metrics, (2) compare deep learning segmentation with threshold-based methods, and (3) evaluate BW prediction using single-time-point cross-validation with linear regression (LR) and extreme gradient boosting (XGBoost) and multiple-time-point cross-validation with LR, XGBoost, and a linear mixed model (LMM). Depth images from Holstein (n = 63) and Jersey (n = 5) pre-weaning calves were collected, with 20 Holstein calves being weighed manually. Results showed that You Only Look Once version 8 (YOLOv8) deep learning segmentation (intersection over union = 0.98) outperformed threshold-based methods (0.89). In single-time-point cross-validation, XGBoost achieved the best BW prediction (R^2 = 0.91, mean absolute percentage error (MAPE) = 4.37%), while LMM provided the most accurate longitudinal BW prediction (R^2 = 0.99, MAPE = 2.39%). These findings highlight the potential of deep learning for automated BW prediction, enhancing farm management.

Accurate myocardial image registration is essential for cardiac strain analysis and disease diagnosis. However, spectral bias in neural networks impedes modeling high-frequency deformations, producing inaccurate, biomechanically implausible results, particularly in pathological data. This paper addresses spectral bias in physics-informed neural networks (PINNs) by integrating Fourier Feature mappings and introducing modulation strategies into a PINN framework. Experiments on two distinct datasets demonstrate that the proposed methods enhance the PINN's ability to capture complex, high-frequency deformations in cardiomyopathies, achieving superior registration accuracy while maintaining biomechanical plausibility - thus providing a foundation for scalable cardiac image registration and generalization across multiple patients and pathologies.

Efficient trajectory generation is critical for autonomous systems, yet current numerical methods often struggle to handle periodic behaviors effectively, especially when equidistant time nodes are required. This paper introduces a novel mixed Bernstein-Fourier approximation framework tailored explicitly for optimal motion planning. Our proposed methodology leverages the uniform convergence properties of Bernstein polynomials for nonperiodic behaviors while effectively capturing periodic dynamics through Fourier series. Theoretical results are established, including uniform convergence proofs for approximations of functions, derivatives, and integrals, as well as detailed error bound analyses. We further introduce a regulated least squares approach for determining approximation coefficients, enhancing numerical stability and practical applicability. Within an optimal control context, we establish feasibility and consistency of approximated solutions to their continuous counterparts. We also extend the covector mapping theorem, providing theoretical guarantees for approximating dual variables crucial in verifying the necessary optimality conditions from Pontryagin's Maximum Principle. Comprehensive numerical examples illustrate the method's superior performance, demonstrating substantial improvements in computational efficiency and precision in scenarios with complex periodic constraints and dynamics. Our mixed Bernstein-Fourier methodology thus presents a robust, theoretically grounded, and computationally efficient approach for advanced optimal trajectory planning in autonomous systems.

Pre-trained deep learning models, known as foundation models, have become essential building blocks in machine learning domains such as natural language processing and image domains. This trend has extended to respiratory and heart sound models, which have demonstrated effectiveness as off-the-shelf feature extractors. However, their evaluation benchmarking has been limited, resulting in incompatibility with state-of-the-art (SOTA) performance, thus hindering proof of their effectiveness. This study investigates the practical effectiveness of off-the-shelf audio foundation models by comparing their performance across four respiratory and heart sound tasks with SOTA fine-tuning results. Experiments show that models struggled on two tasks with noisy data but achieved SOTA performance on the other tasks with clean data. Moreover, general-purpose audio models outperformed a respiratory sound model, highlighting their broader applicability. With gained insights and the released code, we contribute to future research on developing and leveraging foundation models for respiratory and heart sounds.

High-precision ranging plays a crucial role in future 6G Integrated Sensing and Communication (ISAC) systems. To improve the ranging performance while maximizing the resource utilization efficiency, future 6G ISAC networks have to reuse data payload signals for both communication and sensing, whose inherent randomness may deteriorate the ranging performance. To address this issue, this paper investigates the power allocation (PA) design for an OFDM-based ISAC system under random signaling, aiming to reduce the ranging sidelobe level of both periodic and aperiodic auto-correlation functions (P-ACF and A-ACF) of the ISAC signal. Towards that end, we first derive the closed-form expressions of the average squared P-ACF and A-ACF, and then propose to minimize the expectation of the integrated sidelobe level (EISL) under arbitrary constellation mapping. We then rigorously prove that the uniform PA scheme achieves the global minimum of the EISL for both P-ACF and A-ACF. As a step further, we show that this scheme also minimizes the P-ACF sidelobe level at every lag. Moreover, we extend our analysis to the P-ACF case with frequency-domain zero-padding, which is a typical approach to improve the ranging resolution. We reveal that there exists a tradeoff between sidelobe level and mainlobe width, and propose a project gradient descent algorithm to seek a locally optimal PA scheme that reduces the EISL. Finally, we validate our theoretical findings through extensive simulation results, confirming the effectiveness of the proposed PA methods in reducing the ranging sidelobe level for random OFDM signals.

Electrical Impedance Tomography (EIT) provides a non-invasive, portable imaging modality with significant potential in medical and industrial applications. Despite its advantages, EIT encounters two primary challenges: the ill-posed nature of its inverse problem and the spatially variable, location-dependent sensitivity distribution. Traditional model-based methods mitigate ill-posedness through regularization but overlook sensitivity variability, while supervised deep learning approaches require extensive training data and lack generalization. Recent developments in neural fields have introduced implicit regularization techniques for image reconstruction, but these methods typically neglect the physical principles underlying EIT, thus limiting their effectiveness. In this study, we propose PhyNC (Physics-driven Neural Compensation), an unsupervised deep learning framework that incorporates the physical principles of EIT. PhyNC addresses both the ill-posed inverse problem and the sensitivity distribution by dynamically allocating neural representational capacity to regions with lower sensitivity, ensuring accurate and balanced conductivity reconstructions. Extensive evaluations on both simulated and experimental data demonstrate that PhyNC outperforms existing methods in terms of detail preservation and artifact resistance, particularly in low-sensitivity regions. Our approach enhances the robustness of EIT reconstructions and provides a flexible framework that can be adapted to other imaging modalities with similar challenges.