Search Results (4,693)

Non-destructive and automated detection of bacterial contamination is a critical prerequisite for ensuring high efficiency production and quality control in plant tissue culture. In this study, we developed a multispectral image acquisition system for Alocasia explants and proposed a novel image fusion model, termed Intensity-Texture enhanced Swin Fusion (ITSF). The ITSF framework employs convolutional neural networks to extract texture and intensity features from visible and near-infrared channels. Subsequently, a Swin Transformer-based module is integrated to model long-range spatial dependencies, ensuring cross-domain integration between the texture and intensity features. We formulated a composite loss function to guide the fusion process toward optimal results. This objective function integrates texture loss, entropy weighted structural similarity index (SSIM) and intensity aware dynamic gain guided loss. Experimental results demonstrate that the proposed method significantly enhances the visual saliency of bacteria and achieves superior quantitative performance across a comprehensive range of objective image fusion metrics. The detection performance reached a mean Average Precision (mAP50) of 0.949 with the fused images, satisfying industrial requirements for high-precision inspection, which provides a critical technical solution for the industrialization of automated micropropagation. Full article

Computed tomography (CT) enables non-destructive insight into internal log structure, yet fully automated interpretation of CT images remains limited by inconsistent annotations, boundary ambiguity, and insufficient spatial context in 2D slice-based analysis. These challenges restrict the industrial deployment of deep learning for wood quality assessment. This study applies artificial intelligence (AI) and deep learning to the automated analysis of computed tomography (CT) scans of wood logs for detecting internal qualitative features and segmenting bark. Using convolutional neural networks (CNNs), trained models accurately distinguish healthy and damaged regions and segment bark, including discontinuous parts. We introduce a novel pseudo-spatial representation by merging consecutive slices into red–green–blue (RGB) format, which improves prediction accuracy and model robustness across logs. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) highlights regions contributing most to defect detection, particularly knots. Comprehensive evaluation using Sørensen–Dice similarity coefficients and confusion matrices confirms the effectiveness of the proposed approach under industrial conditions. These findings demonstrate that AI-driven CT image analysis can address key limitations of current log-grading workflows and enable more reliable, objective, and scalable quality assessment for timber-dependent economies. Full article

Bothriochloa ischaemum is a key forage species with strong grazing tolerance and high nutritional value, making precise quantification of spike and seed traits essential for germplasm evaluation and yield prediction. However, the compact architecture and minute seed size in natural field conditions render manual counting inefficient and labor-intensive. To address this limitation, this study presents a non-destructive and automated quantification framework integrating advanced object detection and regression analysis for accurate in situ estimation of spikes and seed numbers. To further address the challenges of dense spike detection caused by occlusion and small object sizes, this study developed a modified model named YOLOv12-DAN by integrating DySample dynamic upsampling, ASFF feature fusion, and NWD loss, which achieved a mean average precision (mAP) of 91.6%. Meanwhile, for the detection of dense kernels on compact spikes, an improved YOLOv12 architecture incorporating an Explicit Visual Center (EVC) module was proposed to enhance multi-scale feature representation. The optimized model attained a bounding box precision of 96.5%, a recall rate of 86.4%, an mAP50 of 94.3%, and an mAP50-95 of 73.9%. Furthermore, a univariate linear regression model based on 132 spike samples verified the reliable consistency between the predicted and actual seed counts, with a mean absolute error (MAE) of 6.30, a mean absolute percentage error (MAPE) of 9.35, and an R-squared (R²) value of 0.808. Finally, the model was deployed through a lightweight end-to-end web application, enabling real-time field operation and promoting its applicability in breeding programs and agronomic decision-making. This study provides a robust technical pathway for automated phenotyping and precision forage improvement. Full article

Accurate quantification of cotton content is a key prerequisite for efficient textile recycling. However, it remains challenging due to material heterogeneity and technical limitations. Near-infrared spectroscopy (NIR) combined with advanced data analysis offers a rapid, non-destructive approach. However, systematic evaluations across instrument classes and analysis strategies for industrial textile sorting remain limited. In this study, a unique set of cotton/polyester blends from the same starting material with varying cotton content was analyzed using three NIR systems representing laboratory, handheld, and industrial sensor-based applications. Multiple spectral preprocessing strategies were systematically combined with partial least squares regression and advanced machine learning models. Model performance was evaluated using cross-validation and independent test sets. The benchtop NIR system delivered the highest and most consistent performance, achieving RMSEP values below 1.0% with advanced regression models. The handheld and imaging sensor system exhibited higher RMSEP values (1.2–1.6%), reflecting not only differences in preprocessing and model selection, but also intrinsic instrumental limitations. Overall, the results demonstrate that each NIR instrument class exhibits distinct strengths and limitations with respect to accuracy, sensitivity, and robustness. Consequently, instrument-specific preprocessing, models, and hyperparameters are required, and no universally transferable pipeline was identified. Full article

The concept of self-healing polymers has been prevalent over the last few decades. However, their performance and behaviour in structural applications in the form of layered composites have not been studied extensively. In this study, an attempt has been made to evaluate the recovery of the mechanical properties of Carbon Fibre-Reinforced Polymer composites (CFRPs) with an intrinsically healable polymeric resin system. Destructive tests, including static tensile, compression, and flexural tests, are carried out to evaluate their ability to recover mechanical compliance after healing. Nondestructive tests based on the Acousto-Ultrasonic (AU) approach are carried out to establish and distinguish the state of these composites. The results show that the tested self-healing CFRPs can recover their mechanical properties, particularly their flexural and compressive properties, after unstable matrix damage. On the other hand, the AU approach, supported by Machine Learning (ML) models, demonstrates that the damaged states and the heal states of these composites can be distinguished from the virgin state. Full article

Ultrasound propagation velocity was investigated as a non-destructive predictor of open porosity (${\rho }_0$) and water absorption ($A_w$) in volcanic rocks (two ignimbrites, a trachyte, and a basalt). Six velocity measurements were obtained under dry and saturated conditions along three orthogonal directions, and the dry Z-axis velocity was selected as the reference univariate predictor because it provided the highest explanatory power and the best cross-validated performance among the tested ultrasound variables. Four univariate regressions (linear, exponential, power law, and second-order polynomial), parametric multivariable linear regression, and five machine learning regressors were compared using lithology-stratified 5-fold cross-validation, grouping both ignimbrites as a single lithology. Univariate models showed moderate predictive capability for ${\rho }_0$ (cross-validated coefficient of determination $R^2\approx$ 0.506 to 0.580), whereas $A_w$ was captured more accurately, with the power law model reaching 0.923 ± 0.008. Multivariable linear regression improved ${\rho }_0$ when lithology was included (0.803 ± 0.084), while changes for $A_w$ were small. The highest accuracy was achieved by ensemble tree methods: extremely randomized trees with lithology yielded 0.949 ± 0.015 for ${\rho }_0$ (root mean square error 2.16 ± 0.38 percentage points), and Gradient Boosting with lithology yielded 0.976 ± 0.006 for $A_w$ (0.80 ± 0.12 percentage points). Full article

This study explores the structural safety, mechanical response and optimal construction parameters of the Horizontal Directional Drilling (HDD) technology applied in airport rigid pavements novelly for navigation lighting renovation. This study adopts a combined research method of three-dimensional finite element modeling (FEM) and field tests (full-scale 4C and 4E class airport runway sections). The reliability of the model is verified by the measured data using a Heavy Weight Deflectometer (HWD). The effects of drilling depth, drilling position and typical aircraft loads on the stress and deformation at the bottom of the pavement slab are systematically analyzed. Then, drilling, grouting and non-destructive testing are carried out in the field full-scale test section to investigate the change in pavement bearing capacities. The results show that minimized influence on the mechanical properties of the pavement can be achieved by using 15 cm drilling depths at either slab center or joints. The pavement stiffness slightly decreases by a maximum of 18.9% after drilling. According to the field grouting test, the Impulse Stiffness Modulus (ISM) of most measuring points can be recovered to the original level before drilling. The use of a 10 cm diameter HDD driller meets the structural safety requirements of airport pavements. The HDD technology induces minimized pavement damage and influence on the bearing capacity of the airport runway structure compared with traditional construction technologies, highlighting its advantages in airfield navigation lighting renovations. Full article

The 2022 Chongqing wildfires, occurring during an unprecedented heatwave, severely degraded subtropical forest ecosystems and disrupted hydrological cycling. We developed an integrated artificial intelligence framework combining Long Short-Term Memory and Transformer architectures to simulate post-fire evapotranspiration (ET) dynamics using 37 months of field observations (2022–2025) across 24 plots with four burn severities. The Penman–Monteith–Leuning model provided physically based benchmarks. Results revealed three distinct recovery phases: destruction/stagnation (0–7 months, ET at 6%–10% of pre-fire levels), rapid recovery (8–19 months), and stabilization (20–37 months, reaching 100% ET recovery). The coupled LSTM–Transformer ensemble achieved superior performance (RMSE = 0.10 mm·day⁻¹, NSE = 0.98), outperforming single models by 31% in uncertainty reduction. SHAP analysis identified phase-dependent factor shifts: soil water content dominated Stage I (42.5%), while leaf area index (LAI) controlled Stages II–III (>48%). A bimodal LAI time-lag effect emerged: 4–7 days (leaf water potential equilibrium, 27.7% contribution) and 8–14 days (root uptake compensation, 21.7%). Burn severity significantly extended time-lags (severe burns: 12/21 days vs. unburned: 5/12 days), indicating hydraulic system reconstruction requirements. Despite equivalent LAI recovery, severe burns maintained 12%–15% ET reduction, suggesting lasting hydraulic limitations. This study demonstrates that physics-constrained AI models effectively capture complex post-fire ecohydrological dynamics while providing mechanistic interpretability, advancing understanding of vegetation–water coupling reconstruction under increasing fire frequency. Full article

Temporomandibular joint osteoarthritis (TMJOA) is a degenerative disease characterized by progressive cartilage destruction, and chondrocyte apoptosis plays a critical role in TMJOA progression. As chondrocytes reside in an avascular microenvironment inside the cartilage matrix, energy production via glycolysis is crucial for their survival. This study investigated the role of the key glycolytic enzyme Hexokinase 2 (HK2) in TMJOA pathogenesis and the therapeutic potential of dental pulp stem cell-derived extracellular vesicles (DPSC-EVs). In a rat experimental TMJOA model induced by monosodium iodoacetate (MIA) intra-articular injection, we observed a significantly decreased expression of HK2 along with cartilage matrix degradation. In the in vitro study, MIA induced chondrocyte apoptosis with caspase-3 activation, accompanied by impaired glycolytic function. Intervention with DPSC-EVs effectively rescued the expression of HK2 within chondrocytes, leading to a notable restoration of cellular glycolysis. Consequently, DPSC-EV treatment markedly attenuated the progression of TMJOA by reducing chondrocyte apoptosis and improved cartilage integrity. Our findings demonstrated that DPSC-EVs represent a promising cell-free therapeutic strategy for TMJOA, exerting their protective effects by targeting HK2, thereby preserving chondrocyte viability and attenuating osteoarthritis development. Full article

Periodontitis is a chronic inflammatory disease marked by the progressive destruction of periodontal tissues, where conventional therapies often fail to maintain adequate drug levels at the target site. This study reports the development and characterization of a thermosensitive gel containing nanostructured lipid carriers (NLC) for controlled local periodontal delivery. Apigenin (AP)-loaded NLC were prepared using AP as active agent and clove essential oil (CEO) as liquid lipid subsequently incorporated into Poloxamer 407 (5–15% w/w) hydrogels. The formulations were evaluated in relation to particle size, morphology, thermal and rheological behavior, mucoadhesion, in vitro release, antibacterial activity, and stability. Optimized nanoscale NLC showed a high entrapment efficiency, and uniform morphology. Raman analysis confirmed successful AP incorporation and homogeneous distribution in the gel without incompatibility. NLC-loaded gels exhibited sol–gel transition at physiological temperature with improved viscoelasticity and enhanced mucoadhesion. The drug release was sustained for 48 h and followed the Korsmeyer–Peppas model, indicating diffusion-based and anomalous transport. The antibacterial assessment demonstrated the pronounced inhibitory activity of the NLC formulations against key periodontal pathogens, with the formulation-dependent modulation of antimicrobial efficacy observed following the gel incorporation. Stability studies showed preserved nanoparticle structure and uniform dispersion. Overall, the thermoresponsive NLC-hydrogel system offers a promising strategy for prolonged, localized periodontal therapy. Full article

Digital phenotyping is increasingly recognized as an essential tool for the quantitative analysis of fungal morphology, particularly in controlled indoor cultivation systems where large numbers of fruiting bodies must be assessed consistently and non-destructively. While YOLOv8-based deep learning approaches have previously been applied in phenotypic analyses of edible mushrooms, the applicability of newer YOLO architectures to fungal phenotyping remains largely unexplored. In this study, we present a controlled-environment digital phenotyping framework for indoor mushroom cultivation and conduct a systematic benchmarking evaluation of YOLOv11 for phenotypic segmentation in comparison with YOLOv8. Using bottle-cultivated Pleurotus ostreatus and Flammulina velutipes as representative edible basidiomycetes, we performed a controlled comparison of YOLOv8-seg and YOLOv11-seg using identical datasets, preprocessing pipelines, and hyperparameter configurations. The results demonstrate that YOLOv11 achieves segmentation performance comparable to that of YOLOv8 across all evaluated metrics (ΔmAP_50–95 < 0.01) while substantially reducing computational complexity, including fewer trainable parameters, lower FLOPs, and decreased gradient load. Validation against caliper-based physical measurements revealed moderate, trait-dependent agreement, whereas inter-model consistency between YOLOv8 and YOLOv11 remained consistently high across diverse morphological and segmentation scenarios. These findings suggest that recent developments in object detection architectures can improve computational efficiency without compromising phenotypic measurement fidelity. More broadly, this study highlights the importance of periodically evaluating emerging detection architectures within biological phenotyping pipelines to ensure scalable, sustainable, and high-throughput fungal phenotyping under controlled-environment cultivation systems. Full article

Background: Orthodontic tooth movement is traditionally explained through mechanical deformation of the periodontal ligament (PDL); however, increasing evidence indicates that immune mechanisms critically shape bone remodeling outcomes. Mechanical stimuli influence immune cell recruitment, cytokine release, and phenotypic polarization, but these components are rarely integrated into a unified framework. Conceptual framework: We propose the Osteoimmune Axis Model, a conceptual framework describing how mechanical loading may bias immune polarity and thereby gate periodontal remodeling. Compressive loading appears to favor an M1 macrophage/Th17-dominant program associated with pro-inflammatory cytokines and enhanced RANKL-mediated osteoclastogenesis. In contrast, tensile or physiological strains may favor M2 macrophages and regulatory T cells (Treg), supporting IL-10, TGF-β, angiogenesis, extracellular-matrix repair, and osteoblastic activity. Stromal cells are proposed to act as mechanosensors and immune amplifiers that shape cytokine gradients and feedback loops. Predictions: The model predicts that identical forces may produce divergent outcomes depending on immune baseline; load duration may be more destructive than peak magnitude; tensile strain may stabilize M2/Treg pathways; thin periodontal phenotypes may shift toward the catabolic pole at lower mechanical loads; ROS may amplify immune-mediated bone loss; and immunomodulation may raise the threshold for pathological remodeling. Conclusion: The Osteoimmune Axis integrates mechanobiology and immunology into a testable framework for explaining variability in orthodontic periodontal remodeling and for generating hypothesis-driven, immune-aware risk assessment. Full article

The cheese maturation process involves complex physicochemical and structural changes that directly influence its final quality and consumer acceptance. The development of non-destructive and rapid analytical techniques is therefore essential for monitoring these changes and optimizing quality control strategies. This study evaluated the potential of dielectric spectroscopy and near-infrared (NIR) spectroscopy as tools to predict properties associated with the quality of Swiss-type cheese during the maturation process. The cheese samples were matured for 60 days, and NIR profiles (900–1700 nm), dielectric profiles (40¹–10⁶ Hz) and physical characteristics (color and texture) were obtained every 15 days. Based on these data, models were developed to predict the maturation time (days) and physical properties using partial least squares regression (PLSR). The performance of the model was evaluated using the determination coefficient ($R^2$) and the root mean square error (RMSE). The results showed that dielectric spectroscopy provided a better fit for all the parameters evaluated ($R_{\mathrm{day}}^2=0.999$, $R_{L^{*}}^2=0.912$, $R_{a^{*}}^2=0.983$, $R_{b^{*}}^2=0.982$, and $R_{\mathrm{firmness}}^2=0.625$), with prediction errors of ${\mathrm{RMSE}}_{\mathrm{day}}=0.219$, ${\mathrm{RMSE}}_{L^{*}}=1.184$, ${\mathrm{RMSE}}_{a^{*}}=0.163$, ${\mathrm{RMSE}}_{b^{*}}=0.308$, and ${\mathrm{RMSE}}_{\mathrm{firmness}}=91.094$. In conclusion, dielectric spectroscopy combined with PLSR showed slightly superior performance to predict maturation time and physical changes in Swiss-type cheese. Full article

The adulteration of wheat flour with borax poses a serious food safety risk, yet conventional rapid non-destructive screening methods remain limited. This study developed a machine learning-based microwave non-destructive semi-quantitative detection method for identifying borax adulteration in wheat flour. Using a proprietary microwave detection system, which acquires broadband frequency-domain amplitude attenuation and phase shift responses in the 2.5–11.5 GHz band, amplitude attenuation spectra and dimensional phase offset spectra were obtained from 155 samples prepared at three adulteration levels (0%, 0.1–0.9%, 1–5%). These samples simulated real-world adulteration scenarios. To address high-dimensionality and class imbalance, a hybrid Random Forest-Whale Optimization Algorithm (RF-WOA) was employed to synergistically optimize feature selection and model hyperparameters. Through hierarchical repeated validation and macro-level metric evaluation, this approach achieved an overall classification accuracy of 94.6% and a macro F1 score of 0.95 while compressing the original 1800-dimensional feature space to approximately 200 effective features. Confusion matrix analysis indicates 100% recall for undiluted samples, with misclassifications primarily occurring between adjacent adulteration levels and no false negatives introduced for adulterated samples. These results demonstrate that microwave sensing combined with the RF-WOA provides a rapid, non-destructive, and robust preliminary screening and grading evaluation strategy for borax adulteration in wheat flour, exhibiting significant potential in food safety monitoring and regulatory inspection. Full article

Cotton above-ground biomass (AGB) is a key indicator of crop growth and yield potential. Traditional monitoring methods are labor-intensive and destructive, limiting their suitability for precision agriculture. This study developed a high-precision, non-destructive model for estimating cotton AGB by integrating spectral and texture features derived from UAV multispectral and RGB images. UAV data were collected at major growth stages in 2024. Eight vegetation indices (VIs) and eight texture features (TFs) were extracted. Four machine learning algorithms—support vector regression (SVR), random forest regression (RFR), partial least squares regression (PLSR), and extreme gradient boosting (XGB)—were evaluated using independent validation data. Models based on fused spectral and texture features outperformed single-feature models. RFR achieved the best performance (R² = 0.811; RMSE = 2.931 t ha⁻¹). Texture features alone also showed strong predictive capability (R² = 0.789), highlighting their value in capturing canopy structural information. These results demonstrate that spectral–texture fusion significantly improves cotton AGB estimation and that RFR provides a robust modeling framework for UAV-based crop monitoring. Full article