Search Results (1,800)

Semi-supervised joint classification of Hyperspectral Images (HSIs) and LiDAR-derived Digital Surface Models (DSMs) remains challenging due to scarcity of labeled pixels, strong intra-class variability, and the heterogeneous nature of spectral and elevation features. In this work, we propose a Hybrid Mamba–Graph Fusion Network (HMGF-Net) with Multi-Stage Pseudo-Label Refinement (MS-PLR) for semi-supervised hyperspectral–LiDAR classification. The framework employs a spectral–spatial HSI backbone combining 3D–2D convolutions, a compact LiDAR CNN encoder, Mamba-style state-space sequence blocks for long-range spectral and cross-modal dependency modeling, and a graph fusion module that propagates information over a heterogeneous pixel graph. Semi-supervised learning is realized via a three-stage pseudolabeling pipeline that progressively filters, smooths, and re-weights pseudolabels based on prediction confidence, spatial–spectral consistency, and graph neighborhood agreement. We validate HMGF-Net on three benchmark hyperspectral–LiDAR datasets. Compared with a set of eight state-of-the-art (SOTA) baselines, including 3D-CNNs, SSRN, HybridSN, transformer-based models such as SpectralFormer, multimodal CNN–GCN fusion networks, and recent semi-supervised methods, the proposed approach delivers consistent gains in overall accuracy, average accuracy, and Cohen’s kappa, especially in low-label regimes (10% labeled pixels). The results highlight that the synergy between sequence modeling and graph reasoning in combination with carefully designed pseudolabel refinement is essential to maximizing the benefit of abundant unlabeled samples in multimodal remote sensing scenarios. Full article

Glioblastoma (GBM) is the most common and aggressive primary brain tumor in adults, with a median overall survival of fewer than 15 months despite standard-of-care treatment. Accurate preoperative prognostication is essential for personalized treatment planning; however, existing approaches rely primarily on magnetic resonance imaging (MRI) and often overlook the rich histopathological information contained in postoperative whole-slide images (WSIs). The inherent spatiotemporal gap between preoperative MRI and postoperative WSIs substantially hinders effective multimodal integration. To address this limitation, we propose a contrastive-learning-based Imaging–Pathology Synergistic Alignment (CL-IPSA) framework that aligns MRI and WSI data within a shared embedding space, thereby establishing robust cross-modal semantic correspondences. We further construct a cross-modal mapping library that enables patients with MRI-only data to obtain proxy pathological representations via nearest-neighbor retrieval for joint survival modeling. Experiments across multiple datasets demonstrate that incorporating proxy WSI features consistently enhances prediction performance: various convolutional neural networks (CNNs) achieve an average AUC improvement of 0.08–0.10 on the validation cohort and two independent test sets, with SEResNet34 yielding the best performance (AUC = 0.836). Our approach enables non-invasive, preoperative integration of radiological and pathological semantics, substantially improving GBM survival prediction without requiring any additional invasive procedures. Full article

This study investigates the link between changes in physical activity (PA) measured by wearable accelerometers and the worsening of knee osteoarthritis (KOA) symptoms over two years. Using data from 782 participants in the Osteoarthritis Initiative accelerometer sub-study, PA was tracked with hip-worn ActiGraphs. Participants were classified as “worsening” if their Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) total score increased by >10 points and as “stable” otherwise. PA was categorized into daily counts and minutes spent in various intensity levels, and analyzed in 3 h intervals across the day. Of the participants, 123 (15.7%) experienced worsening symptoms. At baseline, both groups had similar characteristics aside from slower sit-to-stand times in the worsening group. Over two years, the worsening group had a greater decline in total daily activity counts (−18% vs. −10%) and more significant reductions during late afternoon and evening (15:00–21:00; −21% vs. −6%). This group also showed a notable decrease in gait speed, longer sit-to-stand times, and a trend towards greater medial joint space narrowing. These findings suggest that larger declines in PA, especially in activities in the late afternoon and evening, are associated with worsening KOA symptoms, although causality cannot be established. Full article

Space–air–ground systems employing free-space optical (FSO) communication leverage high-altitude platform stations (HAPS) to deliver seamless and ubiquitous connectivity. Although FSO links offer high capacity, they are highly susceptible to cloud extinction, which severely degrades link availability. Hybrid FSO/radio-frequency (RF) transmission and cloud-aware HAPS trajectory optimization can enhance resilience. However, the conventional cloud-aware hybrid FSO/RF transmission system based on hard-switching (HS) between the FSO and RF links leads to frequent link transitions and unstable throughput. To address these challenges, we propose a joint optimization framework that integrates soft-switch between FSO and RF links with deep reinforcement learning (DRL) for HAPS trajectory optimization. Soft-switching based on rateless codes (RCs) enables simultaneous transmission over both links, where the receiver accumulates packets until successful decoding with a single feedback. The feedback frequency of RC is sparse, which avoids feedback storms but also poses challenges to HAPS trajectory optimization. The DRL agent proactively optimizes HAPS trajectories to avoid cloud cover and maintain link availability. To address the sparse feedback of RCs for DRL training, a reward-shaped proximal policy optimization (PPO)-based agent is developed to jointly optimize throughput and trajectory smoothness. Simulations using realistic ERA5 data show that RC-PPO achieves higher throughput and smoother trajectories compared to the HS-PPO baseline. Full article

In the context of Industry 4.0 and intelligent manufacturing, conventional serial manipulators face limitations in dynamic task environments due to fixed structural parameters and the traditional decoupling of mechanism design from motion planning. To address this issue, this study proposes SAC-SC (Soft Actor–Critic-based Structure–Control Co-Design), a reinforcement learning framework for the co-design of manipulator link lengths and motion planning policies. The approach is implemented on a custom four-degree-of-freedom PRRR manipulator with manually adjustable link lengths, where a hybrid action space integrates configuration selection at the beginning of each episode with subsequent continuous joint-level control, guided by a multi-objective reward function that balances task accuracy, execution efficiency, and obstacle avoidance. Evaluated in both a simplified kinematic simulator and the high-fidelity MuJoCo physics engine, SAC-SC achieves 100% task success rate in obstacle-free scenarios and 85% in cluttered environments, with a planning time of only 0.145 s per task, over 15 times faster than the two-stage baseline. The learned policy also demonstrates zero-shot transfer between simulation environments. These results indicate that integrating structural parameter optimization and motion planning within a unified reinforcement learning framework enables more adaptive and efficient robotic operation in unstructured environments, offering a promising alternative to conventional decoupled design paradigms. Full article

As a critical component of demolition robots, the rotary joint supports the entire manipulator arm and operates under severe loading conditions, rendering it highly susceptible to fatigue failure. To address this challenge, topology optimization is integrated into the structural design to simultaneously enhance fatigue life and achieve lightweighting. In this work, multiple working conditions of the demolition robot are considered and analyzed to identify the extreme operating condition. By extracting the resultant stress on the rotary joint from the assembled structure under the extreme condition, an equivalent model of the independent rotary joint is established. Given that topology optimization based on the original structure could not yield a usable structure, two topology optimization strategies based on resetting the design space are proposed, including topology optimization based on the partially filled design space and topology optimization within the fully filled design space. By performing topology optimization under different schemes, the optimized rotary joint models are reconstructed through geometric fusion. Numerical results demonstrate that the optimized rotary joints exhibit significant improvements in fatigue performance, with fatigue life doubled compared to the original design. Concurrently, the structural mass is effectively reduced. This proposed method achieves the dual objectives of fatigue life enhancement and lightweight design. Furthermore, the results reveal that resetting the design space when topology optimization fails to obtain a usable structure yields superior topology optimization outcomes, providing a valuable new insight for future structural optimization design processes in similar engineering scenarios. Full article

The expansion of renewables in modern power systems and the coordinated development of upstream and downstream industrial chains are promoting a shift on the utility side from traditional settlement by energy toward operation driven by data and models. Industrial electricity consumption data exhibit pronounced multi-scale temporal structures and sectoral heterogeneity, which makes unified long-term load and generation forecasting while maintaining accuracy, interpretability, and scalability a challenge. From a modern system identification perspective, this paper proposes a System Identification in Adaptive Bayesian Framework (SIABF) for medium- and long-term industrial load forecasting based on daily freeze electricity time series. By combining daily aggregation of high-frequency data, frequency domain analysis, sparse identification, and long-term extrapolation, we first construct daily freeze series from 15 min measurements, and then we apply discrete Fourier transforms and a spectral complexity index to extract dominant periodic components and build an interpretable sinusoidal basis library. A sparse regression formulation with ${\ell }_1$ regularization is employed to select a compact set of key basis functions, yielding concise representations of sector and enterprise load profiles and naturally supporting multivariate and joint multi-sector modeling. Building on this structure, we implement a state-space-implicit physics-informed Bayesian forecasting model and evaluate it on real data from three representative sectors, namely, steel, photovoltaics, and chemical, using one year of 15 min measurements. Under a one-month-ahead evaluation using one year of 15 min measurements, the proposed framework attains a Mean Absolute Percentage Error (MAPE) of 4.5% for a representative PV-related customer case and achieves low single-digit MAPE for high-inertia sectors, often outperforming classical statistical models, sparse learning baselines, and deep learning architectures. These results should be interpreted as indicative given the limited time span and sample size, and broader multi-year, population-level validation is warranted. Full article

In this paper, we propose a source camera identification method based on disentangled feature modeling, aiming to achieve robust extraction of camera fingerprint features under complex imaging and post-processing conditions. To address the severe coupling between image content and camera fingerprint features in existing methods, which makes content interference difficult to suppress, we develop a dual-branch deep learning framework guided by imaging physics. By introducing physical consistency constraints, the proposed framework explicitly separates image content representations from device-related fingerprint features in the feature space, thereby enhancing the stability and robustness of source camera identification. The proposed method adopts two parallel branches: a content modeling branch and a fingerprint feature extraction branch. The content branch is built upon an improved U-Net architecture to reconstruct scene and color information, and further incorporates texture refinement and multi-scale feature fusion to reduce residual content interference in fingerprint modeling. The fingerprint branch employs ResNet-50 as the backbone network to learn discriminative global features associated with the camera imaging pipeline. Based on these branches, fingerprint information dominated by sensor noise is explicitly extracted by computing the residual between the input image and the reconstructed content, and is further encoded through noise analysis and feature fusion for joint camera model classification. Experimental results on multiple public-source camera forensics datasets demonstrate that the proposed method achieves stable and competitive identification performance in same-brand camera discrimination, complex imaging conditions, and post-processing scenarios, validating the effectiveness of the proposed disentangled modeling and physical consistency constraint strategy for source camera identification. Full article

Planar multi-loop fractionated kinematic chains (FKCs)—kinematic chains that can be decomposed into two or more coupled subchains by separating joints or links—are widely used in heavy-duty manipulators, yet their large design space makes automatic synthesis and application-oriented screening challenging. The novelty of this paper is a general automated synthesis-and-screening framework for planar fractionated kinematic chains, regardless of whether multiple joints are present; multiple-joint chains are handled via an equivalent transformation to single-joint models, enabling the construction of a deduplicated topological graph atlas. In the mine scaler manipulator case study, an 18-link, 5-DOF (N18_M5) FKC with two multiple joints is taken as the target and converted into a single-joint equivalent N20_M7 model consisting of three subchains (KC1–KC3). Atlases of the required non-fractionated kinematic chains (NFKCs) for KC1 and KC3 are generated according to their link counts and DOFs. The subchains are then combined as building blocks under joint-fractionation (A-mode) and link-fractionation (B-mode) to enumerate fractionated candidates, and a WL-hash-based procedure is employed for isomorphism discrimination to obtain a non-isomorphic N20_M7 atlas. Finally, a connectivity-calculation-based screening is performed under task-driven structural and functional constraints, yielding 249 feasible configurations for the overall manipulator arm. The proposed pipeline provides standardized representations and reproducible outputs, offering a practical and transferable route from large-scale enumeration to engineering-feasible configuration sets for planar multi-loop FKCs, including those with multiple joints. Full article

This study analyzes the observed patterns of Generative Artificial Intelligence (Generative AI) use by students in higher education through the lens of the sociotechnical systems (STS) theory, focusing on the academic subsystem. The empirical basis is a survey of 2083 students (3686 responses) from seven countries in Central and Eastern Europe, Central Asia, and Central Africa. Based on these data, two proxy indicators are proposed: A₁, reflecting the overall academic use of Generative AI and A₂, characterizing the use of Generative AI in a research context. The results show that Generative AI is widely incorporated into students’ academic activities (A₁ = 79.06%), while research-oriented use remains less common (A₂ = 46.66%) and varies significantly across subsamples. A joint analysis of A₁ and A₂, visualized as a zoned space A₁–A₂, reveals different configurations of academic practices: from a predominance of routine educational use to a more pronounced focus on research tasks. Cross-country comparisons show that in certain contexts (e.g., Kazakhstan and one of the Ukrainian subsamples), Generative AI is more often used in a research context, while in other cases, its use remains predominantly educational and routine. In this sense, the results indicate that Generative AI is beginning to fulfill the role of an emerging student research assistant in students’ academic life: technology has already become a familiar tool for completing educational tasks, but its use in supporting research activities remains fragmented. The proposed model and proxy indicators allow us to describe and compare current configurations of Generative AI use in the academic subsystem. The obtained results provide a basis for further research aimed at a deeper understanding of the factors determining the inclusion of Generative AI in student research practice, as well as for the development of management approaches regarding its use in higher education. Full article

Brain magnetic resonance imaging (MRI) is highly susceptible to motion artifacts that degrade fine structural details and undermine quantitative analysis. Conventional U-Net-based deep learning approaches for motion artifact reduction typically operate only in the image domain and are often trained on data with simplified motion patterns, thereby limiting physical plausibility and generalization. We propose Sim-DDNet, a simulation-data-based dual-domain network that combines k-space-based motion simulation with a joint image-k-space reconstruction architecture. Motion-corrupted data were generated from T2-weighted Alzheimer’s Disease Neuroimaging Initiative brain MR scans using a k-space replacement scheme with three to five random rotational and translational events per volume, yielding 69,283 paired samples (49,852/6969/12,462 for training/validation/testing). Sim-DDNet integrates a real-valued U-Net-like image branch and a complex-valued k-space branch using cross attention, FiLM-based feature modulation, soft data consistency, and composite loss comprising L1, structural similarity index measure (SSIM), perceptual, and k-space-weighted terms. On the independent test set, Sim-DDNet achieved a peak signal-to-noise ratio of 31.05 dB, SSIM of 0.85, and gradient magnitude similarity deviation of 0.077, consistently outperforming U-Net and U-Net++ across all three metrics while producing less blurring, fewer residual ghost/streak artifacts, and reduced hallucination of non-existent structures. These results indicate that dual-domain, data-consistency-aware learning, which explicitly exploits k-space information, is a promising approach for physically plausible motion artifact correction in brain MRI. Full article

This article presents an integrated framework for robust control and cybersecurity of an industrial robot, combining Quantitative Feedback Theory (QFT), digital twin (DT) technology, and a programmable logic controller–based architecture aligned with the requirements of the NIS2 Directive. The study considers a five-axis industrial manipulator modeled as a set of decoupled linear single-input single-output systems subject to parametric uncertainty and external disturbances. For position control of each axis, closed-loop robust systems with QFT-based controllers and prefilters are designed, and the dynamic behavior of the system is evaluated using predefined key performance indicators (KPIs), including tracking errors in joint space and tool space, maximum error, root-mean-square error, and three-dimensional positional deviation. The proposed architecture executes robust control algorithms in the MATLAB/Simulink environment, while a programmable logic controller provides deterministic communication, time synchronization, and secure data exchange. The synchronized digital twin, implemented in the FANUC ROBOGUIDE environment, reproduces the robot’s kinematics and dynamics in real time, enabling realistic hardware-in-the-loop validation with a real programmable logic controller. This work represents one of the first architectures that simultaneously integrates robust control, real programmable logic controller-based execution, a synchronized digital twin, and NIS2-oriented mechanisms for observability and traceability. The conducted simulation and digital twin-based experimental studies under nominal and worst-case dynamic models, as well as scenarios with externally applied single-axis disturbances, demonstrate that the system maintains robustness and tracking accuracy within the prescribed performance criteria. In addition, the study analyzes how the proposed architecture supports the implementation of key NIS2 principles, including command traceability, disturbance resilience, access control, and capabilities for incident analysis and event traceability in robotic manufacturing systems. Full article

With the deployment of mega-constellations, the proliferation of on-orbit Resident Space Objects (RSOs) poses a severe challenge to Space Situational Awareness (SSA). RSOs produce elongated and stripe-like signatures in long-exposure imagery as a result of their relative orbital motion. The accurate detection of these signatures is essential for critical applications like satellite navigation and space debris monitoring. However, on-orbit detection faces two challenges: the obscuration of dim RSOs by complex stray light interference, and their dense overlapping trajectories. To address these challenges, we propose the Shape-Aware Attention Network (SAANet), establishing a unified Shape-Aware Paradigm. The network features a streamlined Shape-Aware Feature Pyramid Network (SA-FPN) with structurally integrated Two-way Orthogonal Attention (TTOA) to explicitly model linear topologies, preserving dim signals under intense stray light conditions. Concurrently, we propose an Adaptive Linear Oriented Bounding Box (AL-OBB) detection head that leverages a Joint Geometric Constraint Mechanism to resolve the ambiguity of regressing targets amid dense, overlapping trajectories. Experiments on the AstroStripeSet and StarTrails datasets demonstrate that SAANet achieves state-of-the-art (SOTA) performance, achieving Recalls of 0.930 and 0.850, and Average Precisions (APs) of 0.864 and 0.815, respectively. Full article

Understanding how primary structural features and secondary material properties adapt to functional loads is essential to determining their effect on changes in joint biomechanics over time. The objective of this study was to map and correlate spatiotemporal changes in primary structural features, secondary material properties, and dentoalveolar joint (DAJ) stiffness with age in rats subjected to prolonged chewing of soft foods versus hard foods. To probe how loading history shapes the balance between the primary and secondary features, four-week-old rats were fed either a hard-food (HF, N = 25) or soft-food (SF, N = 25) diet for 4, 12, 16, and 20 weeks, and functional imaging of intact mandibular DAJs was performed at 8, 12, 16, 20, and 24 weeks. Across this time course, the primary structural determinants of joint function (periodontal ligament (PDL) space, contact area, and alveolar bone socket morphology) and secondary material and microstructural determinants (tissue-level stiffness encoded by bone and cementum volume fractions, pore architecture, and bone microarchitecture) were quantified. As the joints matured, bone and cementum volume fractions increased in both the HF and SF groups but along significantly different trajectories, and these changes correlated with a pronounced decrease in PDL-space from 12 to 16 weeks in both diets. With further aging, older HF rats maintained significantly wider PDL-spaces than SF rats. These evolving physical features were accompanied by an age-dependent significant increase in the contact ratio in the SF group. The DAJ stiffness was significantly greater in SF than HF animals at younger ages, indicating that food hardness-dependent remodeling alters the relative contribution of structural versus material factors to joint function across the life course. At the tissue level, volumetric strains, representing overall volume changes, and von Mises bone strains, representing shape changes, increased with age in HF and SF joints, with volumetric strain rising rapidly from 16 to 20 weeks and von Mises strain increasing sharply from 12 to 16 weeks. Bone in SF animals exhibited higher and more variable strain values than age-matched HF bone, and changes in joint space, degrees of freedom, contact area, and bone strain correlated with joint biomechanics, demonstrating that multiscale functional biomechanics, including bone strain in intact DAJs, are colocalized with anatomy-specific physical effectors. Together, these spatiotemporal shifts in primary (structure/form), and secondary features (material properties and microarchitecture) define divergent mechanobiological pathways for the DAJ and suggest that altered loading histories can bias joints toward early maladaptation and potential degeneration. Full article

This study develops a field-based techno-economic model and decision framework for a CO₂-enhanced oil recovery and storage project under joint market uncertainty. Historical drilling and completion expenditures calibrate investment cost functions, and three years of production data are fitted with segmented hyperbolic Arps curves to forecast 20-year oil output. Markov-chain models jointly generate internally consistent pathways for crude oil, ETA, and purchased CO₂ prices, which are embedded in a Monte Carlo valuation. The framework outputs probability distributions of NPV and deferral option value; under the mid scenario, their mean values are USD 18.1M and USD 2.0M, respectively. PRCC-based global sensitivity analysis identifies the dominant value drivers as oil price, CO₂ price, utilization factor, oil density, pipeline length, and injection volume. Techno-economic boundary maps in the joint oil and CO₂ price space then delineate feasible regions and break-even thresholds for key design parameters. Results indicate that CCUS-EOR viability cannot be inferred from oil price or any single cost factor alone, but requires coordinated consideration of subsurface constraints, engineering configuration, and multi-market dynamics, including the value of waiting in unfavorable regimes, contributing to low-carbon development and sustainable energy transition objectives. Full article