Search Results (38,336)

Unmanned aerial vehicles (UAVs) often face significant challenges in trajectory tracking within complex dynamic environments, where uncertainties, external disturbances, and nonlinear dynamics hinder accurate and stable control. To address this issue, a bio-inspired deep reinforcement learning (DRL) algorithm is proposed, integrating behavior cloning (BC) and long short-term memory (LSTM) networks. This method can achieve autonomous learning of high-precision control policy without establishing an accurate system dynamics model. Motivated by the memory and prediction functions of biological neural systems, an LSTM module is embedded into the policy network of the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. This structure captures temporal state patterns more effectively, enhancing adaptability to trajectory variations and resilience to delays or disturbances. Compared to memoryless networks, the LSTM-based design better replicates biological time-series processing, improving tracking stability and accuracy. In addition, behavior cloning is employed to pre-train the DRL policy using expert demonstrations, mimicking the way animals learn from observation. This biomimetic plausible initialization accelerates convergence by reducing inefficient early-stage exploration. By combining offline imitation with online learning, the TD3-LSTM-BC framework balances expert guidance and adaptive optimization, analogous to innate and experience-based learning in nature. Simulation experimental results confirm the superior robustness and tracking accuracy of the proposed method, demonstrating its potential as a control solution for autonomous UAVs. Full article

The development of adaptive and comfortable sports bras is essential for adolescents, who experience rapid changes in body morphology during growth. Traditional bras, often made with molded polyurethane bra pads, frequently fail to accommodate these variations, leading to discomfort and poor fit. This study investigates the design of a flexible-fit bra utilizing advanced knitting technology and bio-based materials, including organic cotton and renewable acetate, to enhance comfort and adaptability. The bra, crafted from bio-based yarns, offers stretchability, breathability, and fit, allowing it to adapt to various breast shapes and sizes. Such a bra design is particularly suitable for adolescents undergoing rapid growth. This study includes assessments of material properties and user feedback to evaluate the effectiveness of the design and identify areas for improvement. Positive results were reported from both material tests and subjective evaluations, confirming the effectiveness of the design. The seamless knitting minimizes irritation, while the inlay spacer fabric absorbs impact, and the pointelle structure improves moisture management. Adjustable components enhance adaptability and ensure a flexible fit. This study highlights the potential of knitted biomaterials for creating adaptive intimate apparel, offering a scalable solution for size-inclusive fashion. Full article

Pavement damage classification is crucial for road maintenance and driving safety. However, restricted to the varying scales, irregular shapes, small area ratios, and frequent overlap with background noise, traditional methods struggle to achieve accurate recognition. To address these challenges, a novel pavement damage classification model is designed based on the MambaOut named Multi-scale Damage Enhancement MambaOut (MDEM). The model incorporates two key modules to improve damage classification performance. The Multi-scale Dynamic Feature Fusion Block (MDFF) adaptively integrates multi-scale information to enhance feature extraction, effectively distinguishing visually similar cracks at different scales. The Damage Detail Enhancement Block (DDE) emphasizes fine structural details while suppressing background interference, thereby improving the representation of small-scale damage regions. Experiments were conducted on multiple datasets, including CQU-BPMDD, CQU-BPDD, and Crack500-PDD. On the CQU-BPMDD dataset, MDEM outperformed the baseline model with improvements of 2.01% in accuracy, 2.64% in precision, 2.7% in F1-score, and 4.2% in AUC. The extensive experimental results demonstrate that MDEM significantly surpasses MambaOut and other comparable methods in pavement damage classification tasks. It effectively addresses challenges such as varying scales, irregular shapes, small damage areas, and background noise, enhancing inspection accuracy in real-world road maintenance. Full article

To elucidate the mechanism by which soil disturbance affects tillage performance during subsoiling remediation of northeastern primary sodic saline–alkali soil, this study established a mathematical prediction model linking subsoiler configuration parameters with draft force and soil porosity based on the soil dynamic equation and the fourth strength theory. Discrete element simulation and field experiments demonstrated the model’s accuracy in predicting draft force and soil looseness (error < 5%). Among three configuration patterns evaluated, the “W”-type arrangement was selected for further simulation testing and predictive analysis through parameter adjustment. The simulation results aligned with the prediction results. Particle flow analysis revealed a quadratic relationship between subsoiler spacing variation, draft force, and soil looseness. At the particle scale, soil particle movement patterns were found to govern macroscopic effects, where soil clogging and repeated disturbances emerged as primary drivers of nonlinear variations in draft force and soil porosity. Finally, field experiments and simulations were performed using the parameter combinations predicted by the mathematical model, confirming the accuracy of these parameters. Through a tripartite validation approach combining mathematical modeling, DEM simulation, and field trials, this study systematically elucidates the complete mechanism whereby subsoiler arrangement parameters influence the tillage performance of sodic saline–alkali soil via soil–tool interactions, providing theoretical foundations for optimizing subsoiling equipment design and reducing energy consumption in saline–alkali land cultivation. Full article

A Universal Numerical Integrator (UNI) is a computational framework that combines a classical numerical integration method, such as Euler, Runge–Kutta, or Adams–Bashforth, with a universal approximator of functions, such as a feed-forward neural network (including MLP, SVM, RBF, among others) or a fuzzy inference system. The Euler-Type Universal Numerical Integrator (E–TUNI) is a particular case of UNI based on the first-order Euler integrator and is designed to model non-linear dynamic systems observed in real-world scenarios accurately. The UNI framework can be organized into three primary methodologies: the NARMAX model (Non-linear AutoRegressive Moving Average with eXogenous input), the mean derivatives approach (which characterizes E–TUNI), and the instantaneous derivatives approach. The E–TUNI methodology relies exclusively on mean derivative functions, distinguishing it from techniques that employ instantaneous derivatives. Although it is based on a first-order scheme, the E–TUNI achieves an accuracy level comparable to that of higher-order integrators. This performance is made possible by the incorporation of a neural network acting as a universal approximator, which significantly reduces the approximation error. This article provides a comprehensive overview of the E–TUNI methodology, focusing on its application to the modeling of non-linear autonomous dynamic systems and its use in predictive control. Several computational experiments are presented to illustrate and validate the effectiveness of the proposed method. Full article

Chronic respiratory diseases claim nearly four million lives annually, making them the third leading cause of death worldwide. Extracorporeal membrane oxygenation (ECMO) is often the last line of support for patients with severe lung failure. Still, its performance is limited by an incomplete understanding of gas exchange in hollow fiber membrane (HFM) oxygenators. Computational fluid dynamics (CFD) has become a robust oxygenator design and optimization tool. However, most models oversimplify O₂ and CO₂ transport by ignoring their physiological coupling, instead relying on fixed saturation curves or constant-content assumptions. For the first time, this study introduces a novel physiologically informed CFD model that integrates the Bohr and Haldane effects to capture the coupled transport of oxygen and carbon dioxide as functions of local pH, temperature, and gas partial pressures. The model is validated against in vitro experimental data from the literature and assessed against established CFD models. The proposed CFD model achieved excellent agreement with experiments across blood flow rates (100–500 $\mathrm{mL}/\min$ ), with relative errors below 5% for oxygen and 10–15% for carbon dioxide transfer. These results surpassed the accuracy of all existing CFD approaches, demonstrating that a carefully formulated single-phase model combined with physiologically informed diffusivities can outperform more complex multiphase simulations. This work provides a computationally efficient and physiologically realistic framework for oxygenator optimization, potentially accelerating device development, reducing reliance on costly in vitro testing, and enabling patient-specific simulations. Full article

Background/Objectives: Effective clinical handover is a critical component of nursing care, particularly in mental health settings, where the transfer of clinical and behavioral information is essential for both patients’ and health personnel’s safety. Gamification has emerged as a promising strategy to enhance clinical education, yet few interventions have focused specifically on mental health care contexts. This study aimed to evaluate the effectiveness of a serious game designed to teach the SBAR (Situation, Background, Assessment, Recommendation) handover framework to undergraduate nursing students through a psychiatric care unit scenario. Methods: A quasi-experimental pre–post design was employed with a convenience sample of 48 nursing students from a Northern Italian university. Participants completed a test assessing their ability to organize clinical information according to the SBAR model before and after the game intervention. Students’ experience was assessed using the Player Experience Inventory. Results: A statistically significant improvement in SBAR application was observed post-intervention. The majority of students reported a positive experience across PXI domains such as Meaning, Challenge, Progress Feedback, and Enjoyment. Comparisons with a previously validated video-based nursing serious game showed a consistent overall pattern in response trends. Conclusions: The SG was an effective and engaging educational tool for improving structured handover skills in nursing students. Gamification may represent a valuable complement to traditional instruction in nursing education, especially in high-communication clinical areas such as mental health. Further research is needed to assess long-term retention and to explore more immersive formats. Full article

Hyperspectral image (HSI) denoising is challenged by complex spatial-spectral noise coupling. Existing deep learning methods, primarily designed for RGB images, fail to address HSI-specific noise distributions and spectral correlations. This paper proposes a Hybrid-Domain Synergistic Transformer (HDST) integrating frequency-domain enhancement and multiscale modeling. Key contributions include (1) a Fourier-based preprocessing module decoupling spectral noise; (2) a dynamic cross-domain attention mechanism adaptively fusing spatial-frequency features; and (3) a hierarchical architecture combining global noise modeling and detail recovery. Experiments on realistic and synthetic datasets show HDST outperforms state-of-the-art methods in PSNR, with fewer parameters. Visual results confirm effective noise suppression without spectral distortion. The framework provides a robust solution for HSI denoising, demonstrating potential for high-dimensional visual data processing. Full article

Large-scene space-borne SAR images with a high resolution are particularly effective for monitoring vast oceanic areas globally. However, ships are easily overlooked in such large scenes due to their small size and cluttered backgrounds, making SAR ship detection challenging for the existing methods. To address this challenge, we propose a progressive saliency-guided (PSG) method, which uses saliency-derived positional priors to guide the model in focusing on small targets and extracting their features. Specifically, a dual-guided perception enhancement (DGPE) module is developed, which introduces additional target saliency maps as prior information to cross-guide and highlight key regions in SAR images at the feature level, enhancing small object feature representation. Additionally, a saliency confidence aware assessment (SCAA) mechanism is designed to strengthen small object proposal learning at the proposal level, guided by classification and localization scores at key locations. The DGPE and SCAA modules jointly enhance small object learning across different network levels. Extensive experiments demonstrate that the PSG method significantly improves the detection performance (+4.38% AP on LS-SSDD and +4.35% on HRSID) for small ships in large-scene SAR images compared to that of the baseline, providing an effective solution for small ship detection in large scenes. Full article

In extended-reach wells, cuttings bed formation in high-deviation sections presents a major challenge for hole cleaning and borehole stability. This study analyzes the morphological and mechanical behavior of cuttings beds, focusing on particle size distribution and repose angle as key indicators of accumulation behavior. The modeling approach considers dominant interparticle forces, including buoyancy and cohesion, while neglecting secondary microscale forces for clarity. A theoretical model is developed to predict repose angles under both rolling and sliding regimes and is calibrated through laboratory-scale experiments using simulated drilling fluid with field-representative rheological properties. Results show that cohesive effects are negligible when cuttings are of similar size but exhibit higher densities. Laboratory measurements reveal that the repose angle of cuttings beds varies between 23.9° and 31.7°, with increasing polyacrylamide (PAM) concentration and particle size contributing to steeper repose angles. Additionally, the rolling repose angle is found to be relatively stable, ranging from 25° to 30°, regardless of fluid or particle property variations. These findings provide a predictive framework and practical guidelines for optimizing hole cleaning strategies and designing more effective models in extended-reach drilling. Full article

To address the severe challenges of task allocation for UAV swarms in uncertain complex environments, this paper introduces the concept of equivalent load, constructs the load capability matrix of a single UAV and the task required load matrix of the task area, and designs a new task resilience capability indicator accordingly to conduct research on a resilience-based optimization framework. Aiming at this multi-objective optimization problem, the “Problem Decomposability Theorem” is proposed, which theoretically proves the feasibility of decomposing the UAV swarm problem into “lower-level Integer Linear Programming (ILP) cost optimization” and “upper-level Particle Swarm Optimization (PSO) resilience optimization”. Based on this, a Particle Swarm Optimization–Integer Linear Programming (PSO-ILP) two-layer nested optimization algorithm is designed. Simulation experiments covering three task areas, five payload types and multiple UAV types are carried out, and the results show that the proposed method has outstanding performance in multi-objective optimization, especially in terms of algorithm convergence and the comprehensive efficiency of swarm load cost and task resilience. In particular, when the interruption probability is in the range of 0.2 to 0.6, it can not only maintain high task resilience but also achieve cost minimization, with a significant improvement in resilience performance. These results not only enrich the theoretical research on UAV swarm resilience but also provide a universal solution for UAV swarm task optimization in multiple fields. Full article

The linear rolling guide (LRG) is widely used in the computer numerical control machine tool industry and other industries. To accurately evaluate the performance of LRGs, a multi-parameter test bench was developed to measure motion accuracy, preload drag force (PDF), vibration, temperature rise, and fatigue life. The mechanical structure and measurement and control system of the test bench were designed based on established principles and methods. ANSYS 19.0 software was used for static analysis of the gantry, modal analysis of the upper bed, and simulation of the impact of loading block thickness on load distribution uniformity. At the same time, we used an impact hammer modal test to verify the correctness of the finite element analysis of the upper bed. The analysis results validated the structural design. To verify the test bench’s repeatability, comparative experiments were conducted with the Hilectro LGD35-type LRGs, focusing on motion accuracy, PDF, and fatigue life. The experimental results confirmed the test bench’s high repeatability and validated the derived equations for measuring motion accuracy. Full article

This study investigates the complex interaction between in-game behaviors, post-game emotional expressions, and Game Transfer Phenomena (GTP) among MOBA players. A multidimensional framework is adopted to examine how gaming experiences shape real-world cognition, perception, and behavior through the integration of objective behavioral metrics and affective computing-based emotion recognition. The results indicate that in-game Deaths are negatively associated with altered sensory perceptions—specifically Altered Visual and Auditory Perceptions (AVP and AAP)—suggesting that performance failures may disrupt immersive engagement. In contrast, Assists, as indicators of team-based collaboration, are positively associated with Automatic Mental Processes (AMP), highlighting the cognitive impact of cooperative gameplay. Although no significant mediating effects were observed, emotional dimensions, such as Social Discomfort and Cognitive Focus, offered additional insights into the transfer between in-game and post-game experiences. These findings bridge the gap between virtual and real-world experiences, offering theoretical advancements in GTP research and practical implications for game design, emotional regulation, and psychological interventions. Full article

Most existing ultra-deep gas wells are characterized by high temperature, high pressure, and high sulfur content. During development, they face serious challenges such as unclear mechanisms of acid gas-induced blowouts and difficulties in wellbore pressure inversion, posing significant challenges to well control operations. To reveal the reasons behind the tendency of acidic gases to trigger blowouts and to clarify the impact of different concentrations of acidic gases on the flow behavior of annular fluids, this study considers the effects of solubility and phase changes on the physical properties of acidic gases. A method replacing critical parameters with pseudo-critical parameters is used to analyze the variation trends of gas density, solubility, and other properties along the well depth. A mathematical model for the annular flow of acidic gas overflow incorporating solubility phase change effects is established. The model is numerically solved using a four-point difference scheme, exploring the essential characteristics of gas flow in the annulus after overflow, and discussing the distribution patterns of physical properties of acidic gases, as well as dynamic parameters such as wellbore pressure and temperature along the well depth. Numerical simulations show that the physical properties of acidic gases change significantly with well depth: the more acidic gas present in the wellbore, the smaller the deviation factor, and the greater the density and viscosity, with parameter changes exceeding 40% near the pseudo-critical point for binary mixtures with 40% H₂S. Compared to pure methane, mixed fluids containing acidic gas experience more than 20% volume expansion near the wellhead for ternary mixtures with 20% CO₂ and 20% H₂S, and the flow velocity increases by more than 10% for mixtures with ≥30% acidic gas content, leading to a higher risk of a sudden pressure drop during well control. This study clarifies the migration patterns of acidic gas overflow in HPHT (high pressure, high temperature) gas wells, providing valuable guidance for optimizing well control design, improving well control emergency plans, and developing well-killing measures. Full article

The construction sector is a major contributor to environmental degradation due to high energy consumption and CO₂ emissions. This study presents a low-tech, sustainable construction system based on the manual fabrication of curved laminated bamboo beams, assembled with screws and steel straps, without adhesives or heavy machinery. The case study is part of a bamboo roof structure built within Jericoacoara National Park, Brazil, using Dendrocalamus asper for its mechanical strength and carbon storage capacity. The construction process of three vertical lower laminated curved beams (Vig.CLIV-1, CLIV-2, and CLIV-3) was systematized into two main phases—preparation and construction. Due to the level of detail involved, only Vig.CLIV-1 is fully presented, broken down into work items, processes, and sub-processes to identify critical points for quality control and time efficiency. Comparative analysis of the three beams complements the findings, highlighting differences in logistics, labor performance, and learning outcomes. The results demonstrate the potential of this handcrafted system to achieve high geometric accuracy in complex site conditions, with low embodied energy and strong replicability. Developed by bamboo specialists from Colombia and Peru with support from local assistants, this experience illustrates the viability of low-impact, appropriate construction solutions for ecologically sensitive contexts and advances the integration of sustainable, replicable practices in architectural design. Full article