Search Results (4,188)

Accurate real-time detection of hawthorn by vision systems is a fundamental prerequisite for automated harvesting. This study addresses the challenges in hawthorn orchards—including target overlap, leaf occlusion, and environmental variations—which lead to compromised detection accuracy, high computational resource demands, and poor real-time performance in existing methods. To overcome these limitations, we propose YOLO-DCL (group shuffling convolution and coordinate attention integrated with a lightweight head based on YOLOv8n), a novel lightweight hawthorn detection model. The backbone network employs dynamic group shuffling convolution (DGCST) for efficient and effective feature extraction. Within the neck network, coordinate attention (CA) is integrated into the feature pyramid network (FPN), forming an enhanced multi-scale feature pyramid network (HSPFN); this integration further optimizes the C2f structure. The detection head is designed utilizing shared convolution and batch normalization to streamline computation. Additionally, the PIoUv2 (powerful intersection over union version 2) loss function is introduced to significantly reduce model complexity. Experimental validation demonstrates that YOLO-DCL achieves a precision of 91.6%, recall of 90.1%, and mean average precision (mAP) of 95.6%, while simultaneously reducing the model size to 2.46 MB with only 1.2 million parameters and 4.8 GFLOPs computational cost. To rigorously assess real-world applicability, we developed and deployed a detection system based on the PySide6 framework on an NVIDIA Jetson Xavier NX edge device. Field testing validated the model’s robustness, high accuracy, and real-time performance, confirming its suitability for integration into harvesting robots operating in practical orchard environments. Full article

Traditional nutritional diagnosis suffers from inefficiency, high cost, and damage when predicting the nitrogen, phosphorus, and potassium content of sugarcane leaves. Non-destructive nutritional diagnosis of sugarcane leaves based on traditional machine learning and deep learning suffers from poor generalization and lower accuracy. To address these issues, this study proposes a novel convolutional neural network called WT-ResNet. This model incorporates wavelet transform into the residual network structure, enabling effective feature extraction from sugarcane leaf images and facilitating the regression prediction of nitrogen, phosphorus, and potassium content in the leaves. By employing a cascade of decomposition and reconstruction, the wavelet transform extracts multi-scale features, which allows for the capture of different frequency components in images. Through the use of shortcut connections, residual structures facilitate the learning of identity mappings within the model. The results show that by analyzing sugarcane leaf images, our model achieves R² values of 0.9420 for nitrogen content prediction, 0.9084 for phosphorus content prediction, and 0.8235 for potassium content prediction. The accuracy rate for nitrogen prediction reaches 88.24% within a 0.5 tolerance, 58.82% for phosphorus prediction within a 0.1 tolerance, and 70.59% for potassium prediction within a 0.5 tolerance. Compared to other algorithms, WT-ResNet demonstrates higher accuracy. This study aims to provide algorithms for non-destructive sugarcane nutritional diagnosis and technical support for precise sugarcane fertilization. Full article

The male flower of the maize plant, known as the tassel, is a strong indicator of the growth, development, and reproductive stages of maize crops. Monitoring maize tassels under natural conditions is significant for maize breeding, management, and yield estimation. Unmanned aerial vehicle (UAV) remote sensing combined with deep learning-based semantic segmentation offers a novel approach for monitoring maize tassel phenotypic traits. The morphological and size variations in maize tassels, together with numerous similar interference factors in the farmland environment (such as leaf veins, female ears, etc.), pose significant challenges to the accurate segmentation of tassels. To address these challenges, we propose DECC-Net, a novel segmentation model designed to accurately extract maize tassels from complex farmland environments. DECC-Net integrates the Dynamic Kernel Feature Extraction (DKE) module to comprehensively capture semantic features of tassels, along with the Lightweight Channel Cross Transformer (LCCT) and Adaptive Feature Channel Enhancement (AFE) modules to guide effective fusion of multi-stage encoder features while mitigating semantic gaps. Experimental results demonstrate that DECC-Net achieves advanced performance, with IoU and Dice scores of 83.3% and 90.9%, respectively, outperforming existing segmentation models while exhibiting robust generalization across diverse scenarios. This work provides valuable insights for maize varietal selection, yield estimation, and field management operations. Full article

Leaves of Gentiana lutea L., traditionally used for treating heart disorders, represent a sustainable and underutilized source of bitter secoiridoids and xanthones, also found in Gentianae radix—an official herbal drug derived from the same, protected species. As root harvesting leads to the destruction of the plant, using the more readily available leaves could help reduce the pressure on this endangered natural resource. This study aimed to optimize the ultrasound-assisted extraction of the secoiridoid swertiamarin and the xanthone isogentisin from G. lutea leaves using response surface methodology (RSM). Subsequently, the stability of the bioactive compounds (swertiamarin, gentiopicrin, mangiferin, isoorientin, isovitexin, and isogentisin) in the optimized extract was monitored over a 30-day period under different storage conditions. The influence of extraction time (5–65 min), ethanol concentration (10–90% v/v), liquid-to-solid ratio (10–50 mL/g), and temperature (20–80 °C) was analyzed at five levels according to a central composite design. The calculated optimal extraction conditions for the simultaneous maximization of swertiamarin and isogentisin yields were 50 min extraction time, 30% v/v ethanol concentration, 30 mL/g liquid-to-solid ratio, and 62.7 °C extraction temperature. Under these conditions, the experimentally obtained yields were 3.75 mg/g dry weight for swertiamarin and 1.57 mg/g dry weight for isogentisin, closely matching the RSM model predictions. The stability study revealed that low-temperature storage preserved major bioactive compounds, whereas mangiferin stability was compromised by elevated temperature and light exposure. The established models support the production of standardized G. lutea leaf extracts and may facilitate the efficient separation and purification of their bioactive compounds, thereby contributing to the further valorization of this valuable plant material. Full article

Accurate segmentation of pear leaf diseases is paramount for enhancing diagnostic precision and optimizing agricultural disease management. However, variations in disease color, texture, and morphology, coupled with changes in lighting conditions and gradual disease progression, pose significant challenges. To address these issues, we propose EBMA-Net, an edge-aware multi-scale network. EBMA-Net introduces a Multi-Dimensional Joint Attention Module (MDJA) that leverages atrous convolutions to capture lesion information at different scales, enhancing the model’s receptive field and multi-scale processing capabilities. An Edge Feature Extraction Branch (EFFB) is also designed to extract and integrate edge features, guiding the network’s focus toward edge information and reducing information redundancy. Experiments on a self-constructed pear leaf disease dataset demonstrate that EBMA-Net achieves a Mean Intersection over Union (MIoU) of 86.25%, Mean Pixel Accuracy (MPA) of 91.68%, and Dice coefficient of 92.43%, significantly outperforming comparison models. These results highlight EBMA-Net’s effectiveness in precise pear leaf disease segmentation under complex conditions. Full article

Objectives: This study analyzed the antiproliferative potential of Eugenia uniflora L. leaf extracts against cervical cancer and non-cancerous cell lines. Methods: The extracts were prepared by maceration using hexane (EUH), dichloromethane (EUD), and ethyl acetate (EUA). Their cytotoxic potential was evaluated through MTT assays, wound healing assays, and flow cytometry. To identify classes of secondary metabolites, total phenolic and flavonoid contents were quantified using spectrophotometric methods, and individual metabolites were tentatively identified by LC-MS/MS. Results: EUH, EUD. and EUA exhibited cytotoxicity in HeLa cells, with IC₅₀ values of 63.03 μg/mL, 33.79 μg/mL, and 38.38 μg/mL, respectively. Due to their lower IC₅₀ values, the EUD and EUA fractions were selected for further investigation. EUA and EUD inhibited cell migration at all the time points tested and altered the cell cycle. Twenty-eight compounds were tentatively identified in E. uniflora L. leaf extracts based on the interpretation of their fragmentation patterns and molecular formulas obtained from mass spectrometry. Conclusions: The EUD and EUA extracts appear to modulate the metabolism of cervical cancer cells, leading to cell cycle arrest and inhibition of cell migration. Flavonoids and other phenolic compounds are likely responsible for these observed biological effects. Full article

Leaf Area Index (LAI) is a critical biophysical parameter for characterizing vegetation canopy structure and function. However, fine-scale LAI estimation remains challenging due to limitations in spatial resolution and structural detail in traditional remote sensing data and the insufficiency of single-index models like the LiDAR Penetration Index (LPI) in capturing canopy complexity. This study proposes a multi-scale LAI estimation approach integrating high-density UAV-based LiDAR data with LPI and point cloud texture features. A total of 40 field-sampled plots were used to develop and validate the model. LPI was computed at three spatial scales (5 m, 10 m, and 15 m) and corrected using a scale-specific adjustment coefficient (μ). Texture features including roughness and curvature were extracted and combined with LPI in a multiple linear regression model. Results showed that μ = 15 provided the optimal LPI correction, with the 10 m scale yielding the best model performance (R² = 0.40, RMSE = 0.35). Incorporating texture features moderately improved estimation accuracy (R² = 0.49, RMSE = 0.32). The findings confirm that integrating structural metrics enhances LAI prediction and that spatial scale selection is crucial, with 10 m identified as optimal for this study area. This method offers a practical and scalable solution for improving LAI retrieval using UAV-based LiDAR in heterogeneous forest environments. Full article

Wild blackberry (Rubus ulmifolius Schott) is a culinary and medicinal plant traditionally used to treat various ailments, including hypertension. This study evaluated the vasorelaxant effects of five crude leaf extracts of R. ulmifolius (hexane, dichloromethane, ethyl acetate, methanol, and aqueous), as well as the hypotensive and antioxidant activities of its methanolic extract (MERu), and analyzed its phytochemical profile. Crude extracts, obtained using a Soxhlet apparatus, were tested in vitro on isolated rat aortic rings precontracted with phenylephrine. The hypotensive effect of MERu was examined in vivo in normotensive rats, and its antioxidant activity was assessed using the DPPH assay. Total phenolic and tannin contents were quantified by the Folin–Ciocalteu and hide powder methods, respectively, while UHPLC-MS was used to identify its phytochemicals. All crude extracts induced concentration-dependent vasorelaxation, with MERu showing the strongest effect (59.31% relaxation at 10⁻¹ g/L). Intravenous MERu induced significant blood pressure reductions in rats, starting at 1 mg/kg. At 20 mg/kg, systolic, diastolic, and mean arterial pressures dropped by 38.61%, 51.58%, and 45.19%, respectively. MERu also demonstrated potent antioxidant activity and was rich in polyphenols, particularly tannins. Sixteen compounds were identified, notably rubanthrone A, a galloyl-bis-HHDP glucose derivative, ellagic acid, and quercetin-3-O-β-D-glucuronide. These results suggest that R. ulmifolius may have therapeutic potential for hypertension and exhibits promising characteristics as a functional food. Full article

Moringa oleifera leaf (MOL) and their extracts have been demonstrated to possess hypoglycemic effects in a variety of species, but they are still unknown in dogs. This study examined the effects of Moringa oleifera leaf peptide (MOLP) on α-amylase and α-glucosidase activities. Furthermore, we assessed the impact of MOLP on the estimated glycemic index (eGI) of snacks in vitro and the postprandial glycemic response in dogs. The findings indicated that MOLP exhibited significant inhibitory activities against α-amylase (IC₅₀ = 2.29 ± 0.10 mg/mL) and α-glucosidase (IC₅₀ = 2.80 ± 0.04 mg/mL). Moreover, the MOLP-containing snacks exhibited a lower rate of starch hydrolysis during in vitro digestion, leading to a notable reduction in the eGI when compared to white bread (WB) and control snacks. Incorporating MOLP into snacks causes smoother alterations in postprandial blood glucose, significantly reducing glucose peak, time to peak, and glycemic index (GI). Our findings indicate that MOLP exhibits hypoglycemic potential, offering a scientific foundation for the future development of functional foods aimed at managing diabetes in dogs. Full article

This study explores the sustainable extraction and application of natural dyes from figs (Ficus carica) and Eucalyptus leaves using an aqueous alkaline medium. The dyeing process was optimized for cotton fabric using the exhaust-dyeing method. Fabrics dyed with Ficus carica extract and its blend with Eucalyptus exhibited enhanced color strength, excellent crocking fastness (rated 4–5), and good washing fastness (rated 3–4 on the gray scale). The use of Aloe barbadensis Miller as a bio-mordant significantly improved dye fixation, resulting in deeper, earthy shades, such as green, yellow–green, and yellowish brown. The highest K/S value (5.85) was recorded in samples treated with a mordant, sodium chloride (NaCl), and the combined dye extracts, indicating a synergistic effect among the components. Mosquito repellency tests revealed that treated fabrics exhibited up to 70% repellency, compared to just 20% in undyed samples. Antibacterial testing against E. coli showed that dyed fabrics achieved over 80% bacterial reduction after 24 h, indicating promising antimicrobial functionality. Air permeability slightly decreased post-dyeing due to the potential shrinkage in cotton fabrics. Furthermore, adsorption studies showed a removal efficiency of 57% for Ficus carica dye on graphene oxide (GO) under ultrasonication. These findings confirm the potential of GO as an effective adsorbent material for treating wastewater from natural textile dyes. Overall, the study highlights the environmental safety, functional performance, and multifunctional advantages of plant-based dyeing systems in sustainable textile applications. Full article

Seed priming is an innovative pre-planting technique to improve germination and accelerate early seedling growth, offering a sustainable and eco-friendly alternative to chemical treatments. In this study, silver nanoparticles (AgNPs) were synthesized using flower extracts of neem plants for the first time, alongside the conventional neem leaf extract-based AgNPs, and their comparative efficacy was evaluated in wheat seed priming. The biosynthesized AgNPs were characterized through UV–Vis spectroscopy, Fourier Transform Infrared Spectroscopy (FTIR), X-ray Diffraction (XRD), Field Emission Scanning Electron Microscopy (FESEM), Energy-Dispersive Spectroscopy (EDS), Dynamic Light Scattering (DLS), and zeta potential analysis to confirm their formation, stability, and surface functionality. Wheat seeds were primed with varying concentrations (25, 50, 75, 100 mg/L) of flower-mediated nanoparticles (F-AgNPs) and leaf-mediated nanoparticles (L-AgNPs). Effects on seed germination, seedling growth, plant pigments, secondary metabolites, and antioxidant enzyme activities were systematically investigated. The results indicated that F-AgNP priming treatment significantly enhanced wheat seedlings’ performances in comparison to L-AgNPs, which could be attributed to the difference in phytochemical profiles in the extracts. This study contributes a comparative experimental analysis highlighting the potential of biogenic AgNPs—particularly those derived from neem flower extract—offering a promising strategy for enhancing seedling establishment in wheat through seed priming. Full article

Early and accurate identification of maize diseases is crucial for ensuring sustainable agricultural development. However, existing maize disease identification models face challenges including high inter-class similarity, intra-class variability, and limited capability in identifying early-stage symptoms. To address these limitations, we proposed DSTANet (decomposed spatial token aggregation network), a lightweight and high-performance model for maize leaf disease identification. In this study, we constructed a comprehensive maize leaf image dataset comprising six common disease types and healthy samples, with early and late stages of northern leaf blight and eyespot specifically differentiated. DSTANet employed MobileViT as the backbone architecture, combining the advantages of CNNs for local feature extraction with transformers for global feature modeling. To enhance lesion localization and mitigate interference from complex field backgrounds, DSFM (decomposed spatial fusion module) was introduced. Additionally, the MSTA (multi-scale token aggregator) was designed to leverage hidden-layer feature channels more effectively, improving information flow and preventing gradient vanishing. Experimental results showed that DSTANet achieved an accuracy of 96.11%, precision of 96.17%, recall of 96.11%, and F1-score of 96.14%. With only 1.9M parameters, 0.6 GFLOPs (floating point operations), and an inference speed of 170 images per second, the model meets real-time deployment requirements on edge devices. This study provided a novel and practical approach for fine-grained and early-stage maize disease identification, offering technical support for smart agriculture and precision crop management. Full article

Crotalaria juncea L. (Fabaceae: Faboideae), traditionally used as green manure due to its nitrogen-fixing capacity, also exhibits therapeutic potential for conditions such as anemia and psoriasis. However, its cosmetic applications remain largely unexplored. This study examined the phytochemical profiles and biological activities of ethanolic extracts from the root, flower, and leaf of C. juncea, focusing on their potential use in cosmetic formulations. Soxhlet extraction with 95% ethanol was employed. Among the extracts, the leaf showed the highest total flavonoid content, while the root contained the highest total phenolic content. The root extract demonstrated the strongest antioxidant activity, as assessed by DPPH, FRAP, and lipid peroxidation assays, along with significant anti-tyrosinase and anti-aging effects via collagenase and elastase inhibition. LC-MS/QTOF analysis identified genistein and kaempferol as the major bioactive constituents in the root extract. Molecular docking confirmed their strong interactions with enzymes associated with skin aging. Additionally, the root extract exhibited notable anti-inflammatory activity. These results suggest that C. juncea root extract is a promising multifunctional natural ingredient for cosmetic applications due to its antioxidant, anti-tyrosinase, anti-aging, and anti-inflammatory properties. Full article

Recurrent vulvovaginal candidiasis (RVVC), predominantly caused by Candida albicans, represents a global health issue, particularly in developing regions. This study explores the antifungal potential of aqueous leaf extract of Schinus weinmanniifolia Mart. ex Engl., a native Latin American plant. The extract was evaluated for phytochemical composition, antifungal efficacy, and safety profile. Phytochemical analyses identified six major compounds, including shikimic acid, gallic acid, and methyl gallate, with antioxidant and antimicrobial properties. The extract showed potent antioxidant activity, with IC₅₀ values between 1.52–5.51 µg/mL. It strongly inhibited C. albicans, with a minimum inhibitory concentration (MIC) of 1.95 µg/mL, and was active against other yeasts (MIC 0.48–62.5 µg/mL). The growth kinetics assay revealed reduced C. albicans viability after 12 h at 2 × MIC versus the positive control. Scanning electron microscopy confirmed reduced fungal counts without morphological damage. The extract impaired C. albicans virulence, reducing germ tube formation by 75.49% and hyphal transition by 84.34%, outperforming fluconazole. Biocompatibility assays showed it is non-hemolytic (IC₅₀ > 1000 µg/mL), non-mutagenic, and highly selective for fungal cells (SI = 512.82), suggesting minimal human cell toxicity. In conclusion, the extract combines strong antifungal activity and favorable safety, with cost-effective preparation suitable for traditional medicine in resource-limited regions. Full article

Background/Objectives: High concentration of plasma low-density lipoprotein cholesterol (LDL-C) is the predominant cause of atherosclerotic cardiovascular disease progression and coronary heart disease. Nutraceutical combination together with a cholesterol-lowering action provides an alternative to pharmacotherapy in patients reporting intolerance to statins and in subjects with low cardiovascular risk. The effects on lipid parameters were evaluated over 6 months for a food supplement containing aqueous extract of Berberis aristata and Olea europea, fenugreek seed extract, water/ethanol extract of artichoke leaf and phytosterols from sunflower seeds (Ritmon Colesystem^®). Methods: Laboratory data were obtained at baseline from 44 otherwise healthy subjects (33 males, mean 50 ± 11 years) without cardiovascular disease having LDL-C in the range 115 to 190 mg/dL pharmacologically untreated for hypercholesterolemia. Subjects were re-evaluated at 1, 3 and 6 months during which they took one tablet of Ritmon Colesystem^® after dinner. Results: At baseline, the mean values were 151 ± 21 mg/dL for LDL-C, 223 ± 24 mg/dL for total cholesterol (T-C), 52 ± 14 mg/dL for high-density lipoprotein cholesterol (HDL-C), and 124 ± 58 mg/dL for triglycerides. A significant reduction in LDL-C was observed; 9 mg/dL (95% confidence interval 3–14), 10 (4–17) and 7 (1–14) at 1, 3 and 6 months. A similar significant trend was detected for T-C while triglycerides did not show significant changes and HDL-C had lower values only at 3 months. Conclusions: These nutraceuticals in individuals with sub-optimal blood cholesterol levels at intermediate–low cardiovascular risk reduced LDL-C and T-C over 6 months contributing to the improvement of cholesterol control by dietary supplements. Full article