Search Results (2,312)

Real-time lossless image compression based on the JPEG-LS algorithm is in high demand for critical missions such as satellite remote sensing and space exploration due to its excellent balance between complexity and compression rate. However, few researchers have made appropriate modifications to the JPEG-LS algorithm to make it more suitable for high-speed hardware implementation and application to Bayer pattern data. This paper addresses the current limitations by proposing a real-time lossless compression system specifically tailored for Bayer pattern images from spaceborne cameras. The system integrates a hybrid encoding strategy modified from JPEG-LS, combining run-length encoding, predictive encoding, and a non-encoding mode to facilitate high-speed hardware implementation. Images are processed in tiles, with each tile’s color channels processed independently to preserve individual channel characteristics. Moreover, potential error propagation is confined within a single tile. To enhance throughput, the compression algorithm operates within a 20-stage pipeline architecture. Duplication of computation units and the introduction of key-value registers and a bypass mechanism resolve structural and data dependency hazards within the pipeline. A reorder architecture prevents pipeline blocking, further optimizing system throughput. The proposed architecture is implemented on a XILINX XC7Z045-2FFG900C SoC (Xilinx, Inc., San Jose, CA, USA) and achieves a maximum throughput of up to 346.41 MPixel/s, making it the fastest architecture reported in the literature. Full article

Optimal airfoil design remains a critical challenge in aerodynamic engineering, with traditional methods requiring extensive computational resources and iterative processes. This paper presents GEO-DSGA, a novel framework integrating hybrid geometric neural networks with deep symbiotic genetic algorithms for enhanced airfoil optimization. The methodology employs graph-based representations of airfoil geometries through a hybrid architecture combining graph convolutional networks with traditional deep learning, enabling precise capture of spatial geometric relationships. The parametric modeling stage utilizes CST, Bézier curves, and PARSEC methods to generate mathematically robust airfoil representations, subsequently transformed into graph structures preserving local and global shape characteristics. The optimization framework incorporates a deep symbiotic genetic algorithm enhanced with dominant feature phenotyping, applying biological symbiotic principles where design parameters achieve superior performance through mutual enhancement rather than independent optimization. This systematic exploration maintains geometric feasibility and aerodynamic validity throughout the design space. Experimental results demonstrate an 88.6% reduction in computational time while maintaining prediction accuracy within 1.5% error margin for aerodynamic coefficients across diverse operating conditions. The methodology successfully identifies airfoil geometries outperforming baseline NACA profiles by up to 12% in lift-to-drag ratio while satisfying manufacturing and structural constraints, establishing GEO-DSGA as a significant advancement in computational aerodynamic design optimization. Full article

This paper introduces a hybrid learning framework that synergistically combines Reinforcement Learning (RL) and Supervised Learning (SL) to train autonomous cyber-defense agents capable of operating effectively in dynamic and adversarial environments. The proposed approach leverages RL for strategic exploration and policy development, while incorporating SL to distill high-reward trajectories into refined policy updates, enhancing sample efficiency, learning stability, and robustness. The framework first targets specialized agent training, where each agent is optimized against a specific adversarial behavior. Subsequently, it is extended to enable the training of a generalized agent that learns to counter multiple, diverse attack strategies through multi-task and curriculum learning techniques. Comprehensive experiments conducted in the CybORG simulation environment demonstrate that the hybrid RL–SL framework consistently outperforms pure RL baselines across both specialized and generalized settings, achieving higher cumulative rewards. Specifically, hybrid-trained agents achieve up to 23% higher cumulative rewards in specialized defense tasks and approximately 18% improvements in generalized defense scenarios compared to RL-only agents. Moreover, incorporating temporal context into the observation space yields a further 4–6% performance gain in policy robustness. Furthermore, we investigate the impact of augmenting the observation space with historical actions and rewards, revealing consistent, albeit incremental, gains in SL-based learning performance. Key contributions of this work include: $\left(i\right)$ a novel hybrid learning paradigm that integrates RL and SL for effective cyber-defense policy learning, $\left(ii\right)$ a scalable extension for training generalized agents across heterogeneous threat models, and $\left(iii\right)$ empirical analysis on the role of temporal context in agent observability and decision-making. Collectively, the results highlight the promise of hybrid learning strategies for building intelligent, resilient, and adaptable cyber-defense systems in evolving threat landscapes. Full article

Specific emitter identification (SEI), which classifies radio transmitters by extracting hardware-intrinsic radio frequency fingerprints (RFFs), faces critical challenges in noise robustness, generalization under limited training data and class imbalance. To address these limitations, we propose adaptive deep ensemble learning (ADEL)—a framework that integrates heterogeneous neural networks including convolutional neural networks (CNN), multilayer perception (MLP) and transformer for hierarchical feature extraction. Crucially, ADEL also adopts adaptive weighted predictions of the three base classifiers based on reconstruction errors and hybrid losses for robust classification. The methodology employs (1) three heterogeneous neural networks for robust feature extraction; (2) the hybrid losses refine feature space structure and preserve feature integrity for better feature generalization; and (3) collaborative decision-making via adaptive weighted reconstruction errors of the base learners for precise inference. Extensive experiments are performed to validate the effectiveness of ADEL. The results indicate that the proposed method significantly outperforms other competing methods. ADEL establishes a new SEI paradigm through robust feature extraction and adaptive decision integrity, enabling potential deployment in space target identification and situational awareness under limited training samples and imbalanced classes conditions. Full article

The growing penetration of renewable energy sources requires resilient microgrids capable of providing stable and continuous operation. Hybrid energy storage systems (HESS), which integrate hydrogen-based storage systems (HBSS), battery storage systems (BSS), and supercapacitor banks (SCB), are essential to ensuring the flexibility and robustness of these microgrids. Accurate modelling of these microgrids is crucial for analysis, controller design, and performance optimization, but the complexity of HESS poses a significant challenge: simplified linear models fail to capture the inherent nonlinear dynamics, while nonlinear approaches often require excessive computational effort for real-time control applications. To address this challenge, this study presents a novel state space model with linear variable parameters (LPV), which effectively balances accuracy in capturing the nonlinear dynamics of the microgrid and computational efficiency. The research focuses on a high-voltage DC bus microgrid architecture, in which the BSS and SCB are connected directly in parallel to provide passive DC bus stabilization, a configuration that improves system resilience but has received limited attention in the existing literature. The proposed LPV framework employs recursive linearisation around variable operating points, generating a time-varying linear representation that accurately captures the nonlinear behaviour of the system. By relying exclusively on directly measurable state variables, the model eliminates the need for observers, facilitating its practical implementation. The developed model has been compared with a reference model validated in the literature, and the results have been excellent, with average errors, MAE, RAE and RMSE values remaining below 1.2% for all critical variables, including state-of-charge, DC bus voltage, and hydrogen level. At the same time, the model maintains remarkable computational efficiency, completing a 24-h simulation in just 1.49 s, more than twice as fast as its benchmark counterpart. This optimal combination of precision and efficiency makes the developed LPV model particularly suitable for advanced model-based control strategies, including real-time energy management systems (EMS) that use model predictive control (MPC). The developed model represents a significant advance in microgrid modelling, as it provides a general control-oriented approach that enables the design and operation of more resilient, efficient, and scalable renewable energy microgrids. Full article

Occupational segregation between men and women and between rural and urban areas is a persistent driver of labor market inequality in Europe. Women and rural workers are often overrepresented in lower-paid and lower-status occupations, reflecting structural barriers to occupational mobility. This paper investigates how occupational segregation varies across gender, space, and telework status and examines the potential of telework to reduce these inequalities. Using microdata from the 2023 European Labor Force Survey, we calculate segregation indices to measure occupational segregation and monetary gains, as well as losses due to segregation. We further analyze the relationship of segregation and telework. We find the highest segregation and economic disadvantages due to segregation for rural men. Female teleworkers are less clustered in feminized roles compared to non-teleworking women, suggesting that remote work can broaden occupational opportunities. Telework shows reduced segregation when primarily working remotely, but not in hybrid settings. Our findings contribute to a better understanding of spatial and gendered labor market disparities. We further identify the potential of telework to promote a more equitable occupational integration across gender and space. Full article

Accurate modeling of non-cooperative space targets remains a significant challenge, particularly under complex illumination conditions. A hybrid virtual–real framework is proposed that integrates photometric compensation, 3D reconstruction, and visibility determination to enhance the robustness and accuracy of monocular-based modeling systems. To overcome the breakdown of the classical photometric constancy assumption under varying illumination, a compensation-based photometric model is formulated and implemented. A point cloud–driven virtual space is constructed and refined through Poisson surface reconstruction, enabling per-pixel depth, normal, and visibility information to be efficiently extracted via GPU-accelerated rendering. An illumination-aware visibility model further distinguishes self-occluded and shadowed regions, allowing for selective pixel usage during photometric optimization, while motion parameter estimation is stabilized by analyzing angular velocity precession. Experiments conducted on both Unity3D-based simulations and a semi-physical platform with robotic hardware and a sunlight simulator demonstrate that the proposed method consistently outperforms conventional feature-based and direct SLAM approaches in trajectory accuracy and 3D reconstruction quality. These results highlight the effectiveness and practical significance of incorporating virtual space feedback for non-cooperative space target modeling. Full article

Selecting an appropriate Multi-Criteria Decision-Making (MCDM) algorithm for optimizing marine diesel engine operation presents a complex challenge due to the diversity in mathematical formulations, normalization schemes, and trade-off resolutions across methods. This study systematically evaluates fourteen MCDM algorithms, which are grouped into five primary methodological categories: Scoring-Based, Distance-Based, Pairwise Comparison, Outranking, and Hybrid/Intelligent System-Based methods. The goal is to identify the most suitable algorithm for real-time performance optimization of two stroke marine diesel engines. Using Diesel-RK software, calibrated for marine diesel applications, simulations were performed on a variant of the MAN-B&W-S60-MC-C8-8 engine. A refined five-dimensional parameter space was constructed by systematically varying five key control variables: Start of Injection (SOI), Dwell Time, Fuel Mass Fraction, Fuel Rail Pressure, and Exhaust Valve Timing. A subset of 4454 high-potential alternatives was systematically evaluated according to three equally important criteria: Specific Fuel Consumption (SFC), Nitrogen Oxides (NO_x), and Particulate Matter (PM). The MCDM algorithms were evaluated based on ranking consistency and stability. Among them, Proximity Indexed Value (PIV), Integrated Simple Weighted Sum Product (WISP), and TriMetric Fusion (TMF) emerged as the most stable and consistently aligned with the overall consensus. These methods reliably identified optimal engine control strategies with minimal sensitivity to normalization, making them the most suitable candidates for integration into automated marine engine decision-support systems. The results underscore the importance of algorithm selection and provide a rigorous basis for establishing MCDM in emission-constrained maritime environments. This study is the first comprehensive, simulation-based evaluation of fourteen MCDM algorithms applied specifically to the optimization of two stroke marine diesel engines using Diesel-RK software. Full article

To address the issue of jitter and oscillation of guidance command during multi-vehicle cooperative engagement with maneuvering platforms, this paper proposes a novel terminal guidance law with prescribed performance constraints for multiple cooperative vehicles, which explicitly considers both transient and steady-state performance. Firstly, based on the vehicle-target relative kinematics, with time and space as the main constraint indicators, a multi-vehicle cooperative guidance model is established in the inertial coordinate system. Secondly, combined with the sliding mode control theory, cooperative guidance laws are designed for both the line-of-sight (LOS) direction and the LOS normal direction, respectively, and the Lyapunov stability proof is given. Furthermore, to counteract the impact of target maneuvers on guidance performance, a non-homogeneous disturbance observer is designed to estimate target maneuver information that is difficult to obtain directly, which ensures that performance constraints are still satisfied under strong target maneuvering conditions. Simulation results demonstrate that the proposed guidance law enables multiple coordinated vehicles to successfully engage the target under different maneuvering modes, while satisfying the terminal time-space constraints. Compared with conventional sliding mode control methods exhibiting inherent chattering, the proposed approach employs a novel PPC-SMC hybrid structure to quantitatively constrain the transient convergence of cooperative errors. This structure enhances the multi-vehicle cooperative guidance performance by effectively eliminating chattering and oscillations in the guidance commands, thereby significantly improving the system’s transient behavior. Full article

To address the ill-posedness of the Hessian matrix in monocular visual-inertial SLAM (Simultaneous Localization and Mapping) caused by unobservable depth of feature points, which leads to convergence difficulties and reduced robustness, this paper proposes a Pre-Dog-Leg feature optimization method based on an adaptive preconditioner. First, we propose a multi-candidate initialization method with robust characteristics. This method effectively circumvents erroneous depth initialization by introducing multiple depth assumptions and geometric consistency constraints. Second, we address the pathology of the Hessian matrix of the feature points by constructing a hybrid SPAI-Jacobi adaptive preconditioner. This preconditioner is capable of identifying matrix pathology and dynamically enabling preconditioning as a strategy. Finally, we construct a hybrid adaptive preconditioner for the traditional Dog-Leg numerical optimization method. To address the issue of degraded convergence performance when solving pathological problems, we map the pathological optimization problem from the original parameter space to a well-conditioned preconditioned space. The optimization equivalence is maintained by variable recovery. The experiments on the EuRoC dataset show that the method reduces the number of Hessian matrix conditionals by a factor of 7.9, effectively suppresses outliers, and significantly improves the overall convergence time. From the analysis of trajectory error, the absolute trajectory error is reduced by up to 16.48% relative to RVIO2 on the MH_01 sequence, 20.83% relative to VINS-mono on the MH_02 sequence, and up to 14.73% relative to VINS-mono and 34.0% relative to OpenVINS on the highly dynamic MH_05 sequence, indicating that the algorithm achieves higher localization accuracy and stronger system robustness. Full article

We synthesized the current evidence from the literature and conducted a 2 × 3 factorial experiment to quantify the impact of thermocycling on the Vickers microhardness (HV) of dental CAD/CAM materials: VITA ENAMIC (VE, polymer-infiltrated ceramic network) and CERASMART (CS, nanofilled resin-matrix). Sixty polished specimens (n = 10 per Material × Cycles cell; 12 × 2 × 2 mm) were thermocycled at 5–55 °C (0, 10,000, 20,000 cycles; 30 s dwell, ≈10 s transfer) and tested as HV0.3/10 (300 gf, 10 s; five indentations/specimen with standard spacing). Assumptions regarding the model residuals were met (Shapiro–Wilk W ≈ 0.98, p ≈ 0.36; Levene F(5,54) ≈ 1.12, p ≈ 0.36), so a two-way ANOVA (Type II) with Tukey’s HSD post hoc (α = 0.05) was applied. VE maintained consistently higher HV than CS at all cycle levels and showed a smaller drop from baseline: VE (mean ± SD): 200.2 ± 10.8 (0), 192.4 ± 13.9 (10,000), and 196.7 ± 9.3 (20,000); CS: 60.8 ± 6.1 (0), 53.4 ± 4.7 (10,000), and 62.1 ± 3.8 (20,000). ANOVA revealed significant main effects from the material (η²p = 0.972) and cycles (η²p = 0.316), plus a Material × Cycles interaction (η²p = 0.201). Results: Thermocycling produced material-dependent changes in microhardness. Relative to baseline, VE varied by −3.9% (10,000) and −1.7% (20,000), while CS varied by −12.2% (10,000) and +2.1% (20,000); from 10,000→20,000 cycles, microhardness recovered by +2.2% (VE) and +16.3% (CS). Pairwise comparisons were consistent with these trends (CS decreased at 10,000 vs. 0 and recovered at 20,000; VE only showed a modest change). Conclusions: Thermocycling effects were material-dependent, with smaller losses and better retention in VE (PICN) than in CS. These results align with the literature (resin-matrix/hybrids are more sensitive to thermal aging; polished finishes mitigate losses). While HV is only one facet of performance, the superior retention observed in PICN under thermal challenge suggests the improved preservation of superficial integrity; standardized reporting of aging parameters and integration with wear, fatigue, and adhesion outcomes are recommended to inform indications and longevity. Full article

Deploying Large Language Models (LLMs) in edge environments faces two major challenges: (i) the conflict between limited device resources and high computational demands, and (ii) the dynamic impact of user mobility on model partitioning and task offloading decisions. To address these challenges, this paper proposes the Dynamic Adaptive Partitioning and Offloading (DAPO) framework, an intelligent solution for multi-user, multi-edge Mobile Edge Intelligence (MEI) systems. DAPO employs a Deep Deterministic Policy Gradient (DDPG) algorithm to jointly optimize the model partition point and the task offloading destination. By mapping continuous policy outputs onto valid discrete actions, DAPO efficiently addresses the high-dimensional hybrid action space and dynamically adapts to user mobility. Through extensive simulations, we demonstrate that DAPO outperforms baseline strategies and mainstream RL methods, achieving up to 27% lower latency and 18% lower energy consumption compared to PPO and A2C, while maintaining fast convergence and scalability in dynamic mobile environments. Full article

With the large-scale integration of renewable energy into distribution networks, the intermittency and uncertainty of renewable generation pose significant challenges to the voltage security of the power grid under extreme scenarios. To address this issue, this paper proposes an optimal scheduling method for power grids under extreme scenarios, based on an improved Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. By simulating potential extreme scenarios in the power system and formulating targeted secure scheduling strategies, the proposed method effectively reduces trial-and-error costs. First, the time series clustering method is used to construct the extreme scene dataset based on the principle of maximizing scene differences. Then, a mathematical model of power grid optimal dispatching is constructed with the objective of ensuring voltage security, with explicit constraints and environmental settings. Then, an interactive scheduling model of distribution network resources is designed based on a multi-agent algorithm, including the construction of an agent state space, an action space, and a reward function. Then, an improved MADDPG multi-agent algorithm based on specific information fusion is proposed, and a hybrid optimization experience sampling strategy is developed to enhance the training efficiency and stability of the model. Finally, the effectiveness of the proposed method is verified by the case studies of the distribution network system. Full article

In-cylinder pressure provides critical insights for analyzing and optimizing combustion in internal combustion engines, yet its acquisition across the full operating space requires extensive testing, while physics-based models are computationally demanding. Machine learning (ML) offers an alternative, but its application to direct reconstruction of full pressure traces remains limited. This study evaluates three strategies for reconstructing cylinder pressure under unmeasured operating conditions, establishing a machine learning-assisted framework that generates the complete pressure–crank angle (P–CA) trace. The framework treats crank angle and operating conditions as inputs and predicts either pressure directly or apparent heat release rate (HRR) as an intermediate variable, which is then integrated to reconstruct pressure. In all approaches, discrete pointwise predictions are combined to form the full P–CA curve. Direct pressure prediction achieves high accuracy for overall traces but underestimates HRR-related combustion features. Training on HRR improves combustion representation but introduces baseline shifts in reconstructed pressure. A hybrid approach, combining non-combustion pressure prediction with combustion-phase HRR-based reconstruction delivers the most robust and physically consistent results. These findings demonstrate that ML can efficiently reconstruct in-cylinder pressure at unmeasured conditions, reducing experimental requirements while supporting combustion diagnostics, calibration, and digital twin applications. Full article

As more machine learning models are used in sensitive fields like healthcare, finance, and smart infrastructure, protecting structured tabular data from privacy attacks is a key research challenge. Although several privacy-preserving methods have been proposed for tabular data, a comprehensive comparison of their performance and trade-offs has yet to be conducted. We introduce and empirically assess a combined defense system that integrates differential privacy, federated learning, adaptive noise injection, hybrid cryptographic encryption, and ensemble-based obfuscation. The given strategies are analyzed on the benchmark tabular datasets (ADULT, GSS, FTE), showing that the suggested methods can mitigate up to 50 percent of model inversion attacks in relation to baseline models without decreasing the model utility (F1 scores are higher than 0.85). Moreover, on these datasets, our results match or exceed the latest state-of-the-art (SOTA) in terms of privacy. We also transform each defense into essential data privacy laws worldwide (GDPR and HIPAA), suggesting the best applicable guidelines for the ethical and regulation-sensitive deployment of privacy-preserving machine learning models in sensitive spaces. Full article