Search Results (2,132)

This paper presents a real-time pedestrian situation detection framework for autonomous mobility platforms. The proposed approach extracts pedestrians from images acquired by a camera mounted on an autonomous mobility system, classifies their postures, tracks their trajectories, and subsequently detects pedestrian situations. A convolutional neural network (CNN) is employed for pedestrian detection and posture classification, where the YOLOv12 model is fine-tuned via transfer learning for this purpose. To improve detection and classification performance, a region of interest (ROI) is defined using camera calibration data, enabling robust detection of small-scale pedestrians over long distances. Using a custom-labeled dataset, the proposed method achieves a precision of 96.6% and a recall of 97.0% for pedestrian detection and posture classification. The detected pedestrians are tracked using the DeepSORT algorithm, and their situations are inferred through a rule-based analysis module. Experimental results demonstrate that the proposed system operates at an execution speed of 58.11 ms per frame, corresponding to 17.2 fps, thereby satisfying the real-time requirements for autonomous mobility applications. These results confirm that the proposed framework enables reliable real-time pedestrian extraction and situation awareness in real-world autonomous mobility environments. Full article

Background: Soft tissue stability around dental implant abutments is critical for maintaining a functional peri-implant seal. Yellow anodization is used to improve the aesthetic and surface characteristics of titanium abutments, yet its epithelial effects under more physiologically relevant 3D conditions remain insufficiently explored. Objective: To develop a 3D bioprinted in vitro peri-implant mucosa model and to compare epithelial cell responses on yellow anodized versus turned titanium abutment surfaces. Methods: Commercial Grade 5 (Ti6Al4V) titanium abutments were anodized and compared with turned controls. A collagen-based 3D bioprinted “collar-like” construct incorporating YD-38 epithelial cells was fabricated using a custom holder system to simulate peri-implant mucosal contact. Samples were cultured for 14 and 21 days. Cell distribution and morphology were assessed by optical microscopy and HE staining, while cytoskeletal organization was evaluated by TRITC-phalloidin/Hoechst staining and confocal microscopy. Quantitative fluorescence analysis was performed at 21 days. Results: Both surfaces supported epithelial coverage in the 3D environment. Anodized specimens showed more pronounced actin cytoskeletal organization and the presence of actin-rich, filamentous cellular extensions compared with turned controls. Quantitative image analysis demonstrated significantly higher TRITC-phalloidin signal intensity at 21 days on anodized samples (p < 0.001). Conclusions: Within the limitations of a 3D epithelial in vitro model using YD-38 cells, yellow anodization was associated with enhanced epithelial cytoskeletal organization compared with turned titanium. The presented 3D bioprinted platform may serve as a practical in vitro tool for screening abutment surface modifications relevant to peri-implant soft tissue integration. Full article

This study introduces a framework for estimating the optical scattering properties of thin-film phantoms using a custom-built Spectral-Domain Dental Optical Coherence Tomography (DEN-OCT) system operating within the 780–900 nm spectral range. The purpose of this work was to assess the performance of this system. The system exhibited high depth-resolved imaging performance with an axial resolution of approximately 16.30 µm, a signal-to-noise ratio of about 32.4 dB, and a 6 dB sensitivity roll-off depth near 2 mm, yielding an effective imaging range of 2.5 mm. Thin-film phantoms with controlled optical characteristics were fabricated and analyzed using Beer–Lambert and diffusion approximation models to evaluate attenuation behavior. Samples representing different tissue analogs demonstrated distinct scattering responses: one sample showed strong scattering similar to hard tissues, while the others exhibited lower scattering and higher transmission, resembling soft-tissue properties. Spectrophotometric measurements at 840 nm supported these trends through characteristic transmittance and reflectance profiles. While homogeneous samples conformed to analytical models, the highly scattering sample deviated due to structural non-uniformity, requiring Monte Carlo simulation to accurately describe photon transport. OCT A-scan analyses fitted with exponential decay models produced attenuation coefficients consistent with spectrophotometric data, confirming the dominance of scattering over absorption. The integration of OCT imaging, optical modeling, and Monte Carlo simulation establishes a reliable methodology for quantitative scattering estimation and demonstrates the potential of the developed DEN-OCT system for advanced dental and biomedical imaging applications. The innovation of this work lies in the integration of phantom-based optical calibration, multi-model scattering analysis, and depth-resolved OCT signal modeling, providing a validated pathway for quantitative parameter extraction in dental OCT applications. Full article

Technological advancements have significantly improved cattle farming, particularly in sensor-based activity monitoring for health management, estrus detection, and overall herd supervision. However, such a sensor-based monitoring framework often illustrates several issues, such as high cost, animal discomfort, and susceptibility to false measurement. This study introduces a vision-based cattle activity monitoring approach deployed in a commercial Nestlé dairy farm, specifically one that is estrus-focused, where overhead cameras capture unconstrained herd behavior under variable lighting, occlusions, and crowding. A custom dataset of 2956 Images are collected and then annotated into four fine-grained behaviors—standing, lying, grazing, and estrus—enabling detailed analysis beyond coarse activity categories commonly used in prior livestock monitoring studies. Furthermore, computer vision-based deep learning algorithms are deployed on this dataset to classify the aforementioned classes. A comparative analysis of YOLOv8 and YOLOv9 is provided, which clearly illustrates that YOLOv8-L achieved a mAP of 91.11%, whereas YOLOv9-E achieved a mAP of 90.23%. Full article

Curling presents a challenging continuous-control problem in which shot outcomes depend on long-horizon interactions between complex physical dynamics, strategic intent, and opponent responses. Despite recent progress in applying reinforcement learning (RL) to games and sports, curling lacks a unified environment that jointly supports stable, rule-consistent simulation, structured state abstraction, and scalable agent training. To address this gap, we introduce a comprehensive learning framework for curling AI, consisting of a full-sized simulation environment, a task-aligned Markov decision process (MDP) formulation, and a two-phase training strategy designed for stable long-horizon optimization. First, we propose a novel MDP formulation that incorporates stone configuration, game context, and dynamic scoring factors, enabling an RL agent to reason simultaneously about physical feasibility and strategic desirability. Second, we present a two-phase curriculum learning procedure that significantly improves sample efficiency: Phase 1 trains the agent to master delivery mechanics by rewarding accurate placement around the tee line, while Phase 2 transitions to strategic learning with score-based rewards that encourage offensive and defensive planning. This staged training stabilizes policy learning and reduces the difficulty of direct exploration in the full curling action space. We integrate this MDP and training procedure into a unified Curling RL Framework, built upon a custom simulator designed for stability, reproducibility, and efficient RL training and a self-play mechanism tailored for strategic decision-making. Agent policies are optimized using Soft Actor–Critic (SAC), an entropy-regularized off-policy algorithm designed for continuous control. As a case study, we compare the learned agent’s shot patterns with elite match records from the men’s division of the Le Gruyère AOP European Curling Championships 2023, using 6512 extracted shot images. Experimental results demonstrate that the proposed framework learns diverse, human-like curling shots and outperforms ablated variants across both learning curves and head-to-head evaluations. Beyond curling, our framework provides a principled template for developing RL agents in physics-driven, strategy-intensive sports environments. Full article

Background: Occupational exposure to aerosol particles can pose a substantial health risk. The study aimed to characterise the deposition of occupationally relevant aerosols in a 3D anatomical adult nasal cavity model under steady and unsteady flows. Materials: The deposition of aerosolised wheat flour, pine wood sanding dust, carbon black, and Arizona Test Dust A3 was quantified under steady flows (5, 7.5, and 20 L/min per nostril) and an unsteady breathing pattern generated by the commercial breathing simulator. Image analysis with custom software quantified the area covered by deposited particles. The Downstream Penetration Index (DPI) was determined from the outlet mass. Results: The highest segmental deposition occurred in the anterior segment of the lateral wall (WA) and septum (SA), with moderate values in the middle lateral wall (WM) and the lowest in the posterior lateral wall (WP, nasopharynx) and septum (SP). Arizona Test Dust A3 and carbon black demonstrated higher middle-posterior deposition and DPI, consistent with finer particle size distributions (PSD) and greater sub-10 µm fractions. In contrast, wheat flour and pine wood dust, with larger median particle sizes and lower sub-10 µm fractions, showed stronger anterior filtration and lower DPI. Increased flow enhanced anterior filtration of coarse particles and shifted deposition forward, aligning with increased inertial impaction, but elevated DPI for fine particles. Under unsteady flow, deposition was intermediate between 7.5 and 20 L/min. Conclusions: This study shows that PSD, morphology, and flow conditions influence nasal deposition. Coarse aerosols were filtered in the anterior nose, while fine-rich aerosols showed relatively greater middle-posterior deposition and higher DPI. These findings are essential for assessing occupational exposure and developing interventions and prevention strategies. Full article

This in vitro study compared the antimicrobial and antibiofilm efficacy of four commercially available chlorhexidine (CHX)-based mouthwashes, with different nominal CHX concentrations, against clinically relevant postoperative oral pathogens, including Staphylococcus aureus, Streptococcus mutans, Escherichia coli, Pseudomonas aeruginosa, Candida albicans, and Candida auris. Antimicrobial potency was evaluated using MIC and CEMIC indices, while biofilm thickness reduction was quantified using 3D digital microscopy and custom image analysis software. Among the tested formulations, the excipient-enriched formulation exhibited the lowest MIC values and the most significant reduction in biofilm thickness, particularly against Gram-negative bacteria and Candida species. All mouthwashes achieved CEMIC < 0.1, confirming high theoretical applicability margins; however, CEMIC reflects potential clinical usefulness rather than clinical superiority. The findings demonstrate that the antimicrobial and antibiofilm activity of CHX rinses is formulation-dependent and cannot be predicted solely by CHX concentration. The influence of excipients is discussed as a possible contributing factor, but related mechanisms remain speculative and require direct validation in future studies. This work supports a formulation-driven, evidence-based approach to antiseptic comparison in postoperative dentistry, without assessing clinical wound-healing outcomes. Full article

The unpredictable nature of outdoor settings introduces numerous safety concerns, making hazard detection crucial for safe navigation. To address this issue, this paper proposes a sidewalk hazard detection system that combines a Variational Autoencoder (VAE) with a One-Class Support Vector Machine (OCSVM), using a wearable RGB camera as the primary sensing modality to enable low-cost, portable deployment and provide visual detail for detecting surface irregularities and unexpected objects. The VAE is trained exclusively on clean, obstruction-free sidewalk data to learn normal appearance patterns. At inference time, the reconstruction error produced by the VAE is used to identify spatial anomalies within each frame. These flagged anomalies are passed to an OCSVM, which determines whether they constitute a non-hazardous anomaly or a true hazardous anomaly that may impede navigation. To support this approach, we introduce a custom dataset consisting of over 20,000 training images of normal sidewalk scenes and 8000 testing frames containing both hazardous and non-hazardous anomalies. Experimental results demonstrate that the proposed VAE + OCSVM model achieves an AUC of 0.92 and an F1 score of 0.85, outperforming baseline anomaly detection models for outdoor sidewalk navigation. These findings indicate that the hybrid method offers a robust solution for sidewalk hazard detection in real-world outdoor environments. Full article

Background and Objectives: Academic point-of-care (POC) manufacturing enables the in-hospital design and production of patient-specific medical devices within certified environments, integrating clinical practice, engineering, and translational research. This model represents a new academic ecosystem that accelerates innovation while maintaining compliance with medical device regulations. Gregorio Marañón University Hospital has established one of the first ISO 13485-certified academic manufacturing facilities in Spain, providing on-site production of anatomical models, surgical guides, and custom implants for oral and maxillofacial surgery. This study presents a retrospective review of all devices produced between April 2017 and September 2025, analyzing their typology, materials, production parameters, and clinical applications. Materials and Methods: A descriptive, retrospective study was conducted on 442 3D-printed medical devices fabricated for oral and maxillofacial surgical cases. Recorded variables included device classification, indication, printing technology, material type, sterilization method, working and printing times, and clinical utility. Image segmentation and design were performed using 3D Slicer and Meshmixer. Manufacturing used fused deposition modeling (FDM) and stereolithography (SLA) technologies with PLA and biocompatible resin (Biomed Clear V1). Data were analyzed descriptively. Results: During the eight-year period, 442 devices were manufactured. Biomodels constituted the majority (approximately 68%), followed by surgical guides (20%) and patient-specific implants (7%). Trauma and oncology were the leading clinical indications, representing 45% and 33% of all devices, respectively. The orbital region was the most frequent anatomical site. FDM accounted for 63% of the printing technologies used, and PLA was the predominant material. The mean working time per device was 3.4 h and mean printing time 12.6 h. Most devices were applied to preoperative planning (59%) or intraoperative use (35%). Conclusions: Academic POC manufacturing offers a sustainable, clinically integrated model for translating digital workflows and additive manufacturing into daily surgical practice. The eight-year experience of Gregorio Marañón University Hospital demonstrates how academic production units can enhance surgical precision, accelerate innovation, and ensure regulatory compliance while promoting education and translational research in healthcare. Full article

This study presents a compact bulb-shaped ultra-wideband microstrip patch antenna designed for microwave imaging applications, more specifically, breast tumor detection. Traditional antenna design methods for medical applications are time-consuming. The proposed antenna, designed in CST Microwave Studio 2019 on a Rogers RT 5880 substrate with a slotted ground plane, achieves a bandwidth of 11.1 GHz, a gain of 6.2 dBi, and an efficiency above 80%. In response to the limitations of conventional antenna design approaches, this study introduces a novel machine learning-based approach to accelerate the design process, where a custom CatBoost model predicts key dimensions—feedline width, large circle radius, and small circle radius, based on the performance metrics such as resonant frequency, minimum reflection coefficient, bandwidth, real and imaginary part of impedance. The model achieves a cross-validation score of 95.13% with a mean absolute error of 0.0166 mm, outperforming conventional machine learning approaches. Shapley Additive exPlanations analysis is applied to interpret feature contributions. A prototype is fabricated using the prediction of a machine learning model. The bulb-shaped antenna structure, wide operational bandwidth, consistent gain, and strong sensitivity to tissue dielectric variations enhance its effectiveness for breast tumor detection compared with conventional antennas. Furthermore, experiments with a breast phantom confirmed the prototype’s suitability for detecting dielectric contrasts in tissue, establishing a foundation for machine learning-assisted antenna design in medical imaging. Full article

The growing global population and increasing food demand highlight the need for sustainable agricultural practices that balance productivity with environmental protection. Traditional blanket pesticide spraying leads to overuse of chemicals, environmental pollution, and biodiversity loss. This study aims to develop an innovative approach to precision pest management using mobile computing, computer vision, and deep learning techniques. A mobile measurement platform equipped with cameras and an onboard computer was designed to collect real-time field data and detect pest infestations. The system uses an advanced object detection algorithm based on the YOLOv4 architecture, trained on a custom dataset of rapeseed pest images. Modifications were made to enhance detection accuracy, especially for small objects. Field tests demonstrated the system’s ability to identify and count pests, such as the pollen beetle (Brassicogethes aeneus), in rapeseed crops. The collected data, combined with GPS information, generated pest density maps, which can guide site-specific pesticide applications. The results show that the proposed method achieved a mean average precision (mAP) of 83.7% on the test dataset. Field measurements conducted during the traversal of rapeseed fields enabled the creation of density maps illustrating the distribution of pollen beetles. Based on these maps, the potential for pesticide savings was demonstrated, and the migration dynamics of pollen beetle were discussed. Full article

In the modern era, demand forecasting enhances the decision-making tasks of industries for controlling production planning and reducing inventory costs. However, the dynamic nature of the fashion and apparel retail industry necessitates precise demand forecasting to optimize supply chain operations and meet customer expectations. Consequently, this research proposes the Formicary Zebra Optimization-Based Distributed Attention-Guided Convolutional Recurrent Neural Network (FZ-DACR) model for improving the demand forecasting. In the proposed approach, the combination of the Formicary Zebra Optimization and Distributed Attention mechanism enabled deep learning architectures to assist in capturing the complex patterns of the retail sales data. Specifically, the neural networks, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), facilitate extracting the local features and temporal dependencies to analyze the volatile demand patterns. Furthermore, the proposed model integrates visual and textual data to enhance forecasting accuracy. By leveraging the adaptive optimization capabilities of the Formicary Zebra Algorithm, the proposed model effectively extracts features from product images and historical sales data while addressing the complexities of volatile demand patterns. Based on extensive experimental analysis of the proposed model using diverse datasets, the FZ-DACR model achieves superior performance, with minimum error values including MAE of 1.34, MSE of 4.7, RMS of 2.17, and R² of 93.3% using the DRESS dataset. Moreover, the findings highlight the ability of the proposed model in managing the fluctuating trends and supporting inventory and pricing strategies effectively. This innovative approach has significant implications for retailers, enabling more agile supply chains and improved decision making in a highly competitive market. Full article

Mechanical stimulation critically regulates mesenchymal stem cell (MSC) differentiation, yet its effects in three-dimensional (3D) environments remain poorly defined. Here, we developed a custom dynamic stretcher integrating poly(dimethylsiloxane) (PDMS) chambers to apply cyclic strain to human MSCs encapsulated in Fmoc-diphenylalanine (Fmoc-FF) peptide hydrogels—a fully synthetic, tunable extracellular matrix mimic. Finite element modeling verified uniform strain transmission across the hydrogel. Dynamic stretching at 0.5 Hz and 10% strain induced pronounced cytoskeletal alignment, enhanced actin stress fiber formation (coherency index $\approx 0.85$), and significantly increased proliferation compared to static or high-frequency (2.5 Hz, 1%) conditions (coherency index $\approx 0.6$). Quantitative image analysis confirmed strain-dependent increases in coherency index and F-actin intensity, indicating enhanced mechanotransductive remodeling. Biochemical assays and qRT–PCR revealed 2–3-fold upregulation of osteogenic markers—RUNX2, ALP, COL1A1, OSX, BMP, ON, and IBSP—under optimal strain. These results demonstrate that low-frequency, high-strain mechanical loading in 3D peptide hydrogels activates RhoA/ROCK and YAP/TAZ pathways, driving osteogenic differentiation. The integrated experimental–computational approach provides a robust platform for studying mechanobiological regulation and advancing mechanically tunable biomaterials for bone tissue engineering. Full article

The operational reliability of wind turbines is critical for sustainable energy production in smart grids. This study proposes a remote monitoring approach using perceptually enhanced satellite imagery. Sentinel-2 multispectral data (10 m resolution) has been processed with a Super-Resolution Generative Adversarial Network (SRGAN) to improve visual quality to a perceptual resolution of 30 cm. Although true spatial refinement is not achieved, the sharper structural details enhance classification accuracy. The data set comprises 15,000 images—10,000 SRGAN-enhanced and 5000 augmented through rotation, zoom in, increasing brightness, noise addition, and blurring. A custom Convolutional Neural Network (CNN) has been trained to classify turbines as damaged or intact, achieving 95% accuracy, a 0.99 ROC-AUC, and a 0.95 F1 score. These results demonstrate that perceptually sharpened satellite data can effectively support automated wind turbine damage detection and predictive maintenance. The proposed framework also lays the groundwork for broader real-time and multimodal monitoring and cost-efficient applications in renewable energy systems. Full article

This study presents a robust deep learning-based approach for temperature sensing using Fiber Specklegram Sensors (FSS), leveraging an extended experimental framework to evaluate model generalization. A convolutional neural network (CNN), specifically a customized MobileNet architecture (MNet-reg), was trained on multiple experimental datasets to assess the impact of increasing data availability on sensing accuracy. Generalization is evaluated as cross-dataset performance under unseen experimental realizations, rather than under controlled intra-dataset splits. The experimental setup utilized a multi-mode optical fiber (MMF) (core diameter 62.5 µm) subjected to controlled thermal cycles via a PID-regulated heating system. The curated dataset comprises 24,528 specklegram images captured over a temperature range of 25.00 °C to 200.00 °C with increments of ~0.20 °C. The experimental results demonstrate that models trained with an increasing number of datasets (from 1 to 13) significantly improve accuracy, reducing Mean Absolute Error (MAE) from 13.39 to 0.69 °C, and achieving a Root Mean Square Error (RMSE) of 0.90 °C with an R² score of 0.99. Our systematic analysis establishes that scaling experimental data diversity—through training on multiple independent realizations—is the foundational strategy to overcome domain shift and enable robust cross-dataset generalization. Full article