Papers

Precise in-hand manipulation of force-sensitive objects typically requires judicious coordinated force planning as well as accurate contact force feedback and control. Unlike multi-arm platforms with gripper end effectors, multi-fingered hands rely solely on fingertip point contacts and are not able to apply pull forces, therefore poses a more challenging problem. Furthermore, calibrated torque sensors are lacking in most commercial dexterous hands, adding to the difficulty. To address these challenges, we propose a dual-layer framework for multi-finger coordination, enabling high-precision manipulation of force-sensitive objects through joint control without tactile feedback. This approach solves coordinated contact force planning by incorporating graph rigidity and force closure constraints. By employing a force-to-position mapping, the planned force trajectory is converted to a joint trajectory. We validate the framework on a custom dexterous hand, demonstrating the capability to manipulate fragile objects-including a soft yarn, a plastic cup, and a raw egg-with high precision and safety.

Wireless communication systems exhibit structural and functional similarities to neural networks: signals propagate through cascaded elements, interact with the environment, and undergo transformations. Building upon this perspective, we introduce a unified paradigm, termed wireless physical neural networks (WPNNs), in which components of a wireless network, such as transceivers, relays, backscatter, and intelligent surfaces, are interpreted as computational layers within a learning architecture. By treating the wireless propagation environment and network elements as differentiable operators, new opportunities arise for joint communication-computation designs, where system optimization can be achieved through learning-based methods applied directly to the physical network. This approach may operate independently of, or in conjunction with, conventional digital neural layers, enabling hybrid communication learning pipelines. In the article, we outline representative architectures that embody this viewpoint and discuss the algorithmic and training considerations required to leverage the wireless medium as a computational resource. Through numerical examples, we highlight the potential performance gains in processing, adaptability, efficiency, and end-to-end optimization, demonstrating the promise of reconfiguring wireless systems as learning networks in next-generation communication frameworks.

Operating complex real-world systems, such as soft robots, can benefit from precise predictive control schemes that require accurate state and model knowledge. This knowledge is typically not available in practical settings and must be inferred from noisy measurements. In particular, it is challenging to simultaneously estimate unknown states and learn a model online from sequentially arriving measurements. In this paper, we show how a recently proposed gray-box system identification tool enables the estimation of a soft robot's current pose while at the same time learning a bending stiffness model. For estimation and learning, we only need a nominal constant-curvature robot model and measurements of the robot's base reactions (e.g., base forces). The estimation scheme – relying on a marginalized particle filter – allows us to conveniently interface nominal constant-curvature equations with a Gaussian Process (GP) bending stiffness model to be learned. This, in contrast to estimation via a random walk over stiffness values, enables prediction of bending stiffness and improves overall model quality. We demonstrate, using a real-world soft robot, that the method learns a bending-stiffness model online while accurately estimating the robot's pose. Notably, reduced error in multi-step forward predictions indicates that the learned bending-stiffness GP improves overall model quality.

Extra-large apertures, high carrier frequencies, and integrated sensing and communications (ISAC) are pushing array processing into the Fresnel region, where spherical wavefronts induce a range-dependent phase across the aperture. This curvature breaks the Fourier/Vandermonde structure behind classical subspace methods, and it is especially limiting with hybrid front-ends that provide only a small number of pilot measurements. Consequently, practical systems need continuous angle resolution and joint angle-range inference where many near-field approaches still rely on costly 2D gridding. We show that convexity can meet curvature via a lifted, gridless superresolution framework for near-field measurements. The key is a Bessel-Vandermonde factorization of the Fresnel-phase manifold that exposes a hidden Vandermonde structure in angle while isolating the range dependence into a compact coefficient map. Building on this, we introduce a lifting that maps each range bin and continuous angle to a structured rank-one atom, converting the nonlinear near-field model into a linear inverse problem over a row-sparse matrix. Recovery is posed as atomic-norm minimization and an explicit dual characterization via bounded trigonometric polynomials yields certificate-based localization that super-resolves off-grid angles and identifies active range bins. Simulations with strongly undersampled hybrid observations validate reliable joint angle-range recovery for next-generation wireless and ISAC systems.

Decentralized federated learning (DFL) enables edge devices to collaboratively train models through local training and fully decentralized device-to-device (D2D) model exchanges. However, these energy-intensive operations often rapidly deplete limited device batteries, reducing their operational lifetime and degrading the learning performance. To address this limitation, we apply energy harvesting technique to DFL systems, allowing edge devices to extract ambient energy and operate sustainably. We first derive the convergence bound for wireless DFL with energy harvesting, showing that the convergence is influenced by partial device participation and transmission packet drops, both of which further depend on the available energy supply. To accelerate convergence, we formulate a joint device scheduling and power control problem and model it as a multi-agent Markov decision process (MDP). Traditional MDP algorithms (e.g., value or policy iteration) require a centralized coordinator with access to all device states and exhibit exponential complexity in the number of devices, making them impractical for large-scale decentralized networks. To overcome these challenges, we propose a fully decentralized policy iteration algorithm that leverages only local state information from two-hop neighboring devices, thereby substantially reducing both communication overhead and computational complexity. We further provide a theoretical analysis showing that the proposed decentralized algorithm achieves asymptotic optimality. Finally, comprehensive numerical experiments on real-world datasets are conducted to validate the theoretical results and corroborate the effectiveness of the proposed algorithm.

Deep learning (DL)-based joint source–channel coding (JSCC), particularly vector quantization (VQ)-based JSCC, enables efficient semantic communication by mapping high-dimensional feature vectors into compact codeword indices for digital modulation. However, existing methods, including universal JSCC (uJSCC), rely on fixed, modulation-specific encoders, decoders, and codebooks, limiting adaptation to fine-grained channel variations. We propose an extended universal JSCC (euJSCC) framework that enables adaptive transmission across both modulation orders and fine-grained channel conditions within a single model using hypernetwork-based normalization and a dynamic codebook generation (DCG) network that refines modulation-specific base codebooks according to channel quality indicator (CQI) feedback. To support time-varying channels with periodic CQI feedback, euJSCC employs an inner–outer encoder–decoder architecture, where the outer modules capture long-term channel statistics and the inner modules refine feature vectors to align with block-wise codebooks. A two-phase training strategy first pretrains the outer modules and DCG network over additive white Gaussian noise (AWGN) channels to establish stable feature–codebook alignment and then fine-tunes the full model over time-varying channels. Experiments demonstrate that euJSCC consistently outperforms state-of-the-art channel-adaptive digital JSCC schemes in image transmission, while additional evaluations under practical channel and feedback conditions and on a downstream task further validate its effectiveness.

The Received Signal Strength Indicator (RSSI) is ubiquitously available on commodity WiFi devices but is commonly regarded as too coarse for fine-grained sensing. This paper revisits its sensing potential and presents WiRSSI, a bistatic WiFi sensing framework that enables RSSI-only passive human tracking and motion sensing. WiRSSI employs a transmitter and a receiver equipped with a three-antenna array (1Tx-3Rx), and is readily extensible to Multiple-Input Multiple-Output (MIMO) deployments. We first show how Channel State Information (CSI) power implicitly preserves phase-related motion modulation and how this relationship carries over to RSSI, indicating that RSSI can retain exploitable Doppler, Angle-of-Arrival (AoA), and delay cues. WiRSSI extracts Doppler-AoA features via a lightweight 2D Fast Fourier Transform (FFT) pipeline and infers bistatic delay from amplitude-only information in the absence of subcarrier-level phase. The estimated AoA and delay are then mapped to Cartesian coordinates and denoised to recover motion trajectories. Experiments in practical environments show that WiRSSI achieves median XY localization errors of 0.905 m, 0.784 m, and 0.785 m for elliptical, linear, and rectangular trajectories, respectively, compared with 0.574 m, 0.599 m, and 0.514 m from a representative CSI-based method. We further demonstrate RSSI-only gesture recognition on the Widar3.0 dataset, where WiRSSI features provide meaningful discriminative performance. These results suggest that, despite lacking subcarrier-level information compared with CSI, RSSI can support practical WiFi sensing as a complementary and hardware-friendly option when CSI is restricted, unreliable, or privacy-sensitive.

Quasi-static human activities such as lying, standing or sitting produce very low Doppler shifts and highly spread radar signatures, making them difficult to detect with conventional constant-false-alarm rate (CFAR) detectors tuned for point targets. Moreover, privacy concerns and low lighting conditions limit the use of cameras in long-term care (LTC) facilities. This paper proposes a lightweight, non-visual image-based method for robust quasi-static human presence detection using a low-cost 60 GHz FMCW radar. On a dataset covering five semi-static activities, the proposed method improves average detection accuracy from 68.3% for Cell-Averaging CFAR (CA-CFAR) and 78.8% for Order-Statistics CFAR (OS-CFAR) to 93.24% for Subject 1, from 51.3%, 68.3% to 92.3% for Subject 2, and 57.72%, 69.94% to 94.82% for Subject 3, respectively. Finally, we benchmarked all three detectors across all activities on a Raspberry Pi 4B using a shared Range-Angle (RA) preprocessing pipeline. The proposed algorithm obtains an average 8.2 ms per frame, resulting in over 120 frames per second (FPS) and a 74 times speed-up over OS-CFAR. These results demonstrate that simple image-based processing can provide robust and deployable quasi-static human sensing in cluttered indoor environments.

Accurate cascaded channel state information is pivotal for extremely large-scale intelligent reflecting surfaces (XL-IRS) in next-generation wireless networks. However, the large XL-IRS aperture induces spherical wavefront propagation due to near-field (NF) effects, complicating cascaded channel estimation. Conventional dictionary-based methods suffer from cumulative quantization errors and high complexity, especially in uniform planar array (UPA) systems. To address these issues, we first propose a tensor modelization method for NF cascaded channels by exploiting the tensor product among the horizontal and vertical response vectors of the UPA-structured base station (BS) and the incident-reflective array response vector of the IRS. This structure leverages spatial characteristics, enabling independent estimation of factor matrices to improve efficiency. Meanwhile, to avoid quantization errors, we propose an off-grid cascaded channel estimation framework based on sparse Tucker decomposition. Specifically, we model the received signal as a Tucker tensor, where the sparse core tensor captures path gain-delay terms and three factor matrices are spanned by BS and NF IRS array responses. We then formulate a sparse core tensor minimization problem with tri-modal log-sum sparsity constraints to tackle the NP-hard challenge. Finally, the method is accelerated via higher-order singular value decomposition preprocessing, combined with majorization-minimization and a tailored tensor over-relaxation fast iterative shrinkage-thresholding technique. We derive the Cramér-Rao lower bound and conduct convergence analysis. Simulations show the proposed scheme achieves a 13.6 dB improvement in normalized mean square error over benchmarks with significantly reduced runtime.

Cardiac MRI is limited by long acquisition times, which can lead to patient discomfort and motion artifacts. We aim to accelerate Cartesian dynamic cardiac MRI by learning efficient, scan-adaptive undersampling patterns that preserve diagnostic image quality. We develop a learning-based framework for designing scan- or slice-adaptive Cartesian undersampling masks tailored to dynamic cardiac MRI. Undersampling patterns are optimized using fully sampled training dynamic time-series data. At inference time, a nearest-neighbor search in low-frequency $k$-space selects an optimized mask from a dictionary of learned patterns. Our learned sampling approach improves reconstruction quality across multiple acceleration factors on public and in-house cardiac MRI datasets, including PSNR gains of 2-3 dB, reduced NMSE, improved SSIM, and higher radiologist ratings. The proposed scan-adaptive sampling framework enables faster and higher-quality dynamic cardiac MRI by adapting $k$-space sampling to individual scans.

In this paper, we propose a data-enabled moving horizon estimation (MHE) approach for a class of nonlinear systems without explicit modeling, by leveraging Koopman operator theory and Willems fundamental lemma. Specifically, the nonlinear system is lifted to a linear parameter-varying Koopman surrogate, in which the lifting functions and scheduling mappings are learned directly from data using neural networks. Willems fundamental lemma is then employed to construct a trajectory-based representation of the Koopman surrogate, which bypasses the explicit identification of the matrices of the Koopman surrogate. Based on this representation, we formulate a convex data-enabled MHE design, which provides real-time estimates of the Koopman surrogate states, from which the states of the original nonlinear system are reconstructed. Sufficient conditions are derived to ensure the stability of the estimation error. The effectiveness of the proposed method is illustrated using a simulated membrane-based biological wastewater treatment process.

This paper investigates a six-wave mixing (SWM)-based Rydberg atomic receiver as a wideband radio frequency (RF)-to-optical quantum transducer. Specifically, we develop an explicit baseband input-output model that bridges the RF-induced atomic coherence to the detected optical readout. Based on the exact detected SWM response, we develop a reduced-order closed-form two-pole low-pass approximation under the near-resonant weak-signal of interest, which provides an analytical insight into how the 3-dB bandwidth is manipulated by the dressed higher-level atomic dynamics and optical/RF parameters. The validity range of this approximation is then quantified to clarify the operating conditions under which this reduced-order model accurately represents the exact SWM response. We further characterize the linear dynamic range by employing the 1-dB compression point (P1dB) and the input-referred third-order intercept point (IIP3), unveiling a communication-compatible characterization of the bandwidth-sensitivity-linearity trade-off. Extensive simulation results demonstrate that SWM can achieve a 3-dB bandwidth of approximately 10 MHz while maintaining favorable linearity and sensitivity under the strict low-pass condition. The comparison with the EIT regime indicates that the two schemes should be treated as complementary rather than universally ordered. From an engineering perspective, the preferred SWM operating region is therefore not the one with the largest bandwidth, but the one that simultaneously provides a large bandwidth, acceptable sensitivity, favorable linearity, and low-pass regularity.

Multi-branch deep neural networks like AASIST3 achieve state-of-the-art comparable performance in audio anti-spoofing, yet their internal decision dynamics remain opaque compared to traditional input-level saliency methods. While existing interpretability efforts largely focus on visualizing input artifacts, the way individual architectural branches cooperate or compete under different spoofing attacks is not well characterized. This paper develops a framework for interpreting AASIST3 at the component level. Intermediate activations from fourteen branches and global attention modules are modeled with covariance operators whose leading eigenvalues form low-dimensional spectral signatures. These signatures train a CatBoost meta-classifier to generate TreeSHAP-based branch attributions, which we convert into normalized contribution shares and confidence scores (Cb) to quantify the model's operational strategy. By analyzing 13 spoofing attacks from the ASVspoof 2019 benchmark, we identify four operational archetypes-ranging from Effective Specialization (e.g., A09, Equal Error Rate (EER) 0.04%, C=1.56) to Ineffective Consensus (e.g., A08, EER 3.14%, C=0.33). Crucially, our analysis exposes a Flawed Specialization mode where the model places high confidence in an incorrect branch, leading to severe performance degradation for attacks A17 and A18 (EER 14.26% and 28.63%, respectively). These quantitative findings link internal architectural strategy directly to empirical reliability, highlighting specific structural dependencies that standard performance metrics overlook.

Voltage stability in modern power systems involves coupled dynamics across multiple time scales. Conventional methods based on time-scale separation or static stability margins may overlook instabilities caused by the coupling of slow and fast transients. Uncertainty in operating conditions further complicates stability assessment, and high computational cost of Monte Carlo simulations limit its applicability to multi-scale dynamics. This paper presents a deep reinforcement learning-based framework for probabilistic reachability analysis of multi-scale voltage dynamics. By formulating each instability mechanism as a distinct absorbing state and introducing a multi-critic architecture for mechanism-specific learning, the proposed method enables consistent learning of risk probabilities associated with multiple instability types within a unified framework. The approach is demonstrated on a four-bus system with load tap changers and over-excitation limiters, illustrating effectiveness of the proposed learning-based reachability analysis in identifying and quantifying the mechanisms leading to voltage collapse.

This paper presents the history of the online simulation program Java-DSP (J-DSP) and the most recent function development and deployment. J-DSP was created to support online laboratories in DSP classes and was first deployed in our ASU DSP class in 2000. The development of the program and its extensions was supported by several NSF grants including CCLI and IUSE. The web-based software was developed by our team in Java and later transitioned to the more secure HTML5 environment. J-DSP supports laboratory exercises on: digital filters and their design, the FFT and its utility in spectral analysis, machine learning for signal classification, and more recently online simulations with the Quantum Fourier Transform. Throughout the J-DSP development and deployment of this tool and its associated laboratory exercises, we documented evaluations. Mobile versions of the program for iOS and Android were also developed. J-DSP is used to this day in several universities, and specific functions of the program have been used in NSF REU, IRES and RET workforce development and high school outreach.

Tasks ranging from sleep staging to clinical diagnosis traditionally rely on standard polysomnography (PSG) devices, bedside monitors and wearable devices, which capture diverse nocturnal biosignals (e.g., EEG, EOG, ECG, SpO$_2$). However, heterogeneity across devices and frequent sensor dropout pose significant challenges for unified modelling of these multimodal signals. We present sleep2vec, a foundation model for diverse and incomplete nocturnal biosignals that learns a shared representation via cross-modal alignment. sleep2vec is contrastively pre-trained on 42,249 overnight recordings spanning nine modalities using a Demography, Age, Site & History-aware InfoNCE objective that incorporates physiological and acquisition metadata (e.g., age, gender, recording site) to dynamically weight negatives and mitigate cohort-specific shortcuts. On downstream sleep staging and clinical outcome assessment, sleep2vec consistently outperforms strong baselines and remains robust to any subset of available modalities and sensor dropout. We further characterize, to our knowledge for the first time, scaling laws for nocturnal biosignals with respect to modality diversity and model capacity. Together, these results show that unified cross-modal alignment, coupled with principled scaling, enables label-efficient, general-purpose modelling of real-world nocturnal biosignals.

We present a physics-informed voiced backend renderer for singing-voice synthesis. Given synthetic single-channel audio and a fund-amental–frequency trajectory, we train a time-domain Webster model as a physics-informed neural network to estimate an interpretable vocal-tract area function and an open-end radiation coefficient. Training enforces partial differential equation and boundary consistency; a lightweight DDSP path is used only to stabilize learning, while inference is purely physics-based. On sustained vowels (/a/, /i/, /u/), parameters rendered by an independent finite-difference time-domain Webster solver reproduce spectral envelopes competitively with a compact DDSP baseline and remain stable under changes in discretization, moderate source variations, and about ten percent pitch shifts. The in-graph waveform remains breathier than the reference, motivating periodicity-aware objectives and explicit glottal priors in future work.

Reliable localization of unmanned aerial vehicles (UAVs) becomes challenging when Global Navigation Satellite System (GNSS) signals are degraded, blocked, or intentionally jammed. In such GNSS-denied conditions, visual information obtained from onboard cameras can provide complementary cues for navigation by identifying spatially stable and distinc tive landmarks. This study proposes a compact convolutional segmentation framework for extracting candidate visual land marks from aerial imagery. The proposed model combines fully convolutional processing with dilation-based spatial con text extraction and residual feature transfer. Since a dedicated UAV landmark dataset is not available in this study, an aerial building segmentation dataset is adapted as an initial evaluation environment. Experimental results indicate that the proposed architecture provides a feasible front-end for candidate landmark extraction, while further improvements are required through extended training, UAV-specific datasets, and integration with localization or matching algorithms.

Cochlear implants (CIs) have been developed to the point where they can restore hearing and speech understanding in a large proportion of patients. Although spatial hearing is central to controlling and directing attention and to enabling speech understanding in noisy environments, it has been largely neglected in the past. We propose here a multi-disciplinary research framework in which physicians, psychologists and engineers collaborate to improve spatial hearing for CI users.

Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains limited. In addition, most existing fMRI analysis methods rely on static Functional Connectivity (FC) representations, which obscure transient neural dynamics critical for neurodevelopmental disorders such as autism. Recent state-space approaches, including Mamba, model temporal structure efficiently, but are typically used as standalone feature extractors without explicit high-level reasoning. We propose NeuroMambaLLM, an end-to-end framework that integrates dynamic latent graph learning and selective state-space temporal modelling with LLMs. The proposed method learns the functional connectivity dynamically from raw Blood-Oxygen-Level-Dependent (BOLD) time series, replacing fixed correlation graphs with adaptive latent connectivity while suppressing motion-related artifacts and capturing long-range temporal dependencies. The resulting dynamic brain representations are projected into the embedding space of an LLM model, where the base language model remains frozen and lightweight low-rank adaptation (LoRA) modules are trained for parameter-efficient alignment. This design enables the LLM to perform both diagnostic classification and language-based reasoning, allowing it to analyze dynamic fMRI patterns and generate clinically meaningful textual reports.

Spoofing-robust automatic speaker verification (SASV) seeks to build automatic speaker verification systems that are robust against both zero-effort impostor attacks and sophisticated spoofing techniques such as voice conversion (VC) and text-to-speech (TTS). In this work, we propose a novel SASV architecture that introduces score-aware gated attention (SAGA), SASV-SAGA, enabling dynamic modulation of speaker embeddings based on countermeasure (CM) scores. By integrating speaker embeddings and CM scores from pre-trained ECAPA-TDNN and AASIST models respectively, we explore several integration strategies including early, late, and full integration. We further introduce alternating training for multi-module (ATMM) and a refined variant, evading alternating training (EAT). Experimental results on the ASVspoof 2019 Logical Access (LA) and Spoofceleb datasets demonstrate significant improvements over baselines, achieving a spoofing aware speaker verification equal error rate (SASV-EER) of 1.22% and minimum normalized agnostic detection cost function (min a-DCF) of 0.0304 on the ASVspoof 2019 evaluation set. These results confirm the effectiveness of score-aware attention mechanisms and alternating training strategies in enhancing the robustness of SASV systems.

Mobile robotic gas distribution mapping (GDM) provides critical situational awareness during emergency responses to hazardous gas releases. However, most systems still rely on teleoperation, limiting scalability and response speed. Autonomous active GDM is challenging in unknown and cluttered environments, because the robot must simultaneously explore traversable space, map the environment, and infer the gas distribution belief from sparse chemical measurements. We address this by formulating active GDM as a next-best-trajectory informative path planning (IPP) problem and propose XIT (Exploration and Exploitation Informed Trees), a sampling-based planner that balances exploration and exploitation by generating concurrent trajectories toward exploration-rich goals while collecting informative gas measurements en route. XIT draws a batch of samples from an Upper Confidence Bound (UCB) information field derived from the current gas posterior and expands trees using a cost that trades off travel effort against information acquisition. To enable plume-aware exploration, we introduce the gas frontier concept, defined as unobserved regions adjacent to high gas concentrations, and propose the Wavefront Gas Frontier Detection (WGFD) algorithm for their identification. High-fidelity simulations and a real-world experiment demonstrate the benefits of XIT in terms of GDM quality and efficiency. Although developed for active GDM, XIT is readily applicable to other robotic information-gathering tasks in unknown environments that face the exploration and exploitation trade-off.

In safety-critical applications such as medical image segmentation, prediction systems must provide reliability guarantees that extend beyond conventional expected loss control. While risk-controlling prediction sets (RCPS) offer probabilistic guarantees on the expected risk, they fail to capture tail behavior and worst-case scenarios that are crucial in high-stakes settings. This paper introduces optimized certainty equivalent RCPS (OCE-RCPS), a novel framework that provides high-probability guarantees on general optimized certainty equivalent (OCE) risk measures, including conditional value-at-risk (CVaR) and entropic risk. OCE-RCPS leverages upper confidence bounds to identify prediction set parameters that satisfy user-specified risk tolerance levels with provable reliability. We establish theoretical guarantees showing that OCE-RCPS satisfies the desired probabilistic constraint for loss functions such as miscoverage and false negative rate. Experiments on image segmentation demonstrate that OCE-RCPS consistently meets target satisfaction rates across various risk measures and reliability configurations, while OCE-CRC fails to provide probabilistic guarantees.

Accurate, computationally efficient, and adaptive vehicle models are essential for autonomous vehicle control. Hybrid models that combine a nominal model with a Gaussian Process (GP)-based residual model have emerged as a promising approach. However, the GP-based residual model suffers from the curse of dimensionality, high evaluation complexity, and the inefficiency of online learning, which impede the deployment in real-time vehicle controllers. To address these challenges, we propose SPLIT, a sparse incremental learning framework for control-oriented vehicle dynamics modeling. SPLIT integrates three key innovations: (i) Model Decomposition. We decompose the vehicle model into invariant elements calibrated by experiments, and variant elements compensated by the residual model to reduce feature dimensionality. (ii) Local Incremental Learning. We define the valid region in the feature space and partition it into subregions, enabling efficient online learning from streaming data. (iii) GP Sparsification. We use bayesian committee machine to ensure scalable online evaluation. Integrated into model-based controllers, SPLIT is evaluated in aggressive simulations and real-vehicle experiments. Results demonstrate that SPLIT improves model accuracy and control performance online. Moreover, it enables rapid adaptation to vehicle dynamics deviations and exhibits robust generalization to previously unseen scenarios.

This paper provides two results that are useful in the study of the existence and the stability properties of a periodic solution for a given dynamical system. The first result deals with scalar time-periodic systems and establishes the equivalence of the existence of a periodic solution and the existence of a bounded solution. The second result provides sufficient conditions for the existence and the stability of a periodic solution for a time-periodic dynamical system. Both results are applied to extremum seeking problems for a static output map with no plant dynamics and novel non-local results are provided without the use of averaging theorems and singular perturbation arguments.

As deepfake audio becomes more realistic and diverse, developing generalizable countermeasure systems has become crucial. Existing detection methods primarily depend on XLS-R front-end features to improve generalization. Nonetheless, their performance remains limited, partly due to insufficient attention to fine-grained information, such as physiological cues or frequency-domain features. In this paper, we propose BreathNet, a novel audio deepfake detection framework that integrates fine-grained breath information to improve generalization. Specifically, we design BreathFiLM, a feature-wise linear modulation mechanism that selectively amplifies temporal representations based on the presence of breathing sounds. BreathFiLM is trained jointly with the XLS-R extractor, in turn encouraging the extractor to learn and encode breath-related cues into the temporal features. Then, we use the frequency front-end to extract spectral features, which are then fused with temporal features to provide complementary information introduced by vocoders or compression artifacts. Additionally, we propose a group of feature losses comprising Positive-only Supervised Contrastive Loss (PSCL), center loss, and contrast loss. These losses jointly enhance the discriminative ability, encouraging the model to separate bona fide and deepfake samples more effectively in the feature space. Extensive experiments on five benchmark datasets demonstrate state-of-the-art (SOTA) performance. Using the ASVspoof 2019 LA training set, our method attains 1.99% average EER across four related eval benchmarks, with particularly strong performance on the In-the-Wild dataset, where it achieves 4.70% EER. Moreover, under the ASVspoof5 evaluation protocol, our method achieves an EER of 4.94% on this latest benchmark.

We introduce Discernment, a semantic communication system that transmits the meaning of physical signals (baseband radio and audio) over a technical channel using GenAI models operating in discrete spaces. Discernment dynamically adapts to channel impairments - modeled as erasure channels - by switching between an autoregressive or a diffusion-based generative algorithm, depending on the erasure pattern. Our results show that Discernment maintains semantic integrity even as channel capacity severely degrades, exhibiting very small and graceful performance decline in both classification accuracy and statistical fidelity of the reconstructed meaning. These findings demonstrate Discernment's ability to adjust to diverse physical channel conditions while maintaining spectral efficiency and low model complexity, making it well suited for IoT deployments and strongly motivating further research on this semantic channel paradigm.

Off-grid targets whose Doppler (or angle) does not lie on the discrete processing grid can severely degrade classical normalized matched-filter (NMF) detectors: even at high SNR, the detection probability may saturate at operationally relevant low false-alarm rates. A principled remedy is the continuous-parameter GLRT, which maximizes a normalized correlation over the parameter domain; however, dense scanning increases test-time cost and remains sensitive to covariance mismatch through whitening. We propose DopplerGLRTNet, an amortized off-grid GLRT: a lightweight regressor predicts the continuous Doppler within a resolution cell from the whitened observation, and the detector outputs a single GLRT/NMF-like score given by the normalized matched-filter energy at the predicted Doppler. Monte Carlo simulations in Gaussian and compound-Gaussian clutter show that DopplerGLRTNet mitigates off-grid saturation, approaches dense-scan performance at a fraction of its cost, and improves robustness to covariance estimation at the same empirically calibrated Pfa.

Small Island Developing States (SIDS) are disproportionately exposed to climate-driven disasters, yet often rely on fragile terrestrial networks that fail when they are most needed. TV White Space (TVWS) links offer long-range, low-power coverage; however, current deployments depend on Protocol to Access White Spaces (PAWS) database connectivity for channel authorization, creating a single point of failure during outages. We present SIDSense, an edge AI framework for database-free TVWS operation that preserves regulatory intent through a compliance-gated controller, audit logging, and graceful degradation. SIDSense couples CNN-based spectrum classification with a hybrid sensing-first, authorization-as-soon-as-possible workflow and co-locates sensing and video enhancement with a private 5G stack on a maritime vessel to sustain situational-awareness video backhaul. Field experiments in Barbados demonstrate sustained connectivity during simulated PAWS outages, achieving 94.2% sensing accuracy over 470-698 MHz with 23 ms mean decision latency, while maintaining zero missed 5G Layer-1 (L1) deadlines under GPU-aware scheduling. We release an empirical Caribbean TVWS propagation and occupancy dataset and look to contribute some of the components of the SIDSense pipeline to the open source community to accelerate resilient connectivity deployments in climate-vulnerable regions.

In this paper, we propose a fast algorithm for element selection, a multiplication-free form of dimension reduction that produces a dimension-reduced vector by simply selecting a subset of elements from the input. Dimension reduction is a fundamental technique for reducing unnecessary model parameters, mitigating overfitting, and accelerating training and inference. A standard approach is principal component analysis (PCA), but PCA relies on matrix multiplications; on resource-constrained systems, the multiplication count itself can become a bottleneck. Element selection eliminates this cost because the reduction consists only of selecting elements, and thus the key challenge is to determine which elements should be retained. We evaluate a candidate subset through the minimum mean-squared error of linear regression that predicts a target vector from the selected elements, where the target may be, for example, a one-hot label vector in classification. When an explicit target is unavailable, the input itself can be used as the target, yielding a reconstruction-based criterion. The resulting optimization is combinatorial, and exhaustive search is impractical. To address this, we derive an efficient formula for the objective change caused by swapping a selected and an unselected element, using the matrix inversion lemma, and we perform a swap-based local search that repeatedly applies objective-decreasing swaps until no further improvement is possible. Experiments on MNIST handwritten-digit images demonstrate the effectiveness of the proposed method.