Search Results (8,040)

Tool wear degrades sharpness and durability, causing poor surface quality, dimensional errors, and high costs. Precise RUL prediction optimizes production, reduces rework, and prevents downtime. Conventional replacement relies on experience and risks inaccuracy. Real-time monitoring enables optimal intervals. Predictive maintenance cuts tooling costs and ensures quality. Industry 4.0 integrates sensors for intelligent wear management. This study applies GRNN to predict RUL with minimal TMD. A C#-based system with intuitive HMI was validated in real machining. Full article

Background: Nuclear cataracts cause visual degradation through light scattering by aggregated proteins and particles within the crystalline lens. Existing computational models mainly consider submicron scatterers, while the optical impact of micrometer-scale particles observed in human nuclear cataracts remains underexplored. Objective: This study extends a LOCS III–based computational cataract model by incorporating micrometer-scale particles and quantitatively evaluates their effects on forward and backward light scattering across nuclear cataract grades. Methods: A physics-based scattering model was implemented using optical simulation software (LightTools). Three particle populations—nanometer-scale (S-type), submicron-scale (M-type), and micrometer-scale (L-type)—were uniformly distributed within the lens. Retinal luminance reduction was analyzed for forward scattering, while slit-lamp-based backward scattering simulations were used to evaluate luminance distributions and chromaticity changes. Particle concentrations were varied within clinically reported ranges corresponding to LOCS III grades. Results: Micrometer-scale particles had minimal impact in early nuclear cataract grades but significantly increased forward scattering and luminance loss in advanced grades (NO5–NO6). Backward scattering simulations revealed pronounced luminance enhancement and yellow chromaticity shifts with increasing micrometer-scale particle concentration. One micrometer-scale particle produced a luminance-reduction effect equivalent to approximately 6–7 submicron particles, depending on cataract severity. Conclusions: Including micrometer-scale particles enables a more complete optical representation of nuclear cataracts, linking retinal image degradation with slit-lamp appearance. The model provides a physically grounded framework for offline analysis and reference data generation to support clinical interpretation of cataract grading. Full article

The ubiquity of smartphones has transformed them into primary repositories of sensitive data; however, traditional one-time authentication mechanisms create a critical trust gap by failing to verify identity post-unlock. Our aim is to mitigate these vulnerabilities and align with the Zero Trust Architecture (ZTA) framework and philosophy of “never trust, always verify,” as formally defined by the National Institute of Standards and Technology (NIST) in Special Publication 800-207. This study introduces a robust continuous authentication (CA) framework leveraging multimodal behavioral biometrics. A dedicated application was developed to synchronously capture touch, sliding, and inertial sensor telemetry. For feature modeling, a heterogeneous deep learning pipeline was employed to capture modality-specific characteristics, utilizing Convolutional Neural Networks (CNNs) for sensor data, Long Short-Term Memory (LSTM) networks for curvilinear sliding, and Gated Recurrent Units (GRUs) for discrete touch. To resolve performance degradation caused by class imbalance in Zero Trust environments, a Grid Search Optimization (GSO) strategy was applied to optimize a weighted voting ensemble, identifying the global optimum for decision thresholds and modality weights. Empirical validation on a dataset of 35,519 samples from 15 subjects demonstrates that the optimized ensemble achieves a peak accuracy of 99.23%. Sensor kinematics emerged as the primary biometric signature, followed by touch and sliding features. This framework enables high-precision, non-intrusive continuous verification, bridging the critical security gap in contemporary mobile architectures. Full article

Background and Objectives: Endothelial dysfunction is an early indicator of cardiovascular disease and is commonly assessed using flow-mediated dilation (FMD). Although handheld ultrasound (HHUS) devices improve measurement accessibility, image analysis for conventional flow-mediated dilation (FMD) assessment remains time-consuming and highly operator-dependent. This study aimed to evaluate the between-day test–retest reliability of an AI-assisted brachial artery image analysis workflow integrating HHUS imaging with a YOLO_v12 deep learning model in postmenopausal women. Materials and Methods: Seventeen postmenopausal women aged 55–70 years completed two flow-mediated dilation assessments conducted seven days apart. Brachial artery images were acquired using a standardized FMD protocol with a handheld ultrasound system. An AI-assisted image analysis workflow based on a YOLO_v12 deep learning model was used to automatically measure baseline diameter (D_base), peak diameter (D_peak), absolute FMD (FMD_abs), and relative FMD (FMD%). Between-day reliability was evaluated using intraclass correlation coefficients (ICCs), coefficients of variation (CVs), and Bland–Altman analysis. Results: Good between-day repeatability was observed for baseline and peak diameters, with ICCs of 0.81 and 0.76 and low CVs (3.26% and 3.22%), respectively. Functional vascular outcomes also demonstrated good reliability, with ICCs of 0.81 for FMD_abs and 0.87 for FMD%. However, higher CVs were observed for FMD_abs (17.15%) and FMD% (19.09%), indicating substantial inter-individual variability. Bland–Altman analysis showed a small mean difference for FMD% (0.34%), with no evidence of systematic bias. Conclusions: An AI-assisted HHUS image analysis workflow integrating a YOLO_v12 deep learning model demonstrates acceptable between-day reliability for diameter-based and dilation-based measures of flow-mediated dilation in postmenopausal women. While variability in functional responses exists, the proposed system is feasible for research-oriented vascular assessment, providing a methodological foundation for future validation and clinical translation studies. Full article

Chronic obstructive pulmonary disease (COPD) is a major health burden worldwide and in Taiwan, ranking as the third leading cause of death globally, and its prevalence in Taiwan continues to rise. Readmission within 14 days is a key indicator of disease instability and care efficiency, driven jointly by patient-level physiological vulnerability (such as reduced lung function and multiple comorbidities) and healthcare system-level deficiencies in transitional care. To mitigate the growing burden and improve quality of care, it is urgently necessary to develop an AI-based prediction model for 14-day readmission. Such a model could enable early identification of high-risk patients and trigger multidisciplinary interventions, such as pulmonary rehabilitation and remote monitoring, to effectively reduce avoidable early readmissions. However, medical data are commonly characterized by severe class imbalance, which limits the ability of conventional machine learning methods to identify minority-class cases. In this study, we used real-world clinical data from multiple hospitals in Kaohsiung City to construct a prediction framework that integrates data generation and ensemble learning to forecast readmission risk among patients with chronic obstructive pulmonary disease (COPD). CTGAN and kernel density estimation (KDE) were employed to augment the minority class, and the impact of these two generation approaches on model performance was compared across different augmentation ratios. We adopted a stacking architecture composed of six base models as the core framework and conducted systematic comparisons against the baseline models XGBoost, AdaBoost, Random Forest, and LightGBM across multiple recall thresholds, different feature configurations, and alternative data generation strategies. Overall, the results show that, under high-recall targets, KDE combined with stacking achieves the most stable and superior overall performance relative to the baseline models. We further performed ablation experiments by sequentially removing each base model to evaluate and analyze its contribution. The results indicate that removing KNN yields the greatest negative impact on the stacking classifier, particularly under high-recall settings where the declines in precision and F1-score are most pronounced, suggesting that KNN is most sensitive to the distributional changes introduced by KDE-generated data. This configuration simultaneously improves precision, F1-score, and specificity, and is therefore adopted as the final recommended model setting in this study. Full article

The Food Bank of Bogotá is a non-profit organization whose primary mission is to provide food aid to economically vulnerable people and others. One of its key operations is the distribution of food to over 600 beneficiaries. In this research, we present the design and implementation of a computer application that calculates the delivery schedule of the Food Bank vehicles. Firstly, the beneficiaries of the Food Bank are clustered into four delivery zones, and their orders are assigned to specific weeks of the month. Next, a variant of the Capacitated Periodic Vehicle Routing Problem (CPVRP) is solved with an open-source tool. Lastly, routes are assigned to days of the week depending on the traffic conditions. The numerical results showed significant improvements in terms of total time reduction with respect to the business-as-usual practice. This tool is essentially for the monthly planning of the distribution of routes. These routes eventually will need adjustments because of changes in the beneficiaries’ demand, traffic conditions, fleet availability, and so forth. At the time of writing, the model is being integrated with another application that records and tracks the orders in the Food Bank. The users of this application would handle the daily operation and will make manual adjustments if needed. Finally, we discuss the main limitations of the application, which lie primarily in the need to educate both the Food Bank staff and the beneficiaries’ management, who are accustomed to last-minute orders, very tight time windows, and reactive delivery schedules that are highly inefficient. Full article

Accurate and interpretable staging of Alzheimer’s disease (AD) remains challenging due to the heterogeneous progression of neurodegeneration and the complementary nature of imaging and clinical biomarkers. This study implements and evaluates an optimized Hierarchical Multi-Modal Fusion Framework (HMFF) that systematically integrates 3D structural MRI with clinical assessment scales for robust three-class classification of cognitively normal (CN), mild cognitive impairment (MCI), and AD subjects. A standardized preprocessing pipeline, including N4 bias field correction, nonlinear registration to MNI space, ANTsNet-based skull stripping, voxel normalization, and spatial resampling, was employed to ensure anatomically consistent and high-quality MRI inputs. Within the proposed framework, volumetric imaging features were extracted using a 3D DenseNet-121 architecture, while structured clinical information was modeled via an XGBoost classifier to capture nonlinear clinical priors. These heterogeneous representations were hierarchically fused through a lightweight multilayer perceptron, enabling effective cross-modal interaction. To further enhance discriminative capability and model efficiency, a hierarchical feature selection strategy was incorporated to progressively refine high-dimensional imaging features. Experimental results demonstrated that performance consistently improved with feature refinement and reached an optimal balance at approximately 90 selected features. Under this configuration, the proposed HMFF achieved an accuracy of 0.94 (95% Confidence Interval: [0.918, 0.951]), a recall of 0.91, a precision of 0.94, and an F1-score of 0.92, outperforming unimodal and conventional multimodal baselines under comparable settings. Moreover, Grad-CAM visualization confirmed that the model focused on clinically relevant neuroanatomical regions, including the hippocampus and medial temporal lobe, enhancing interpretability and clinical plausibility. These findings indicate that hierarchical multimodal fusion with interpretable feature refinement offers a promising and extensible solution for reliable and explainable automated AD staging. Full article

This study proposes a framework, the RA_WLTE_River model, for quantifying the reliability of flood-altering water-level thresholds, considering rainfall and runoff-related uncertainties. The Keelung River in northern Taiwan is selected as the study area, and associated hydrological data from 2008 to 2016 are applied in the development and application of the model. According to the results from the model development and demonstration, the average and maximum rainfall intensities, roughness coefficients, and maximum tide depths exhibit a significant contribution to the reliability quantification of the estimated water-level thresholds. In addition, empirically based water-level thresholds can achieve the goal of rainfall-induced flood early warning, with a high likelihood of nearly 0.95. Additionally, the probabilistically based water-level thresholds derived from the described reliability can efficiently ensure consistent flood early warning performance at all control points along the river. Full article

Modifying proteins through grafting with polyphenols has received much attention recently due to its immense application potential. This stems from the formation of protein-polyphenol complexes, altering the structural and functional properties of the constituent molecules. In food systems, the interaction between proteins and polyphenols, including covalent and non-covalent binding, represents a green, simple, and effective strategy to transform difficult-to-process protein sources into high-value functional ingredients. In addition, the complexes formed can increase stability, biological activity, and bioavailability of polyphenols, thereby expanding their applications. Gaining insight into protein-polyphenol complexes is essential for developing novel complexes, formulations, and other applications utilizing protein and natural polyphenols. Thus, this review outlines the binding affinities and interaction mechanisms, explains factors affecting complex formation, revisits structural modulation of protein, modern processing technologies, and systematically discusses the synergistic bioactivities of the resulting complexes. We also discuss strategies to address the applications of protein–polyphenol complexes for developing functional food products with prolonged shelf life. These applications can be expanded to other industrial areas, such as pharmaceuticals and material engineering, contributing towards better nutritional quality, beneficial healthy aspects, and sustainability. Full article

Chronic diabetic wounds are characterized by persistent inflammation, impaired angiogenesis, oxidative stress, and defective tissue remodeling, leading to delayed healing. Cordyceps militaris, a medicinal fungus with known anti-inflammatory and antioxidant properties, has shown therapeutic potential in metabolic disorders; however, its role in diabetic wound repair remains unclear. In this study, we evaluated the wound-healing effects of an aqueous extract of C. militaris using in vitro keratinocyte models and a streptozotocin-induced diabetic mouse model. C. militaris treatment significantly accelerated wound closure, improved epidermal regeneration, and enhanced skin barrier integrity. Mechanistically, C. militaris restored HIF-1α and TGF-β1 expression, promoted cell proliferation and fibroblast activation, and increased the expression of matrix metalloproteinases MMP-1 and MMP-2, indicating enhanced extracellular matrix remodeling. In parallel, excessive inflammatory responses were attenuated, as evidenced by reduced IL-6 and TNF-α levels, along with activation of SIRT1/Nrf2/HO-1 antioxidant signaling pathways. Collectively, these findings demonstrate that C. militaris promotes a balanced wound-healing microenvironment and represents a promising natural therapeutic candidate for the treatment of diabetic wounds. Full article

Traditional automated monitoring systems adopted for Intersection Traffic Control still face challenges, including high costs, maintenance difficulties, insufficient coverage, poor multimodal data integration, and limited traffic information analysis. To address these issues, the study proposes a sovereign AI-driven Smart Transportation governance approach, developing a mobile AI solution equipped with multimodal perception, task decomposition, memory, reasoning, and multi-agent collaboration capabilities. The proposed system integrates computer vision, multi-object tracking, natural language processing, Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs) to construct a Pipeline-based Traffic Analysis System (PTAS). The PTAS can produce real-time statistics on pedestrian and vehicle flows at intersections, incorporating potential risk factors such as traffic accidents, construction activities, and weather conditions for multimodal data fusion analysis, thereby providing forward-looking traffic insights. Experimental results demonstrate that the enhanced DuCRG-YOLOv11n pre-trained model, equipped with our proposed new activation function $\beta silu$, can accurately identify various vehicle types in object detection, achieving a frame rate of 68.25 FPS and a precision of 91.4%. Combined with ByteTrack, it can track over 90% of vehicles in medium- to low-density traffic scenarios, obtaining a 0.719 in MOTA and a 0.08735 in MOTP. In traffic flow analysis, the RAG of Vertex AI, combined with Claude Sonnet 4 LLMs, provides a more comprehensive view, precisely interpreting the causes of peak-hour congestion and effectively compensating for missing data through contextual explanations. The proposed method can enhance the efficiency of urban traffic regulation and optimizes decision support in intelligent transportation systems. Full article

The deployment of Advanced Driver-Assistance Systems (ADAS) in economically constrained markets frequently relies on hardware architectures that lack dedicated graphics processing units. Within such environments, the integration of deep neural networks faces significant hurdles, primarily stemming from strict limitations on energy consumption, the absolute necessity for deterministic real-time response, and the rigorous demands of safety certification protocols. Meanwhile, traditional geometry-based lane detection pipelines continue to exhibit limited robustness under adverse illumination conditions, including intense backlighting, low-contrast nighttime scenes, and heavy rainfall. Motivated by these constraints, this work re-examines geometry-based lane perception from a sensor-level viewpoint and introduces a Binary Line Segment Filter (BLSF) that leverages the inherent structural regularity of lane markings in bird’s-eye-view (BEV) imagery within a computationally lightweight framework. The proposed BLSF is integrated into a complete pipeline consisting of inverse perspective mapping, median local thresholding, line-segment detection, and a simplified Hough-style sliding-window fitting scheme combined with RANSAC. Experiments on a self-collected dataset of 297 challenging frames show that the inclusion of BLSF significantly improves robustness over an ablated baseline while sustaining real-time performance on a 2 GHz ARM CPU-only platform. Additional evaluations on the Dazzling Light and Night subsets of the CULane and LLAMAS benchmarks further confirm consistent gains of approximately 6–7% in F₁-score, together with corresponding improvements in IoU. These results demonstrate that interpretable, geometry-driven lane feature extraction remains a practical and complementary alternative to lightweight learning-based approaches for cost- and safety-critical ADAS applications. Full article

Background and Objectives: Lung cancer in never-smokers (LCINS) has become a major global health concern, ranking as the fifth leading cause of cancer-related mortality. Unlike smoking-related lung cancer, LCINS arises from complex interactions between environmental carcinogens and distinct genomic alterations. This review summarizes current evidence on environmental risks, molecular features, and therapeutic progress shaping lung cancer management. Methods: A narrative review was conducted to examine risk factors for lung cancer in non-smokers. Studies reporting driver mutations in never-smokers and smokers were identified across major lung cancer histological subtypes, including small-cell lung cancer (SCLC), lung adenocarcinoma (LUAD), squamous cell carcinoma (SCC), and large-cell carcinoma (LCC). In addition, PubMed was searched for phase III trials and studies on targeted therapies related to driver mutations published between 2016 and 2025. Results: Environmental factors such as cooking oil fumes, radon, asbestos, arsenic, and fine particulate matter (PM_2.5) are strongly associated with LCINS through oxidative stress, DNA damage, and chronic inflammation. EGFR, PIK3CA, OS9, MET, and STK11 mutations are characteristic of never-smokers, in contrast to TP53 mutations, which are more common in smokers. Recent advances in targeted therapy and immunotherapy have improved survival and quality of life, emphasizing the importance of molecular profiling for treatment selection. Conclusions: LCINS represents a distinct clinical and molecular entity shaped by complex interactions between environmental exposures and genetic susceptibility. Genetic alterations promote tumor immune evasion, facilitating cancer development and progression. Continued advances in air quality control, molecular diagnostics, and precision therapies are essential for prevention, early detection, and reduction of the global disease burden. Full article

The increasing demand for sustainable, nutrient-dense plant-based foods has intensified interest in functional ingredients that enhance nutritional quality. This study developed plant-based patties by partially replacing texturized pea protein with chia seed powder (CSP; Salvia hispanica L.) and evaluated their quality during 20 days of refrigerated storage (4 °C) under nitrogen-flushed packaging. Six formulations (F1–F6) containing 0–25% CSP were evaluated for physicochemical properties, lipid oxidation, and nutritional composition. Based on an optimal balance of texture, cooking yield, antioxidant capacity, and nutritional enhancement, the formulation containing 20% CSP was selected for further analyses. Proximate analysis revealed significant increases in protein (18–21%), fat (9–12%), and ash (2–3%) contents, accompanied by a slight reduction in moisture. All formulations maintained a stable pH throughout storage. Lipid oxidation increased gradually from 0.10–0.17 to 0.89–1.10 mg MDA/kg over 20 days but remained within acceptable limits. Fatty acid profiling indicated enhanced polyunsaturated fatty acids, particularly omega-3 and omega-6. Amino acid analysis showed elevated levels of key amino acids, including glutamic acid, aspartic acid, arginine, leucine, and lysine. Overall, patties containing 20% CSP exhibited improved nutritional quality and satisfactory oxidative stability, highlighting CSP as a promising functional ingredient for plant-based meat alternatives. Full article

This paper proposes an optical three-dimensional (3D) point cloud acquisition and sketching system, which is not limited by the measurement size, unlike traditional 3D object measurement techniques. The system employs an optical displacement sensor for surface displacement scanning and a six-axis inertial sensor (accelerometer and gyroscope) for spatial attitude perception. A microprocessor control unit (MCU) is responsible for acquiring, merging, and calculating data from the sensors, converting it into 3D point clouds. Butterworth filtering and Mahoney complementary filtering are used for sensor signal preprocessing and calculation, respectively. Furthermore, a human–machine interface is designed to visualize the point cloud and display the scanning path and measurement trajectory in real time. Compared to existing works in the literature, this system has a simpler hardware architecture, more efficient algorithms, and better operation, inspection, and observation features. The experimental results show that the maximum measurement error on 2D planes is 4.7% with a root mean square (RMS) error of 2.1%, corresponding to the reference length of 10.3 cm. For 3D objects, the maximum measurement error is 5.3% with the RMS error of 2.4%, corresponding to the reference length of 9.3 cm. Finally, it was verified that this system can also be applied to large-sized 3D objects for outlines. Full article