Search Results (4,682)

Defect detection in textile manufacturing is critically hampered by the inefficiency of manual inspection and the dual constraints of deep learning (DL) approaches. Specifically, DL models suffer from poor generalization, as the rapid iteration of fabric types makes acquiring sufficient training data impractical. Furthermore, their high computational costs impede real-time industrial deployment. To address these challenges, this paper proposes a texture-adaptive fabric defect detection method. Our approach begins with a Dynamic Subspace Feature Extraction (DSFE) technique to extract spatial luminance features of the fabric. Subsequently, a Light Field Offset-Aware Reconstruction Model (LFOA) is introduced to reconstruct the luminance distribution, effectively compensating for environmental lighting variations. Finally, we develop a texture-adaptive defect detection system to identify potential defective regions, alongside a probabilistic ‘OutlierIndex’ to quantify their likelihood of being true defects. This system is engineered to rapidly adapt to new fabric types with a small number of labeled samples, demonstrating strong generalization and suitability for dynamic industrial conditions. Experimental validation confirms that our method achieves 70.74% accuracy, decisively outperforming existing models by over 30%. Full article

Modern research laboratories are constantly evolving to meet the growing demands for precision, quality, and flexibility in scientific work. The modernization of existing experimental test benches plays a crucial role in improving efficiency, optimizing processes, and ensuring operational safety. This requires updates to their design, experimental methods, data collection, and results recording—all of which provide the foundation for developing new research concepts. An increasing number of innovations are now guided by the principle of minimizing environmental impact. In line with this approach, an innovative modernization of a tube furnace research station was carried out, based on the concepts of sustainable development and the zero-waste philosophy. To enable thermogravimetric analyses of coffee waste, a previously incomplete tube furnace was refurbished using recycled components. The primary objective was to expand the research capabilities of the existing workstation. As part of the modernization, three indicators of reuse efficiency were calculated: the quantitative indicator W_re-use, the mass indicator $W_{re\text{-}use}^{mass}$, and the cost indicator $W_{re\text{-}use}^{value}$. A quantitative index of 78% and a mass index of approximately 76% were achieved, while the economic value of the recovered components accounted for 11% of the total value of the revitalized research station. This strategy significantly reduced waste generation, carbon dioxide emissions, and the consumption of primary raw materials. Full article

The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement Learning (DRL) agents trained using data from digital twins (DTs) to optimize energy consumption in real time, (2) Physics-Informed Neural Networks (PINNs) to seamlessly embed physical laws within the optimization process, ensuring model accuracy and interpretability, and (3) blockchain (BC) technology to facilitate secure and transparent communication across the smart grid infrastructure. The model was trained and validated using comprehensive datasets, including smart meter energy consumption data, renewable energy outputs, dynamic pricing, and user preferences collected from IoT devices. The proposed framework achieved superior predictive performance with a Mean Absolute Error (MAE) of 0.237 kWh, Root Mean Square Error (RMSE) of 0.298 kWh, and an R-squared (R²) value of 0.978, indicating a 97.8% explanation of data variance. Classification metrics further demonstrated the model’s robustness, achieving 97.7% accuracy, 97.8% precision, 97.6% recall, and an F1 Score of 97.7%. Comparative analysis with traditional models like Linear Regression, Random Forest, SVM, LSTM, and XGBoost revealed the superior accuracy and real-time adaptability of the proposed method. In addition to enhancing energy efficiency, the model reduced energy costs by 35%, maintained a 96% user comfort index, and increased renewable energy utilization to 40%. This study demonstrates the transformative potential of integrating PINNs, DT, and blockchain technologies to optimize energy consumption in smart grids, paving the way for sustainable, secure, and efficient energy management systems. Full article

Background and Objectives: Albuminuria is a key clinical marker for early detection of diabetic kidney disease (DKD) in individuals with type 2 diabetes mellitus (T2DM). The triglyceride-glucose (TyG) index, a simple surrogate of insulin resistance, has been increasingly investigated for its potential association with renal complications. This study aimed to evaluate the relationship between the TyG index and albuminuria in patients with T2DM and assess its clinical utility as an accessible metabolic marker reflecting early renal involvement. Materials and Methods: This retrospective cross-sectional study included 570 adult patients with confirmed T2DM who were followed at a tertiary internal medicine outpatient clinic between January and December 2024. Participants were classified as albuminuric or non-albuminuric based on spot urine albumin-to-creatinine ratio (ACR) values. Clinical and biochemical parameters were collected from medical records, and the TyG index was calculated as ln [fasting triglyceride (mg/dL) × fasting glucose (mg/dL)/2]. Logistic regression models were used to identify independent factors associated with albuminuria. ROC analysis was performed to evaluate the discriminatory accuracy of the TyG index. Results: The median TyG index was significantly higher in the albuminuric group compared to the non-albuminuric group (10.0 vs. 9.1; p < 0.001) and increased progressively with albuminuria severity (p < 0.001). In multivariate logistic regression analysis, elevated TyG index, hyperlipidemia, and reduced estimated glomerular filtration rate were independently associated with albuminuria. When evaluated as a continuous variable, the TyG index showed strong discriminatory ability (area under curve (AUC) = 0.949; 95% confidence interval (CI): 0.933–0.964). Using the optimal cut-off threshold of 9.6, the TyG index maintained high diagnostic performance (AUC = 0.870; 95% CI: 0.839–0.902; sensitivity 87.7%, specificity 86.3%). Subgroup analyses confirmed the robustness of this association across clinical and demographic variables. Conclusions: In this study, higher TyG index values were significantly associated with the presence and severity of albuminuria in individuals with T2DM. While causality cannot be inferred, the findings suggest that the TyG index may serve as a practical, cost-effective tool for identifying patients at increased risk for early diabetic kidney involvement. Prospective longitudinal studies are needed to confirm its predictive value and clinical applicability. Full article

The integration of unmanned aerial vehicles (UAVs) and deep learning (DL) has significantly advanced crop disease detection by enabling scalable, high-resolution, and near real-time monitoring within precision agriculture. This systematic review analyzes peer-reviewed literature indexed in the Web of Science Core Collection as articles or proceeding papers through 2024. The main selection criterion was combining “unmanned aerial vehicle*” OR “UAV” OR “drone” with “deep learning”, “agriculture” and “leaf disease” OR “crop disease”. Results show a marked surge in publications after 2019, with China, the United States, and India leading research contributions. Multirotor UAVs equipped with RGB sensors are predominantly used due to their affordability and spatial resolution, while hyperspectral imaging is gaining traction for its enhanced spectral diagnostic capability. Convolutional neural networks (CNNs), along with emerging transformer-based and hybrid models, demonstrate high detection performance, often achieving F1-scores above 95%. However, critical challenges persist, including limited annotated datasets for rare diseases, high computational costs of hyperspectral data processing, and the absence of standardized evaluation frameworks. Addressing these issues will require the development of lightweight DL architectures optimized for edge computing, improved multimodal data fusion techniques, and the creation of publicly available, annotated benchmark datasets. Advancements in these areas are vital for translating current research into practical, scalable solutions that support sustainable and data-driven agricultural practices worldwide. Full article

Background and Objectives: Hematological parameters are increasingly being investigated as readily accessible biomarkers for the diagnosis of obstructive sleep apnea syndrome (OSAS). In our study, we aimed to investigate the relationship between OSAS and albumin indices and the uric acid-to-HDL ratio (UHR). Methods: The demographic and laboratory data and AHI (apnea–hypopnea index) values of 613 patients who underwent polysomnography were obtained retrospectively from their files. Blood parameters such as white blood cells (WBCs), red blood cell distribution width (RDW), red blood cells (RBCs), hemoglobin (Hb), hematocrit (Hct), platelets (PLTs), C-reactive protein (CRP), albumin, blood urea nitrogen (BUN), and high-density lipoproteins (HDLs) were obtained from the files. Laboratory indices such as the BUN-to-albumin ratio (BAR), neutrophil-to-albumin ratio (NAR), RDW-to-albumin ratio (RAR), CRP-to-albumin ratio (CAR), and UHR were calculated. OSAS was categorized as simple snoring (SS) (control) (AHI < 5), mild (5 ≤ AHI < 15), moderate (15 ≤ AHI < 30), and severe (AHI ≥ 30). The patients were also grouped as severe (AHI ≥ 30) and non-severe (5 > AHI < 30) OSAS and compared in terms of laboratory parameters and indices. Results: Of the 613 participants, 366 (59.7%) were men, and the average age of participants was 55.22 ± 11.13 years. The biomarkers such as RBCs, Hb, Htc, CRP, BUN, creatinine, uric acid, HDLs, CAR, RAR, BAR, and UHR showed significant differences between OSAS patients and controls. WBCs, basophils, RBCs, RDW, Htc, PLTs, HDLs, uric acid, RAR, NAR, and UHR indices were significantly different between the severe OSAS and non-severe OSAS groups (p < 0.05). BAR (OR = 1.151; CI = 1.056 − 1.256; p = 0.001) and UHR (OR = 2.257; 95% CI = 1.507 − 3.382; p < 0.001) were the most important indices predicting OSAS, while RAR (OR = 1.844; CI = 1.224 − 2.778; p = 0.003) and UHR (OR = 2.203; 95% CI = 1.496 − 3.243; p < 0.001) were the strongest indices associated with severe OSAS. Conclusion: In our study, RAR, BAR, and UHR indices were closely associated with the presence and severity of OSAS. These indices can be considered low-cost, readily available methods for predicting OSAS patients. Full article

This study explores the potential of Digital Earth Africa (DE Africa) coastlines products for assessing the Coastal Vulnerability Index (CVI) along the Casablanca coastline, Morocco. The analysis integrates remotely sensed shoreline data with elevation, slope, and geomorphological information from ASTER GDEM and geological maps within a GIS environment. Shoreline change metrics, including Shoreline Change Envelope (SCE), Net Shoreline Movement (NSM), Linear Regression Rate (LRR), and End Point Rate (EPR), were used to evaluate erosion trends from 2000 to 2023. Results show that sandy beach areas, particularly those below 12 m elevation, are highly exposed to erosion (up to 1.5 m/yr) and vulnerable to coastal hazards. Approximately 44% and 23% of the study area were classified as having very high and high vulnerability, respectively. The results indicate that remotely sensed data and GIS techniques are valuable and cost-effective tools for multi-scale geo-hazard coastal assessment studies. The study demonstrates that DE Africa products, combined with local landscape data, provide a valuable tool for coastal vulnerability assessment and monitoring in Africa. Full article

Currently, the customs inspection of wood-boring pests in timber still primarily relies on manual visual inspection, which involves observing insect holes on the timber surface and splitting the timber for confirmation. However, this method has significant drawbacks such as long detection time, high labor cost, and accuracy relying on human experience, making it difficult to meet the practical needs of efficient and intelligent customs quarantine. To address this issue, this paper develops a rapid identification system based on the peristaltic signals of wood-boring pests through the PyQt framework. The system employs a deep learning model with multi-attention mechanisms, namely the Residual Denoising Vision Network (RDVNet). Firstly, a LabVIEW-based hardware–software system is used to collect pest peristaltic signals in an environment free of vibration interference. Subsequently, the original signals are clipped, converted to audio format, and mixed with external noise. Then signal features are extracted through three cepstral feature extraction methods Mel-Frequency Cepstral Coefficients (MFCC), Power-Normalized Cepstral Coefficients (PNCC), and RelAtive SpecTrAl-Perceptual Linear Prediction (RASTA-PLP) and input into the model. In the experimental stage, this paper compares the denoising module of RDVNet (de-RDVNet) with four classic denoising models under five noise intensity conditions. Finally, it evaluates the performance of RDVNet and four other noise reduction classification models in classification tasks. The results show that PNCC has the most comprehensive feature extraction capability. When PNCC is used as the model input, de-RDVNet achieves an average peak signal-to-noise ratio (PSNR) of 29.8 and a Structural Similarity Index Measure (SSIM) of 0.820 in denoising experiments, both being the best among the comparative models. In classification experiments, RDVNet has an average F1 score of 0.878 and an accuracy of 92.8%, demonstrating the most excellent performance. Overall, the application of this system in customs timber quarantine can effectively improve detection efficiency and reduce labor costs and has significant practical value and promotion prospects. Full article

This study explored the feasibility of utilizing tunnel muck-derived recycled granite aggregates (RGAs) in surface-layer asphalt mixtures via hybrid with basalt aggregates. Firstly, RGAs, including coarse aggregates (RGCAs) and fine aggregates (RGFAs), were prepared using a production method integrated with multi-cleaning technology. Then, the material properties of RGAs and RGA–basalt hybrid aggregates with varying RGA volume proportions were investigated. Finally, asphalt mixtures with these hybrid aggregates were designed and their engineering performance was evaluated. Basalt aggregates and their corresponding asphalt mixture served as the control group. Results suggest that since RGAs are rich in quartz and their SiO₂ content is as high as 70.88%, they are acidic aggregates. Employing multi-cleaning technology is a guaranteed method of obtaining RGAs with low mud content. The main conventional technical indexes of RGAs and all hybrid aggregates with 40–70% RGA volume proportions meet the requirements of Chinese technical specifications. Asphalt mixtures incorporating RGAs exhibit slightly higher voids in the mineral aggregates (VMAs) than the control group, indicating that RGAs modify the interlocking skeleton and contact states of aggregates. Blending RGAs with basalt to form hybrid aggregates is an effective way to achieve full-gradation utilization of tunnel muck-derived RGAs in the surface-layer asphalt mixtures. Without additional enhancement measures, a 40% RGA volume proportion in hybrid aggregates is recommended. For a higher RGA recycling rate, combining RGAs with cement is advised, maintaining 70% RGA volume proportion and 50% cement content of total filler volume. When external basalt aggregates are transported over a distance of 50–200 km, applying these schemes to local asphalt pavement surface layers can achieve at least 26.56% aggregate cost savings. Full article

Crude oil and grain, as two pivotal global commodities, exhibit significant price co-movement that profoundly affects national economic stability and food security. From the perspective of systems theory, the energy and grain markets do not exist in isolation but rather form a highly coupled complex system, characterized by nonlinear feedback, cross-market risk contagion, and cascading effects. This study systematically investigates the transmission mechanisms from international crude oil prices to the domestic prices of Chinese four major grains, employing the DY spillover index, Vector Error Correction Model (VECM), and a mediation effect framework. The empirical findings reveal three key insights. First, rising international crude oil prices significantly strengthen the pass-through of global grain prices to domestic markets, while simultaneously weakening the effectiveness of domestic price stabilization policies. Second, higher crude oil prices amplify international-to-domestic price spillovers by increasing maritime freight costs, a key channel in global grain trade logistics. Third, elevated oil prices stimulate demand for renewable biofuels, including biodiesel and ethanol, thereby boosting international demand for corn and soybeans and intensifying the transmission of price fluctuations in these commodities to the domestic market. These findings reveal the key pathways through which shocks in the energy market affect food security and highlight the necessity of studying the “energy–food” coupling mechanism within a systems framework, enabling a more comprehensive understanding of cross-market risk transmission. Full article

The diameter of basalt fiber influences the reinforcement of basalt fiber asphalt mixtures. However, the performance evaluation and mechanistic analysis of asphalt mixtures reinforced with varying fiber diameters have been insufficiently studied. AC-13 asphalt mixtures were designed and prepared with four different fiber diameters 7 μm, 16 μm, 25 μm, and an equal-mass mixture of these. The reinforcement mechanisms were analyzed using the equal cross-section theory. Results indicate that the incorporation of 7 μm and mixed-diameter basalt fibers significantly enhances the pavement performance of the asphalt mixtures compared to the control group without fibers. Additionally, it is shown by triaxial shear tests that the cohesion of the asphalt mixtures with the aforementioned two diameters of basalt fibers is strengthened by 61.5% and 55.5%, respectively. The dynamic modulus values in the high-frequency range are found to be positively correlated with fiber diameters. Since the fiber mass content and modulus were held constant, a decrease in diameter was observed to lead to an increase in fiber quantity. This is manifested by a multiple-fold increase in the total transformed cross-section (TTC_R) index for 7 μm fiber asphalt mixtures, as described by the equal cross-section theory. It is concluded that the performance improvement of the asphalt mixtures can be further enhanced under the same fiber content and cost conditions by optimizing diameter parameters. Full article

Non-communicable diseases (NCDs) are the leading global cause of death, causing over 43 million deaths in 2021, including 18 million premature deaths, disproportionately affecting low- and middle-income countries. NCDs also incur significant economic losses, estimated at USD 7 trillion from 2011 to 2025, despite low prevention costs. This study evaluated body mapping indicators: body mass index (BMI), waist circumference, and waist-to-hip ratio—for predicting NCD risk, including hypertension, diabetes, and cardiovascular diseases, using data from a nationally representative survey in Ghana. The study sampled 5775 participants via multistage stratified sampling, ensuring proportional representation by region, urban/rural residency, age, and gender. Ethical approval and informed consent were obtained. Anthropometric and biochemical data, including height, weight, waist and hip circumferences, blood pressure, fasting glucose, and lipid profiles, were collected using standardized protocols. Data analysis was conducted with STATA 17.0, accounting for complex survey design. Significant sex-based differences were observed: men were taller and lighter, while women had higher BMI and waist/hip circumferences. NCD prevalence increased with age, peaking at 60–69 years, and was higher in females. Lower education and marital status (widowed, divorced, separated) correlated with higher NCD prevalence. Obesity and high waist circumference strongly predicted NCD risk, but individual anthropometric measures lacked screening accuracy. Integrated screening and tailored interventions are recommended for improved NCD detection and management in resource-limited settings. Full article

This paper introduces the Gesture-Based Physical Stability Classification and Rehabilitation System (GPSCRS), a low-cost, non-invasive solution for evaluating physical stability using an Arduino microcontroller and the DFRobot Gesture and Touch sensor. The system quantifies movement smoothness, consistency, and speed by analyzing “up” and “down” hand gestures over a fixed period, generating a Physical Stability Index (PSI) as a single metric to represent an individual’s stability. The system focuses on a temporal analysis of gesture patterns while incorporating placeholders for speed scores to demonstrate its potential for a comprehensive stability assessment. The performance of various machine learning and deep learning models for gesture-based classification is evaluated, with neural network architectures such as Transformer, CNN, and KAN achieving perfect scores in recall, accuracy, precision, and F1-score. Traditional machine learning models such as XGBoost show strong results, offering a balance between computational efficiency and accuracy. The choice of model depends on specific application requirements, including real-time constraints and available resources. The preliminary experimental results indicate that the proposed GPSCRS can effectively detect changes in stability under real-time conditions, highlighting its potential for use in remote health monitoring, fall prevention, and rehabilitation scenarios. By providing a quantitative measure of stability, the system enables early risk identification and supports tailored interventions for improved mobility and quality of life. Full article

To address the limitations of traditional cotton leaf nitrogen content estimation methods, which include low efficiency, high cost, poor portability, and challenges in vegetation index acquisition owing to environmental interference, this study focused on emerging non-destructive nutrient estimation technologies. This study proposed an innovative method that integrates multi-color space fusion with deep and machine learning to estimate cotton leaf nitrogen content using smartphone-captured digital images. A dataset comprising smartphone-acquired cotton leaf images was processed through threshold segmentation and preprocessing, then converted into RGB, HSV, and Lab color spaces. The models were developed using deep-learning architectures including AlexNet, VGGNet-11, and ResNet-50. The conclusions of this study are as follows: (1) The optimal single-color-space nitrogen estimation model achieved a validation set R² of 0.776. (2) Feature-level fusion by concatenation of multidimensional feature vectors extracted from three color spaces using the optimal model, combined with an attention learning mechanism, improved the validation R² to 0.827. (3) Decision-level fusion by concatenating nitrogen estimation values from optimal models of different color spaces into a multi-source decision dataset, followed by machine learning regression modeling, increased the final validation R² to 0.830. The dual fusion method effectively enabled rapid and accurate nitrogen estimation in cotton crops using smartphone images, achieving an accuracy 5–7% higher than that of single-color-space models. The proposed method provides scientific support for efficient cotton production and promotes sustainable development in the cotton industry. Full article

Schizopygopsis younghusbandi is an endemic and ecologically important fish species on the Tibetan Plateau. However, its dietary carbohydrate requirement remains unexplored, limiting the development of cost-effective and physiological-friendly artificial feed. This study investigated the effects of different dietary carbohydrate levels on the growth performance, antioxidant capacity, and hepatointestinal morphology of S.younghusbandi. Six experimental diets were formulated with graded carbohydrate levels of 9% (C9), 12% (C12), 15% (C15), 18% (C18), 21% (C21), and 24% (C24). A total of 720 fish (initial weight 37.49 ± 0.25 g) were randomly allocated to six groups in quadruplicate (30 fish per replicate) and reared in tanks (0.6 m × 0.5 m × 0.4 m) for 8 weeks. Results demonstrated that the diet in the C12 group significantly improved weight gain rate (WGR), specific growth rate (SGR), and feed conversion ratio (FCR) (p < 0.05). Regression fitting analysis on growth performance indicated that the optimal carbohydrate level ranged from 10.42% to 10.49%. Additionally, the C12 group exhibited enhanced total superoxide dismutase (T-SOD) activities and reduced malondialdehyde (MDA) content in the liver, along with reduced interleukin-1β (IL-1β) levels in the serum (p < 0.05). Histological analysis revealed superior hepatointestinal integrity in the C12 group, characterized by lower hepatic lipid droplet accumulation, reduced vacuolation, decreased hepatosomatic index (HSI) (p < 0.05), as well as higher intestinal villus height and muscle thickness (p < 0.05). In conclusion, the C12 group optimally enhanced the growth, antioxidant response, and hepatointestinal health of S. younghusbandi, indicating that the suitable dietary carbohydrate level for this species is 12%. Full article