Search Results (29,247)

Cardiac magnetic resonance imaging (CMR) is widely used for the diagnosis and functional assessment of cardiovascular diseases because of its noninvasive nature and excellent soft-tissue contrast. However, accelerated cine magnetic resonance imaging (cine MRI) acquisition usually relies on undersampling, which may lead to noise, aliasing artifacts, and detail loss in reconstructed images. To address this issue, we propose a wavelet-guided dynamic Transformer with diffusion priors for cardiac cine MRI reconstruction. Specifically, a diffusion model is introduced into a reduced latent feature space to generate high-frequency prior features with only 8 reverse sampling steps, thereby enhancing detail recovery while maintaining moderate computational cost. In addition, a wavelet-guided dynamic Transformer is designed to capture low-frequency structural information and temporal dependencies across adjacent frames. By combining wavelet-domain decomposition, diffusion priors, and dynamic spatiotemporal modeling, the proposed framework improves reconstruction quality while preserving temporal consistency. Experimental results on multiple cardiac cine MRI datasets show that the proposed method achieves superior reconstruction accuracy and temporal consistency over several competing approaches, while maintaining a favorable balance between computational efficiency and reconstruction performance. These findings indicate that the proposed framework is an effective and robust solution for accelerated cardiac cine MRI reconstruction. Full article

Wireless Sensor Networks (WSNs) enable energy-efficient data collection in dynamic environments but continue to face the dual challenges of severely constrained node energy and the spatiotemporal heterogeneity of data traffic. Inspired by honeybee foraging behavior, this paper proposes a hybrid optimization framework that integrates mixed-integer linear programming (MILP) and Markov decision processes (MDP), utilizing Q-learning for adaptive decision-making. The proposed framework systematically maps the dual-layer decision-making mechanism of honeybee foraging onto a synergistic architecture combining MILP-based global planning and MDP-based local adaptation, offering a novel bio-inspired solution for mobile sink trajectory planning and adaptive routing. Specifically, the upper-level MILP module simulates a colony-level global assessment of distant nectar sources, generating an initial global trajectory by determining the optimal access sequence of cluster heads to minimize the movement cost of the mobile sink. The lower-level Q-learning module simulates the individual-level local adaptation, where bees adjust harvesting behavior in real-time based on nectar quality and distance. This module continuously optimizes routing parameters based on real-time network states, including residual energy, the ratio of surviving nodes, data queue lengths, and cluster head density. The algorithm employs an ϵ-greedy strategy to balance exploration and exploitation, while a periodic decision-update mechanism is introduced to harmonize computational efficiency with learning stability. Furthermore, a multi-objective reward function is designed to jointly optimize energy efficiency, network lifetime, end-to-end latency, and path length. Extensive simulation results demonstrate that the proposed MILP-MDP hybrid framework significantly outperforms several representative baseline algorithms in terms of network lifetime extension and energy balance. These findings validate that the integration of bio-inspired foraging strategies and reinforcement learning provides an efficient and robust solution for trajectory planning and adaptive routing in dynamic WSNs. Full article

The application of rheological modeling in polyolefin-based systems has gained increasing attention in the context of sustainable materials and circular economy strategies. In particular, the use of recycled polyolefins reinforced with lignocellulosic fillers presents significant opportunities, but also introduces challenges associated with structural heterogeneity, degradation, and variability in processing behavior. Despite rheology’s central role in linking structure, processing, and properties, its use as a predictive tool in recycled systems remains insufficiently systematized. This work presents a systematic review conducted according to PRISMA guidelines to analyze the use of rheological models in polyolefin-based systems, with particular emphasis on their applicability to recycled materials and composite formulations. We analyze 50 studies using a structured data extraction protocol. The results show that rheological modeling approaches can be organized into a hierarchical framework ranging from indirect flow parameters and generalized Newtonian fluid models to viscoelastic, structural, multiscale, and hybrid approaches. However, these approaches are not evenly distributed across system types. Advanced models are predominantly applied to compositionally controlled systems, whereas recycled and post-consumer polyolefins are mainly addressed using simplified models or experimental characterization. The analysis further indicates that rheology is primarily used for data fitting and process simulation, with limited application as a predictive tool for material formulation. Quantitative trends reported in the literature indicate that filler incorporation typically increases viscosity by approximately 20–200%, depending on filler content, dispersion quality, and interfacial interactions. However, variability in experimental conditions and material heterogeneity significantly limits cross-study comparability. From a mechanistic perspective, the main limitation lies not in the availability of rheological models but in their adaptability to heterogeneous systems characterized by variable composition, degradation, and limited experimental accessibility. This review identifies a gap between the development of rheological models and their application in recycled polyolefin systems. Future progress on eco-composite design will require further development of integrative approaches that balance physical insight, predictive capability, and experimental feasibility. In this context, rheology should be repositioned from a post-characterization technique to a central tool for the design and optimization of sustainable polymer composites. From an applied perspective, these findings support the use of rheological parameters as practical indicators for guiding formulation strategies and optimizing processing conditions in recycled polyolefin-based materials. Full article

To address the issue of motion artifact interference faced by wearable ECG monitoring devices in dynamic environments, this paper proposes an adaptive motion artifact removal framework based on improved Variational Mode Decomposition (VMD). By designing a parameter self-adjustment mechanism and a multi-feature fusion mode selection strategy, the algorithm’s adaptability to non-stationary ECG signals and noise separation accuracy are enhanced. Experiments on the MIT-BIH Arrhythmia Database demonstrate that the improved VMD algorithm outperforms traditional wavelet transform, Recursive Least Squares (RLS), and conventional VMD methods in multiple performance metrics. Specifically, the signal-to-noise ratio (SNR) is improved by 5.17 dB, the Percentage Root Mean Squared Difference (PRD) is reduced to 49.13%, the correlation coefficient is increased to 0.88, and high real-time processing capability (Real-Time Processing Ratio, RTR = 22.5) is maintained, meeting the low-latency requirements of wearable devices. Moreover, case studies on pathological recordings (e.g., Wolff–Parkinson–White syndrome and third-degree atrioventricular block) reveal that the improved VMD better preserves clinically significant features such as delta waves and dissociated P waves. Furthermore, a downstream arrhythmia classification task using a CWT-CNN classifier achieves 91.67% accuracy on denoised heartbeats, which is 2.67 percentage points higher than that on raw noisy signals (89.00%), confirming the practical benefit of the proposed preprocessing for AI-based diagnosis. This study provides an effective processing solution for improving the signal quality of wearable ECG monitoring. Full article

Background: Healthcare inventory management is critical for ensuring timely access to supplies and reducing stockouts. As supply chains grow more complex, algorithms, AI, and analytics techniques have emerged as tools for forecasting, tracking, classification, and procurement. Yet empirical validation across diverse contexts remains inadequate, and existing reviews treat these approaches as separate streams rather than an integrated system. Methods: To evaluate these capabilities, a systematic review of 64 peer-reviewed articles published between 2011 and 2025 was conducted using a descriptive and content analysis approach on the use of Triple A (Analytics, AI, and Algorithms) techniques in inventory frameworks across various healthcare contexts, such as hospitals, pharmaceutical supply chains, and humanitarian supply chains. Results: Integrating multiple Triple A approaches consistently outperforms single-method strategies, particularly with RFID and IoT tools. Key findings often overlooked are: emergency procurement and classification, which remain neglected despite the highest patient safety stakes, and key procurement drivers—organizational conditions, supplier reliability, and team capacity. Data quality, interoperability, and cybersecurity further constrain generalizability. Conclusions: Bridging these gaps requires integrated Triple A approaches rather than single methods. Phased implementation, cloud-based platforms, and privacy-by-design offer practical pathways for building resilience under real-world constraints. Full article

The Kangaroo Escape Optimizer (KEO) is a recently proposed biomimetic metaheuristic inspired by the adaptive escape strategies of kangaroos in predator–prey interactions. Although effective, KEO-like algorithms based on many populations may suffer from premature convergence and loss of population diversity when addressing complex, multimodal, and constrained optimization problems. This paper proposes an Enhanced Kangaroo Escape Optimizer (EKEO) that integrates Differential Evolution Mutation (DEM) and Quasi-Oppositional Learning (QOL) to address fundamental limitations in exploration–exploitation balance. From a biomimetic perspective, DEM mimics the refined high-frequency muscular adjustments of a kangaroo during close-range evasion, enabling local refinement around promising solutions, while QOL emulates the animal’s sudden directional changes and scanning behavior to preserve population diversity and escape local optima. Their principled integration yields a robust optimization framework that consistently outperforms state-of-the-art and classical metaheuristics across benchmark functions and real-world engineering problems. The findings suggest a generalizable design principle for biomimetic hybrid metaheuristics, demonstrating that coupling directed exploitation with diversity-preserving exploration leads to reliable high-performance optimization. The performance of EKEO is rigorously evaluated in two phases. First, its optimization accuracy and convergence speed are benchmarked against 11 state-of-the-art and classical metaheuristics on 23 classical benchmark functions and the CEC 2019 test suite. Second, its practical applicability and constraint-handling effectiveness are validated on four real-world engineering design problems: step-cone pulley, gear system, tubular column, and pressure vessel design. The experimental results are supported by comprehensive statistical analyses (including Wilcoxon rank-sum tests) and convergence curves, showing that EKEO consistently outperforms its competitors in solution quality, convergence speed, and robustness. These findings establish EKEO as a competitive, reliable, and versatile biomimetic optimization tool suitable for solving complex continuous and constrained engineering optimization problems. Full article

Additive manufacturing (AM) enables the fabrication of complex three-dimensional components with embedded internal flow channels, but the as-built inner surfaces often exhibit high roughness and poor surface-quality uniformity, particularly at non-coplanar corner regions such as sharp bends and junctions. Conventional abrasive flow machining (AFM) can improve the overall surface finish of such channels; however, corner regions commonly remain weak-removal zones because of local flow stagnation and insufficient abrasive action. To address this limitation, this study proposes a six-degree-of-freedom (6-DOF) robotic-arm-assisted liquid metal-driven abrasive flow (LM-AF) polishing strategy in which robotic pose regulation is used to guide the liquid metal droplet to designated corner regions while preserving its responsiveness to the electric field. Numerical simulations and conventional AFM experiments on S-shaped and M-shaped spatial channels were first conducted to identify the corner regions as the primary sources of polishing non-uniformity. A robotic posture-control framework was then established through manipulator kinematics, point-cloud-based flow-direction identification, and Rodrigues-matrix-based pose transformation. On this basis, localized secondary polishing was experimentally performed on an S-shaped channel using an AC electric-field-driven liquid-metal abrasive system. The results show that corner-region roughness was significantly reduced and approached the straight-channel benchmark after secondary polishing, demonstrating a marked improvement in inner-surface uniformity. This study provides a practical route for targeted compensation polishing in complex three-dimensional internal channels and offers a new framework for robotic-assisted post-processing of AM-fabricated flow paths. Full article

Speech-driven lip synchronization is an important technique for talking-face video generation, with broad application potential in virtual humans, video dubbing, digital media, and human–computer interaction. However, existing methods still face challenges in achieving reliable lip synchronization while maintaining stable identity preservation, high visual fidelity, and efficient inference, especially in Chinese-language scenarios where related research remains relatively limited. To address these issues, we propose FastTalk, a speech-driven lip synchronization method for Chinese-language scenarios. The proposed framework performs latent-space restoration for efficient video synthesis, uses a fixed-mask strategy to suppress shortcut visual cues and strengthen audio-driven lip-shape prediction, and adopts a two-stage training scheme to reduce the gap between training and inference. This design improves generation stability while preserving efficiency. Experimental results show that FastTalk achieves competitive lip synchronization performance while improving visual quality and identity preservation. These results indicate that FastTalk provides an effective solution for Chinese speech-driven lip synchronization video generation. Full article

Background: Ischemic stroke remains a major cause of disability and reduced quality of life (QoL). This study aimed to identify factors associated with QoL after ischemic stroke, with particular emphasis on independence, illness acceptance, social support, comorbidity status, and the timeliness of diagnosis and treatment. Methods: This single-center cross-sectional study included 100 consecutively recruited patients after ischemic stroke hospitalized in the Department of Neurology with the Stroke Unit at the S. Żeromski Specialist Hospital in Krakow. Data were collected using an author-designed questionnaire and standardized instruments: the World Health Organization Quality of Life-BREF (WHOQOL-BREF), the Multidimensional Scale of Perceived Social Support (MSPSS), the Lawton Instrumental Activities of Daily Living Scale (IADL), and the Acceptance of Illness Scale (AIS). Statistical analysis included Spearman’s rank correlation coefficient and the Mann–Whitney U, Friedman, and Kolmogorov–Smirnov tests. Results: Significant positive correlations were found between all WHOQOL-BREF domains and IADL, AIS, and MSPSS scores. The strongest correlations were observed between IADL and the physical and psychological QoL domains. A strong positive correlation was also found between IADL and AIS (rho = 0.88; p < 0.001). Better QoL and greater independence were observed in patients with fewer comorbidities. Patients who received timely diagnosis and treatment achieved better outcomes in terms of QoL, IADL, and AIS. Perceived social support was comparable across MSPSS subscales (p = 0.56) but positively correlated with all QoL domains (rho = 0.55–0.64; p < 0.001). Conclusions: Better QoL after ischemic stroke was associated with greater independence, higher illness acceptance, stronger perceived social support, and timely diagnosis and treatment, suggesting that post-stroke QoL is related to both functional and psychosocial factors. Full article

The black-winged kite algorithm (BKA) integrates the Cauchy mutation strategy and the leader selection strategy to simulate high-altitude circling exploration, fixed-point diving attack, and group cooperative migration of the black-winged kites to approximate the global optimal solution. The BKA exhibits deficiencies in ponderous convergence efficacy, inefficient calculation precision, and insufficient population diversity. To strengthen the convergence property and computational practicability, an enhanced BKA with multiple strategies (MSBKA) is advocated to accommodate global optimization and constrained engineering applications. The objective is to systematically verify its advancement and competitiveness and accurately actualize the global optimal solution. The ranking-based differential mutation can strengthen population information interaction, accelerate convergence efficiency, restrain premature convergence, diminish homogenization competition, promote exploration and exploitation, intensify elite individual guidance, downscale ineffective iterations, and materialize orderly population renewal. The simplex method can execute the local refinement operations of reflection, expansion, compression and contraction, strengthen local mining efficiency, ameliorate solution accuracy, abate parameter sensitivity, eschew local optimal traps, accelerate accurate convergence, and preserve the optimal individual potential. The elite opposition-based learning strategy can fabricate reverse solutions, expand the monolithic detection space, shorten the convergence process, elevate the quality of initial and iterative solutions, boost population diversity, guide intelligent search direction, and relieve premature convergence. The MSBKA utilizes deficiency orientation, strategy adaptation, and collaborative search to accomplish the realistic demands of high-precision, high-efficiency and strong constraint adaptation, surmount the static trade-off dilemma, endow a strong directional abscond mechanism to replace random perturbation, and actualize the inertia of directional exploration and the blind spots of solution exploitation. Twenty-three benchmark functions and six real-world engineering designs are employed to authenticate theoretical superiority and engineering practicability. The experimental results demonstrate that the MSBKA incorporates strong practicability and reliability to strengthen information interaction, restrain search stagnation, diminish convergence oscillation and fluctuation, facilitate globalized discovery and localized extraction, expedite convergence efficacy, ameliorate solution precision, and consolidate stability and robustness. Full article

Illegal, unreported, and unregulated (IUU) fishing activities have become one of the most critical challenges facing the global fish industry, particularly in developing countries, with the economic impact of fish fraud reaching billions of dollars annually. A major contributor to this problem is the limitation of conventional fish supply chain systems, which lack secure data sharing among stakeholders, fail to provide trusted product information to consumers, and offer insufficient transparency for regulatory authorities. These shortcomings facilitate fraud and weaken trust and oversight across the supply chain. Blockchain technology has demonstrated strong capability to address key cybersecurity challenges by enhancing traceability, transparency, and tamper-resistant data integrity across distributed supply chain stakeholders. In this paper, we present an enterprise-oriented prototype of a secure, permissioned blockchain-based fish supply chain system designed to enable trusted data sharing and end-to-end traceability across multi-stakeholder environments. Building upon our prior work in Ethereum-based seafood quality monitoring, this study contributes: (1) a modular, consortium-grade architecture implemented using Hyperledger Fabric and containerized via Docker, supporting scalable organizational participation; (2) formal UML-based system modeling of supply chain actors, assets, and lifecycle transitions; and (3) custom chaincode logic that enforces ownership transfer workflows and regulatory compliance policies. In addition, the architecture is designed as agent-ready, exposing standardized APIs that enable future integration of autonomous AI-driven client applications for proactive supply chain orchestration. By leveraging a private, permissioned network model, the functional prototype demonstrates the feasibility of improving data veracity and providing a practical foundation for mitigating fraud and enhancing regulatory oversight in the global fish industry. Full article

The efficacy of healthcare performance evaluation systems depends on their design and implementation, as well as on their perceived value and integration into daily practice. This study explores the acceptability of a healthcare performance evaluation system, used by health and administrative professionals in four rural healthcare settings in Ethiopia, Tanzania, and Uganda, three years after its implementation. In-depth semi-structured interviews were conducted, either in person or via video conference, with 17 professionals involved in system design and implementation. The analysis of qualitative data drew on Sekhon’s Theoretical Framework of Acceptability, using content analysis to identify themes across seven dimensions of acceptability. Key findings show that participants’ perceptions of acceptability of the performance evaluation system are influenced by data disclosure and reputational effect, the system’s understandability, alignment with their mission to improve quality of care, perceived usefulness, experienced opportunity costs, and intervention burden. The key features of the performance evaluation system are the most critical factors contributing to its acceptability, but the administrative burden, which includes professionals’ need to invest more time and change work habits to use the new system, poses some challenges and may hinder the medium- to long-term effectiveness of the intervention. Full article

Human–AI systems often involve repeated interaction among users, organizations, and AI components rather than isolated model outputs. In such settings, cooperation can be pursued either by changing agent incentives or by adding an explicit accountability layer. We formalize the Institutional Monitoring and Ledger (IML) framework, which augments a Markov game with monitoring, evidence logging, delayed settlement, and review while leaving the base dynamics unchanged. We derive conservative incentive checks that clarify how detection quality, review accuracy, settlement delay, and sanction size jointly shape deterrence and wrongful-penalty risk. We then provide pilot evidence in two canonical sequential social dilemmas, Harvest and Cleanup, using five agents, PPO training, five training seeds per condition, and comparisons against PPO, inequity aversion, social influence, and IML ablations. In these settings, IML avoided some of the optimization instability observed in the representative internalization baselines tested here, made monitoring error directly visible through ledger records, and showed how false positives can accumulate into a persistent welfare cost. Agent-level analyses in these symmetric environments found nearly uniform measured enforcement burden, while temporal analyses showed that late-stage enforcement is increasingly dominated by residual false positives. These results do not establish legitimacy in human-facing settings or deployment readiness. They instead position IML as a framework with pilot evidence for studying accountability mechanisms in cooperative human–AI systems and highlight measurement error, review design, and due process as central design constraints. Full article

Background: Over the past 25 years, advances in knee surgery have been driven by an improved understanding of fracture morphology and associated injuries, as well as by significant technological progress. The introduction of novel classification systems has led to the refinement of treatment strategies, particularly with respect to the selection of surgical approaches. Furthermore, advances in biomechanical understanding have facilitated the development of new osteosyntheses designed to promote earlier rehabilitation while simultaneously reducing complication rates. Research Question: Which key milestones over the last 25 years have significantly influenced treatment strategies for knee joint fractures, with a perspective on unresolved issues? Results: Recent advances in fracture management, osteosynthesis, imaging techniques, and biomechanical research have substantially improved clinical outcomes, including a reduction in infection rates and improved postoperative results. The implementation of new classification systems has enabled more precise preoperative planning, allowing surgeons to define approaches that ensure adequate visualization of the articular surface while facilitating optimal positioning of the osteosynthesis. In terms of osteosynthesis, the introduction of locking plate technology has become widely established and supported by biomechanical evidence and has largely replaced traditional methods such as tension-band wiring of the patella. Despite these advances, fracture management in geriatric patients remains a considerable challenge, as compromised bone quality frequently limits the ability to achieve sufficiently load-stable osteosynthesis. Direct visualization of the articular surface is essential for adequate assessment and reduction of the affected articular segment. However, there is currently no consensus on which surgical approach or possible extension is most appropriate while simultaneously ensuring a low complication rate. Full article

Background: Automated identification of logistics units is a critical requirement in high-volume warehouse operations, particularly in retails that handle millions of cartons annually. Although barcode-based systems are widely used, they generate recurring costs for labeling, printing, quality control and readability issues, often leading to manual intervention and delays. Methods: This study presents a low-cost and flexible vision-based identification system that directly reads carton identifiers using optical character recognition (OCR). This system designed for edge deployment on resource-constrained hardware and incorporates a rotation-invariant preprocessing pipeline to support robust recognition under real conditions. Proposed approach was tested in two German retails. Results: Tests show recognition accuracies 96% to 98% under operational conditions, with real-time processing performance in the range of 58 to 125 ms per scan, depending on the hardware. These indicate that the system can be integrated into high-throughput logistics workflows. Additionally, the study provides insights into the economic implications of replacing barcode-based identification. Based on site-specific observations and labeling costs, the system shows the potential to reduce manual intervention and lower operational expenses in large-scale retails. Conclusions: Findings suggest that OCR can serve a cost-efficient alternative to barcode systems in environments where flexibility, robustness, and low deployment cost are critical. Full article