Papers

Machine learning researchers strive to develop better and better algorithms to solve computer vision problems, such as image classification. In recent years, the classification of micro-Doppler spectrograms has also benefited from these findings. Convolutional neural networks (CNNs) became the gold standard for these tasks. Unfortunately, CNNs can work on fixed-resolution images, or they need to resize mismatched images to fit input dimensions. It can become a problem when micro-Doppler spectrograms are generated with e.g. different integration times. The goal of this work was to classify the UAV and helicopters micro-Doppler spectrograms with different duration times, using the Vision Transformer (ViT) architecture. Before that, spectrograms signal-to-noise-ratio and micro-Doppler features visibility were improved by denoising algorithm based on modified Dual Tree Complex Wavelet Transform. The experiments were conducted on real data collected using surveillance, short range, military radar. As a result, it has been shown that the ViT model achieved 97.76% accuracy for this task. To further interpret the network performance, the raw self-attention maps were analyzed.

We introduce MedCondDiff, a diffusion-based framework for multi-organ medical image segmentation that is efficient and anatomically grounded. The model conditions the denoising process on semantic priors extracted by a Pyramid Vision Transformer (PVT) backbone, yielding a semantically guided and lightweight diffusion architecture. This design improves robustness while reducing both inference time and VRAM usage compared to conventional diffusion models. Experiments on multi-organ, multi-modality datasets demonstrate that MedCondDiff delivers competitive performance across anatomical regions and imaging modalities, underscoring the potential of semantically guided diffusion models as an effective class of architectures for medical imaging tasks.

Real-world intelligence systems usually operate by combining offline learning and online adaptation with highly correlated and non-stationary system data or signals, which, however, has rarely been investigated theoretically in the literature. This paper initiates a theoretical investigation on the prediction performance of a two-stage learning framework combining offline and online algorithms for a class of nonlinear stochastic dynamical systems. For the offline-learning phase, we establish an upper bound on the generalization error for approximate nonlinear-least-squares estimation under general datasets with strong correlation and distribution shift, leveraging the Kullback-Leibler divergence to quantify the distributional discrepancies. For the online-adaptation phase, we address, on the basis of the offline-trained model, the possible uncertain parameter drift in real-world target systems by proposing a meta-LMS prediction algorithm. This two-stage framework, integrating offline learning with online adaptation, demonstrates superior prediction performances compared with either purely offline or online methods. Both theoretical guarantees and empirical studies are provided.

Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical reliability. The proposal of a holistic framework to establish a foundation for IoT systems with a focus on contextual decision making, proactive adaptation, and scalable structure. A structured process for IoT systems with accuracy and interconnected development would support reducing power consumption and support grid stability. This study presents the feasibility of this proposal through the application of each aspect of the framework. This system would have long term forecasting, short term forecasting, anomaly detection, and consideration of qualitative data with any energy management decisions taken. Performance was evaluated on Power Consumption Time Series data to display the direct application of the framework.

This paper investigates a distributed ISEA system under a Bayesian framework, focusing on incorporating task-relevant priors to maximize inference performance. At the sensing level, an RWB estimator with a GM prior is designed. By weighting class-conditional posterior means with responsibilities, RWB effectively denoises features and outperforms ML at low SNR. At the communication level, two theoretical proxies are introduced: the computation-optimal and decision-optimal proxies. Optimal transceiver designs in terms of closed-form power allocation are derived for both TDM and FDM settings, revealing threshold-based and dual-decomposition structures. Results show that the discriminant-aware allocation yields additional inference gains.

As 6G networks demand massive connectivity and stronger interference control, rate-splitting multiple access (RSMA) is attractive because it superposes a common stream and user-private streams and remains effective under imperfect CSIT and heterogeneous traffic. In practical multiuser deployments, two considerations arise: the common stream decoding constraint imposed by the weakest user, and residual inter-user interference can remain non-negligible, particularly in single-input single-output (SISO) broadcast settings and under an imperfect CSIT scenario. Motivated by prior advances of RSMA research, we investigate a complementary mechanism-fluid antenna systems (FAS), with dynamic port reconfiguration supplies adaptive spatial selectivity without altering the RSMA signaling structure. Can FAS help alleviate these considerations and enhance RSMA performance? We develop a tractable correlation-aware analytical framework based on block-correlation models, including constant block correlation (CBC) and variable block correlation (VBC), to capture realistic spatial dependence among ports. Closed-form expressions are derived for outage probability (OP) and average capacity (AC), revealing how port reconfiguration strengthens the weakest effective channel and improves SINR through higher channel gains and lower relative noise impact. Monte Carlo simulations verify the analysis and show that VBC matches simulations more tightly than CBC across all port configurations. Finally, FAS-RSMA provides clear gains over conventional antenna systems and NOMA, achieving lower OP and higher AC by combining RSMA interference management with FAS spatial diversity.

Data-Enabled Predictive Control (DeePC) has emerged as a powerful framework for controlling unknown systems directly from input-output data. For nonlinear systems, recent work has proposed selecting relevant subsets of data columns based on geometric proximity to the current operating point. However, such proximity-based selection ignores the control objective: different reference trajectories may benefit from different data even at the same operating point. In this paper, we propose a datamodel-based approach that learns a context-dependent influence function mapping the current initial trajectory and reference trajectory to column importance scores. Adapting the linear datamodel framework from machine learning, we model closed-loop cost as a linear function of column inclusion indicators, with coefficients that depend on the control context. Training on closed-loop simulations, our method captures which data columns actually improve tracking performance for specific control tasks. Experimental results demonstrate that task-aware selection substantially outperforms geometry-based heuristics, particularly when using small data subsets.

This paper introduces a novel reachability problem for the scenario involving two agents, where one agent follows another agent using a feedback strategy. The geometry of the reachable set for an agent, termed dependent reachable set, is characterized using the constant bearing pursuit strategy as a case study. Key theoretical results are presented that provide geometric bounds for the associated dependent reachable set. Simulation results are presented to empirically establish the shape of the dependent reachable set. In the process, an original optimization problem is formulated and analyzed for the constant bearing pursuit strategy.

Purpose: To benchmark open-source or commercial medical image-specific VLMs against real-world radiologist-written reports. Methods: This retrospective study included adult patients who presented to the emergency department between January 2022 and April 2025 and underwent same-day CXR and CT for febrile or respiratory symptoms. Reports from five VLMs (AIRead, Lingshu, MAIRA-2, MedGemma, and MedVersa) and radiologist-written reports were randomly presented and blindly evaluated by three thoracic radiologists using four criteria: RADPEER, clinical acceptability, hallucination, and language clarity. Comparative performance was assessed using generalized linear mixed models, with radiologist-written reports treated as the reference. Finding-level analyses were also performed with CT as the reference. Results: A total of 478 patients (median age, 67 years [interquartile range, 50-78]; 282 men [59.0%]) were included. AIRead demonstrated the lowest RADPEER 3b rate (5.3% [76/1434] vs. radiologists 13.9% [200/1434]; P<.001), whereas other VLMs showed higher disagreement rates (16.8-43.0%; P<.05). Clinical acceptability was the highest with AIRead (84.5% [1212/1434] vs. radiologists 74.3% [1065/1434]; P<.001), while other VLMs performed worse (41.1-71.4%; P<.05). Hallucinations were rare with AIRead, comparable to radiologists (0.3% [4/1425]) vs. 0.1% [1/1425]; P=.21), but frequent with other models (5.4-17.4%; P<.05). Language clarity was higher with AIRead (82.9% [1189/1434]), Lingshu (88.0% [1262/1434]), and MedVersa (88.4% [1268/1434]) compared with radiologists (78.1% [1120/1434]; P<.05). Sensitivity varied substantially across VLMs for the common findings: AIRead, 15.5-86.7%; Lingshu, 2.4-86.7%; MAIRA-2, 6.0-72.0%; MedGemma, 4.8-76.7%; and MedVersa, 20.2-69.3%. Conclusion: Medical VLMs for CXR report generation exhibited variable performance in report quality and diagnostic measures.

Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable machine learning systems therefore requires methods that can both estimate predictive uncertainty and detect out-of-distribution (OOD) samples in a unified manner. In this paper, we propose TIE: a Training–Inversion–Exclusion framework for visually interpretable and uncertainty-guided anomaly detection that jointly addresses these challenges through iterative refinement. TIE extends a standard $n$-class classifier to an $(n+1)$-class model by introducing a garbage class initialized with Gaussian noise to represent outlier inputs. Within each epoch, TIE performs a closed-loop process of training, inversion, and exclusion, where highly uncertain inverted samples reconstructed from the just-trained classifier are excluded into the garbage class. Over successive iterations, the inverted samples transition from noisy artifacts into visually coherent class prototypes, providing transparent insight into how the model organizes its learned manifolds. During inference, TIE rejects OOD inputs by either directly mapping them to the garbage class or producing low-confidence, uncertain misclassifications within the in-distribution classes that are easily separable, all without relying on external OOD datasets. A comprehensive threshold-based evaluation using multiple OOD metrics and performance measures such as AUROC, AUPR, and FPR@95%TPR demonstrates that TIE offers a unified and interpretable framework for robust anomaly detection and calibrated uncertainty estimation (UE) achieving near-perfect OOD detection with \textbf{\(\!\approx\!\) 0 FPR@95%TPR} when trained on MNIST or FashionMNIST and tested against diverse unseen datasets.

High-precision localization and environmental sensing are essential for a new wave of applications, ranging from industrial automation and autonomous systems to augmented reality and remote healthcare. Conventional wireless methods, however, often face limitations in accuracy, reliability, and coverage, especially in complex non-line-of-sight (NLoS) environments. Reconfigurable Intelligent Surfaces (RISs) have emerged as a key enabling technology, offering dynamic control over the radio propagation environment to overcome these challenges. This chapter provides a comprehensive overview of RIS-aided localization and sensing, bridging fundamental theory with practical implementation. The core principles of the RIS technology are first described detailing how programmable metasurfaces can intelligently combat blockages, enhance signal diversity, and create virtual line-of-sight (LoS) links. The chapter then reviews a range of application scenarios where RISs can offer significant improvements. A significant portion of the chapter is dedicated to algorithmic methodologies, covering beam sweeping protocols, codebook-based techniques, and advanced optimization and machine learning strategies for both localization and sensing. To validate the theoretical concepts in real-world conditions, recent experimental results using an RIS prototype are detailed, showcasing the technology's efficacy and illustrating key performance trade-offs.

Expected goals (xG) models estimate the probability that a shot results in a goal from its context (e.g., location, pressure), but they operate only on observed shots. We propose xG+, a possession-level framework that first estimates the probability that a shot occurs within the next second and its corresponding xG if it were to occur. We also introduce ways to aggregate this joint probability estimate over the course of a possession. By jointly modeling shot-taking behavior and shot quality, xG+ remedies the conditioning-on-shots limitation of standard xG. We show that this improves predictive accuracy at the team level and produces a more persistent player skill signal than standard xG models.

We introduce EEG Autoclean Vision Language AI (ICVision) a first-of-its-kind system that emulates expert-level EEG ICA component classification through AI-agent vision and natural language reasoning. Unlike conventional classifiers such as ICLabel, which rely on handcrafted features, ICVision directly interprets ICA dashboard visualizations topography, time series, power spectra, and ERP plots, using a multimodal large language model (GPT-4 Vision). This allows the AI to see and explain EEG components the way trained neurologists do, making it the first scientific implementation of AI-agent visual cognition in neurophysiology. ICVision classifies each component into one of six canonical categories (brain, eye, heart, muscle, channel noise, and other noise), returning both a confidence score and a human-like explanation. Evaluated on 3,168 ICA components from 124 EEG datasets, ICVision achieved k = 0.677 agreement with expert consensus, surpassing MNE ICLabel, while also preserving clinically relevant brain signals in ambiguous cases. Over 97% of its outputs were rated as interpretable and actionable by expert reviewers. As a core module of the open-source EEG Autoclean platform, ICVision signals a paradigm shift in scientific AI, where models do not just classify, but see, reason, and communicate. It opens the door to globally scalable, explainable, and reproducible EEG workflows, marking the emergence of AI agents capable of expert-level visual decision-making in brain science and beyond.

Interpreting seismic horizons is a critical task for characterizing subsurface structures in hydrocarbon exploration. Recent advances in deep learning, particularly U-Net-based architectures, have significantly improved automated horizon tracking. However, challenges remain in accurately segmenting complex geological features and interpolating horizons from sparse annotations. To address these issues, a hybrid framework is presented that integrates advanced U-Net variants with spatial clustering to enhance horizon continuity and geometric fidelity. The core contribution is the Context Fusion Attention (CFA) U-Net, a novel architecture that fuses spatial and Sobel-derived geometric features within attention gates to improve both precision and surface completeness. The performance of five architectures, the U-Net (Standard and compressed), U-Net++, Attention U-Net, and CFA U-Net, was systematically evaluated across various data sparsity regimes (10-, 20-, and 40-line spacing). This approach outperformed existing baselines, achieving state-of-the-art results on the Mexilhao field (Santos Basin, Brazil) dataset with a validation IoU of 0.881 and MAE of 2.49ms, and excellent surface coverage of 97.6% on the F3 Block of the North Sea dataset under sparse conditions. The framework further refines merged horizon predictions (inline and cross-line) using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to produce geologically plausible surfaces. The results demonstrate the advantages of hybrid methodologies and attention-based architectures enhanced with geometric context, providing a robust and generalizable solution for seismic interpretation in structurally complex and data-scarce environments.

Fixed-point number representation is commonly employed in digital VLSI designs that have stringent hardware efficiency constraints. However, fixed-point numbers cover a relatively small dynamic range for a given bitwidth. In contrast, floating-point numbers offer a larger dynamic range at the cost of increased hardware complexity. In this paper, we propose a novel number format called variable-point (VP). VP numbers cover a larger dynamic range than fixed-point numbers with similar bitwidth, without notably increasing hardware complexity – this allows for a more efficient representation of signals with high dynamic range. To demonstrate the efficacy of the proposed VP number format, we consider a matrix-vector multiplication engine for spatial equalization in multi-antenna wireless communication systems involving high-dynamic-range signals. Through post-layout VLSI implementation results, we demonstrate that the proposed VP-based design achieves 20% and 10% area and power savings, respectively, compared to a fully optimized fixed-point design, without incurring any noticeable performance degradation.

Accurate material recognition is critical for safe and effective laser cutting, as misidentification can lead to poor cut quality, machine damage, or the release of hazardous fumes. Laser speckle sensing has recently emerged as a low-cost and non-destructive modality for material classification; however, prior work has either relied on computationally expensive backbone networks or addressed only limited subsets of materials. In this study, A lightweight convolutional neural network (CNN) tailored for speckle patterns is proposed, designed to minimize parameters while maintaining high discriminative power. Using the complete SensiCut dataset of 59 material classes spanning woods, acrylics, composites, textiles, metals, and paper-based products, the proposed model achieves 95.05% test accuracy, with macro and weighted F1-scores of 0.951. The network contains only 341k trainable parameters (~1.3 MB) – over 70X fewer than ResNet-50 – and achieves an inference speed of 295 images per second, enabling deployment on Raspberry Pi and Jetson-class devices. Furthermore, when materials are regrouped into nine and five practical families, recall exceeds 98% and approaches 100%, directly supporting power and speed preset selection in laser cutters. These results demonstrate that compact, domain-specific CNNs can outperform large backbones for speckle-based material classification, advancing the feasibility of material-aware, edge-deployable laser cutting systems.

Savitzky-Golay (SG) smoothers are noise suppressing filters operating on the principle of projecting noisy input onto the subspace of polynomials. A poorly selected polynomial order results in over- or under-smoothing which shows as either bias or excessive noise at the output. In this study, we apply the N-fold cross-validation technique (also known as leave-one-out cross-validation) for model order selection and show that the inherent analytical structure of the SG filtering problem, mainly its minimum norm formulation, enables an efficient and effective order selection solution. More specifically, a novel connection between the total prediction error and SG-projection spaces is developed to reduce the implementation complexity of cross-validation method. The suggested solution compares favorably with the state-of-the-art Bayesian Information Criterion (BIC) rule in non-asymptotic signal-to-noise ratio (SNR) and sample size regimes. MATLAB codes reproducing the numerical results are provided.

Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the capacity of small batteries. This paper presents a CNN hardware accelerator optimized for object classification in miniature imaging systems. It processes data from a spatial Dynamic Vision Sensor (DVS), reconfigurable to a temporal DVS via pixel sharing, minimizing sensor area. By using ternary DVS outputs and a ternary-input, binary-weight neural network, the design reduces computation and memory needs. Fabricated in 28 nm CMOS, the accelerator cuts data size by 81% and MAC operations by 27%. It achieves 440 ms inference time at just 1.6 mW power consumption, improving the Figure-of-Merit (FoM) by 7.3x over prior CNN accelerators for miniature systems.

This paper introduces a novel Lyapunov-based small-gain methodology for establishing fixed-time stability (FxTS) guarantees in interconnected dynamical systems. Specifically, we consider interconnections in which each subsystem admits an individual fixed-time input-to-state stability (ISS) Lyapunov function that certifies FxT-ISS. We then show that if a nonlinear small-gain condition is satisfied, then the entire interconnected system is FxTS. Our results are analogous to existing Lyapunov-based small-gain theorems developed for asymptotic and finite-time stability, thereby filling an important gap in the stability analysis of interconnected dynamical systems. The proposed theoretical tools are further illustrated through analytical and numerical examples, including the first result on fixed-time feedback optimization of dynamical systems without time-scale separation between the plant and the controller.

In this paper, we explore how quantum resources can be used to increase the rate of private distributed matrix multiplication (PDMM). In PDMM, a user who has two high-dimensional matrices, A and B, and lacks the computational capabilities to apply matrix multiplication locally, divides the matrices A and B into K and L sub-blocks, respectively. Then, the user sends them to N servers to apply the required multiplication privately, i.e., any $T$ colluding servers cannot get any information about the user's matrices. The goal is to reduce the number of servers needed to perform the required matrix multiplication, thereby decreasing the communication cost. First, in the high-privacy regime, the state-of-the-art classical code is called the gap additive secure polynomial (GASP) code. We define a feasibility requirement in the quantum setting for the GASP code such that the highest performance is achieved when the requirement is satisfied. Thus, super-dense coding gain is achieved when the feasibility condition is satisfied. We show that when $T \geq KL-K+1$, the feasibility condition is always satisfied and the GASP code can be extended to the quantum version. In the case of $T < KL-K+1$, the feasibility can still be satisfied. To further examine this behavior, we numerically study how the minimum privacy requirement depends on the matrix dimensions and provide a quadratic estimate for this relation. The results suggest that feasibility can be achieved when $T \sim 0.5 KL$. Second, in the low-privacy regime, the recently developed cyclic-addition degree tables (CAT) and discretely optimized GASP (DOG) codes are among the most efficient known classical constructions for PDMM. We show that the feasibility condition developed for GASP can be adopted for both CAT and DOG codes as well, thus unifying the feasibility framework for multiple classical PDMM coding schemes.

This paper considers state estimation for general nonlinear discrete-time systems subject to measurement noise and possibly unbounded unknown inputs. To approach this problem, we first propose the concept of strong nonlinear detectability. This condition is sufficient and necessary for the existence of unknown input state estimators (UISEs), which reconstruct states from noisy sampled measurements and yield bounded estimation error even for unbounded unknown inputs. Based on the proposed detectability notion, a UISE is designed via a moving horizon estimation strategy using a full-order model as well as past and current measurements. Next, we tighten this detectability notion to design a two-stage MHE-based UISE, which is computationally more efficient than the MHE-based UISE using full-order models. In a simulation example with a plant growth process, both variants of MHE-based UISEs are compared with a conventional MHE to illustrate the merits of the developed methods.

The impressive growth of wireless data networks has recently led to increased attention to the issue of electromagnetic pollution and the fulfillment of electromagnetic field (EMF) exposure limits. This paper tackles the problem of power control in user-centric cell-free massive multiple-input-multiple-output (CF-mMIMO) systems under EMF constraints. Specifically, the power allocation maximizing the minimum data rate across users is derived for both the uplink and the downlink. To solve such optimization problems, two approaches are proposed, i.e., model-based and data-driven. The proposed model-based solutions for the downlink utilize successive convex optimization and the log-sum-exp approximation for the minimum of a discrete set, whereas ordinary techniques are employed for the uplink. With regard to data-driven solutions, solutions based on both end-to-end architectures and deep unfolding techniques are explored. Extensive numerical results confirm that the proposed model-based solutions effectively fulfill the EMF constraints while ensuring very good performance; moreover, the results show that the proposed data-driven approaches can tightly approximate the performance of model-based solutions but with much lower computational complexity.

In modern communication systems, the fidelity of analog-to-digital converters (ADCs) is limited by sampling clock jitter, i.e., small random timing deviations that undermine ideal sampling. Traditional scalar models often treat jitter as independent Gaussian noise, which makes it essentially untrackable, whereas real ADCs also exhibit temporally correlated (spectrally colored) imperfections. Moreover, spatial cross-correlations between channels in multiple-input multiple-output (MIMO) ADCs are commonly neglected. This paper addresses the joint tracking and compensation of random, cross-correlated timing errors in ADC arrays by modeling jitter as a coupled vector autoregressive process of order one (VAR(1)). We propose a pilot-tone-based Kalman smoother to track and compensate the jitter, and simulations demonstrate substantial reductions in jitter-induced distortion across diverse scenarios.

An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers. In this work, we introduce the concept of distributed dynamic associative memory (DDAM), which extends classical AM to settings with multiple agents and time-varying data streams. In DDAM, each agent maintains a local AM that must not only store its own associations but also selectively memorize information from other agents based on a specified interest matrix. To address this problem, we propose a novel tree-based distributed online gradient descent algorithm, termed DDAM-TOGD, which enables each agent to update its memory on the fly via inter-agent communication over designated routing trees. We derive rigorous performance guarantees for DDAM-TOGD, proving sublinear static regret in stationary environments and a path-length dependent dynamic regret bound in non-stationary environments. These theoretical results provide insights into how communication delays and network structure impact performance. Building on the regret analysis, we further introduce a combinatorial tree design strategy that optimizes the routing trees to minimize communication delays, thereby improving regret bounds. Numerical experiments demonstrate that the proposed DDAM-TOGD framework achieves superior accuracy and robustness compared to representative online learning baselines such as consensus-based distributed optimization, confirming the benefits of the proposed approach in dynamic, distributed environments.

OWC has been considered as a key enabling technology to unlock unprecedented speeds of communication, supporting high demands of data traffic. In this paper, infrared lasers are used as optical transmitters operating in an indoor environment under eye safety regulations due to their high modulation speed. To provide efficient multiple access service, NOMA-based transmission is implemented to multiplex messages intended to multiple users in the power domain and maximize the spectral efficiency of our laser-based OWC network. In particular, a BIA outer precoder is designed to coordinate the transmission among multiple APs and determine the precoding matrices for groups of users potential formed according to NOMA principles. For effective use of NOMA, an optimization problem is formulated to maximize the sum rate of the network through forming optimum groups under certain joint conditions, efficient power allocation, high quality of service for each weak and strong users, and high overall system performance. Such optimization problems are defined as max-min fractional programs difficult to solve in practice. Therefore, a dynamic application for NOMA is introduced using two algorithms. First, a RF-aided dynamic algorithm is designed to form multiple groups, where users exchange binary variables among them through an RF system to establish distance-based weight edges, which are used as a metric for the grouping process. Second, a dynamic power allocation is proposed to determine the optimum power allocated to each group, while the users belonging to a certain group receive their traffic demands regardless of their classification as weak or strong. The results show the convergence of the proposed dynamic application to the optimum solution, and its high performance in terms of sum rate, fairness, and energy efficiency compared to counterpart schemes.

Providing rigorous reachability guarantees for unknown complex systems is a crucial and challenging task. In this paper, we present a novel data-driven framework that addresses this challenge by leveraging Koopman operator theory. Instead of operating in the state space, the proposed method encodes model uncertainty from finite data directly into Koopman spectral representation with quantifiable error bounds. Leveraging this spectral information, we systematically determine time intervals within which trajectories from the initial set are guaranteed, with a prescribed probability, to reach the target set. We finally demonstrate the efficacy of our framework in numerical examples.

Automatic modulation recognition (AMR) is a crucial step in wireless communication systems, which identifies the modulation scheme from detected signals to provide key information for further processing. However, previous work has mainly focused on the identification of a single signal, overlooking the phenomenon of multiple signal superposition in practical channels and the signal detection procedures that must be conducted beforehand. Considering the susceptibility of radio frequency (RF) signals to noise interference and significant spectral variations, we propose a novel Hierarchical Feature Integration (HIFI)-YOLO framework for multi-signal joint detection and modulation recognition. Our HIFI-YOLO framework, with its unique design of hierarchical feature integration, effectively enhances the representation capability of features in different modules, thereby improving detection performance. We construct a large-scale AMR dataset specifically tailored for scenarios of the coexistence or overlapping of multiple signals transmitted through channels with realistic propagation conditions, consisting of diverse digital and analog modulation schemes. Extensive experiments on our dataset demonstrate the excellent performance of HIFI-YOLO in multi-signal detection and modulation recognition as a joint approach.

Radar automatic target recognition (RATR) based on high-resolution range profile (HRRP) has attracted increasing attention due to its ability to capture fine-grained structural features. However, recognizing targets under electronic countermeasures (ECM), especially the mainstream interrupted-sampling repeater jamming (ISRJ), remains a significant challenge, as HRRPs often suffer from serious feature distortion. To address this, we propose a robust HRRP recognition method guided by prior jamming information. Specifically, we introduce a point spread function (PSF) as prior information to model the HRRP distortion induced by ISRJ. Based on this, we design a recognition network that leverages this prior through a prior-guided feature interaction module and a hybrid loss function to enhance the model's discriminative capability. With the aid of prior information, the model can learn invariant features within distorted HRRP under different jamming parameters. Both the simulated and measured-data experiments demonstrate that our method consistently outperforms state-of-the-art approaches and exhibits stronger generalization capabilities when facing unseen jamming parameters.

Magnetic particle imaging reconstructs tracer distributions using a system matrix obtained through time-consuming, noise-prone calibration measurements. Methods for addressing imperfections in measured system matrices increasingly rely on deep neural networks, yet curated training data remain scarce. This study evaluates whether physics-based simulated system matrices can be used to train deep learning models for different system matrix restoration tasks, i.e., denoising, accelerated calibration, upsampling, and inpainting, that generalize to measured data. A large system matrices dataset was generated using an equilibrium magnetization model extended with uniaxial anisotropy. The dataset spans particle, scanner, and calibration parameters for 2D and 3D trajectories, and includes background noise injected from empty-frame measurements. For each restoration task, deep learning models were compared with classical non-learning baseline methods. The models trained solely on simulated system matrices generalized to measured data across all tasks: for denoising, DnCNN/RDN/SwinIR outperformed DCT-F baseline by >10 dB PSNR and up to 0.1 SSIM on simulations and led to perceptually better reconstuctions of real data; for 2D upsampling, SMRnet exceeded bicubic by 20 dB PSNR and 0.08 SSIM at $\times 2$-$\times 4$ which did not transfer qualitatively to real measurements. For 3D accelerated calibration, SMRnet matched tricubic in noiseless cases and was more robust under noise, and for 3D inpainting, biharmonic inpainting was superior when noise-free but degraded with noise, while a PConvUNet maintained quality and yielded less blurry reconstructions. The demonstrated transferability of deep learning models trained on simulations to real measurements mitigates the data-scarcity problem and enables the development of new methods beyond current measurement capabilities.

Traditional and modern machine learning-based path loss models typically assume a constant prediction variance. We propose a neural network that jointly predicts the mean and link-specific variance by minimizing a Gaussian negative log-likelihood, enabling heteroscedastic uncertainty estimates. We compare shared, partially shared, and independent-parameter architectures using accuracy, calibration, and sharpness metrics on blind test sets from large public RF drive-test datasets. The shared-parameter architecture performs best, achieving an RMSE of 7.4 dB, 95.1 percent coverage for 95 percent prediction intervals, and a mean interval width of 29.6 dB. These uncertainty estimates further support link-specific coverage margins, improve RF planning and interference analyses, and provide effective self-diagnostics of model weaknesses.