Search Results (15,112)

This study proposes a novel non-destructive approach to assessing and predicting the quality of stored date fruits using a composite quality index (Qi) modeled via visible–near-infrared (VIS–NIR) spectroscopy and artificial neural networks (ANNs). Two leading cultivars, Sukkary and Khlass, were stored for 12 months using three temperature regimes (25 °C, 5 °C, and −18 °C) and five types of packaging. The samples were grouped into six moisture content categories (4.36–36.70% d.b.), and key physicochemical traits, namely moisture, pH, hardness, total soluble solids (TSSs), density, color, and microbial load, were used to construct a normalized, dimensionless Qi. Spectral data (410–990 nm) were preprocessed using second-derivative transformation and modeled using partial least squares regression (PLSR) and the ANNs. The ANNs outperformed PLSR, achieving the correlation coefficient (R²) values of up to 0.944 (Sukkary) and 0.927 (Khlass), with corresponding root mean square error of prediction (RMSEP) values of 0.042 and 0.049, and the relative error of prediction (REP < 5%). The best quality retention was observed in the dates stored at −18 °C in pressed semi-rigid plastic containers (PSSPCs), with minimal microbial growth and superior sensory scores. The second-order Qi model showed a significantly better fit (p < 0.05, AIC-reduced) over that of linear alternatives, capturing the nonlinear degradation patterns during storage. The proposed system enables real-time, non-invasive quality monitoring and could support automated decision-making in postharvest management, packaging selection, and shelf-life prediction. Full article

Accurate prediction of wheat storage quality is essential for ensuring storage safety and providing early warnings of quality deterioration. However, existing methods focus solely on storage environmental conditions, neglecting the spatial distribution of temperature within grain piles, lacking interpretability, and generally failing to provide reliable forecasts of future quality changes. To overcome these challenges, an interpretable prediction framework for wheat storage quality based on stacked ensemble learning is proposed. Three key features, Effective Accumulated Temperature (EAT), Cumulative High Temperature Deviation (CHTD), and Cumulative Temperature Gradient (CTG), were derived from grain temperature data to capture the spatiotemporal dynamics of the internal temperature field. These features were then input into the stacked ensemble learning model to accurately predict historical quality changes. In addition, future grain temperatures were predicted with high precision using a Graph Convolutional Network-Temporal Fusion Transformer (GCN-TFT) model. The temperature prediction results were then employed to construct features and were fed into the stacked ensemble learning model to enable future quality change prediction. Baseline experiments indicated that the stacked model significantly outperformed individual models, achieving R² = 0.94, MAE = 0.44 mg KOH/100 g, and RMSE = 0.59 mg KOH/100 g. SHAP interpretability analysis revealed that EAT constituted the primary driver of wheat quality deterioration, followed by CHTD and CTG. Moreover, in future quality prediction experiments, the GCN-TFT model demonstrated high accuracy in 60-day grain temperature forecasts, and although the prediction accuracy of fatty acid value changes based on features derived from predicted temperatures slightly declined compared to features based on actual temperature data, it remained within an acceptable precision range, achieving an MAE of 0.28 mg KOH/100 g and an RMSE of 0.33 mg KOH/100 g. The experiments validated that the overall technical route from grain temperature prediction to quality prediction exhibited good accuracy and feasibility, providing an efficient, stable, and interpretable quality monitoring and early warning tool for grain storage management, which assists managers in making scientific decisions and interventions to ensure storage safety. Full article

Background: Polyphenols from Sorbus aucuparia L. (rowanberry) fruits are valuable bioactive compounds, yet their efficient extraction remains a challenge. Ultrasound-assisted extraction (UAE) offers a promising technique to enhance yield, but optimization of parameters is necessary. Methods: UAE was performed using a VC750 processor (20 kHz) at ultrasound intensities of 1.3, 7.65, and 14 W/cm² in pulsed mode (2 s on, 4 s off). Sonication times of 5, 10, and 15 min (total extraction times: 15, 30, 45 min) and ethanol concentrations of 30%, 60%, and 90% were tested. Selected polyphenols (gallic acid, neochlorogenic acid, chlorogenic acid, vanillic acid, epicatechin, trans-ferulic acid, rutin, quercetin, cinnamic acid) were quantified using HPLC. Response Surface Methodology (RSM) was applied for process optimization. Results: High-quality predictive models were obtained, particularly for neochlorogenic acid. Ethanol concentration exerted the strongest influence on extraction efficiency for most of the studied polyphenols, whereas extraction time showed no significant effect. Conclusions: Ethanol concentration is a key factor in maximizing polyphenol yield from S. aucuparia fruits using UAE. These findings may guide selective extraction strategies for phenolic compounds at early stages of food and nutraceutical processing. Full article

Efficient drying is crucial for the preservation and high-value utilization of tricholoma matsutake (TM). Traditional hot-air drying is inefficient, energy-intensive, and prone to quality degradation. This study investigates the application of microwave drying for TM, systematically analyzing its dielectric properties and moisture states, and elucidating the dielectric response mechanisms during drying. Response surface methodology (RSM) was employed to optimize key process parameters, including microwave power, drying time, and sample mass, and to validate the feasibility of the optimized process for industrial applications. Results revealed that the dehydration process of TM comprises three distinct stages, with free water evaporation contributing 69.8% of the total weight loss. Dielectric properties correlated strongly with apparent density and temperature, with the loss tangent ($\mathit{tan}\delta$) increasing by 213.0% at higher temperatures, confirming dipole loss as the primary heating mechanism. Under optimized drying conditions (power: 620.00 W, time: 2.70 min, mass: 13.2 g), a dehydration rate (DR) of 85.41% was achieved, with a 1.50% deviation from the model-predicted values. The optimized process effectively maintained the relative integrity of the microstructure of TM, with the C/O ratio increasing from 1.03 to 1.31. Steam pressure-driven moisture migration was identified as the primary mechanism facilitating microwave-enhanced dehydration. Pilot-scale experiments scaled up the processing capacity to 15 kg/h and confirmed that the new process reduced total costs by 38% compared to traditional hot-air drying. The study developed an efficient and reliable microwave drying model, supporting industrial-scale TM processing. Full article

To address the technical challenge of real-time interpretation of sandstone reservoir porosity during drilling, a data-driven approach is employed by integrating logging data with machine learning algorithms to deeply mine existing logging data and predict the porosity range of encountered reservoirs. Initially, the acquired logging data is cleaned, and correlation analysis is conducted on the feature parameters. Porosity values were discretized into intervals according to field conditions. Subsequently, porosity-intelligent interpretation models are established using One-vs.-One Support Vector Machines (OVO SVMs), Random Forest (RF), XGBoost, and CatBoost algorithms. Model parameters are optimized using grid search and cross-validation methods. Finally, the test data is interpreted based on the four models with optimized parameters. Results indicate that all four models achieve training accuracies exceeding 95% and test accuracies exceeding 85%. Considering precision, recall, and F1 score comprehensively, the RF model is selected for the case study, with all three indicators exceeding 96%. These findings demonstrate that data-driven methods based on machine learning can accurately interpret sandstone reservoir porosity within specified intervals. For porosity interpretation of sandstone reservoirs in different blocks, interpretation models should be developed using multiple machine learning algorithms, and the best performing model should be selected for practical deployment. This method can be integrated with geological steering drilling technology during horizontal well drilling to ensure that the wellbore trajectory passes through higher-quality reservoir intervals, thereby providing certain guidance for maximizing the encounter rate of reservoir sweet spots. Full article

Prompt optimization through textual feedback has shown promising results in improving the performance of large language models (LLMs) on downstream tasks. However, existing approaches often rely on selecting prompt edits from a pool of candidate gradients using random sampling or local heuristics, requiring multiple evaluations to find effective modifications. In this work, we propose a center-aware selection method that identifies high-quality gradient candidates based on their proximity to a robust semantic center representation of the gradient pool. Rather than sampling or scoring candidates iteratively, our method embeds all textual gradients and deterministically selects the top-k closest to the semantic center, which captures the consensus of the candidate pool. Experiments on three diverse datasets demonstrate that our approach not only improves predictive performance but also reduces the number of required model queries. In addition, qualitative analyses reveal that gradients near the center tend to encode more generalizable reasoning patterns. These findings highlight the utility of semantic embedding space as a reliable signal for selecting effective prompt edits in a resource-efficient manner. Full article

Rapid urbanization has increased pressure on ecosystems, posing serious risks to environmental quality and sustainable development. Understanding the spatiotemporal dynamics and driving mechanisms of Fractional Vegetation Cover (FVC), a key indicator of ecological health, is essential for advancing high-quality regional development and ecological civilization. In this study, Normalized Difference Vegetation Index (NDVI), meteorological, and socio-economic data from 2000 to 2022 were used to analyze the changes and driving forces of FVC in the Beijing–Tianjin–Hebei (BTH) urban cluster using a pixel dichotomy model and Partial Least Square–Structural Equation Modeling (PLS–SEM). The CA-Markov model was applied to predict future FVC patterns under different scenarios. The results show that FVC in the BTH increased from 0.462 to 0.576 between 2000 and 2022. However, this positive trend was accompanied by pronounced spatial differences: FVC increased significantly in the northwestern mountains, while it declined in urban built-up areas. PLS–SEM analysis further indicated that climate factors were the main drivers of FVC growth (0.903), whereas socioeconomic (−0.469) and topographic (−0.260) factors exerted limiting effects. Compared with 2022, FVC declined to varying degrees under all scenarios. Notably, the ecological protection scenario resulted in far less FVC degradation than the inertial development and economic priority scenarios. These findings provide scientific support for spatial planning and emphasize the importance of ecological protection policies in sustaining vegetation and promoting long-term sustainable development. Full article

Polymer recycling is challenging due to practical classification difficulties. Even when the polymer matrix is identified, the presence of various polymeric composites complicates their accurate classification. In this study, Fourier-transform infrared spectroscopy (ATR-FTIR) was used in combination with artificial neural networks (ANNs) to quantitatively predict the mineral filler content in polypropylene (PP) composites. Calibration curves were developed to correlate ATR-FTIR spectral features (600–1700 cm⁻¹) with the concentration (wt.%) of three mineral fillers: talc (PP-Talc), calcium carbonate (PP-CaCO₃), and glass fiber (PP-GF). ANN models developed in MATLAB 2024a achieved prediction errors below 7.5% and regression coefficients (R²) above 0.98 for all filler types. The method was successfully applied to analyze a commercial recycled pellet, and its predictions were validated by X-ray fluorescence (XRF) and energy-dispersive X-ray spectroscopy (EDX). This approach provides a simple, rapid, and non-destructive tool for non-expert users to identify both the type and amount of mineral filler in recycled polymer materials, thereby reducing misclassification in their commercialization or quality control in industrial formulations. Full article

In the Ultra-High-Definition (UHD) domain, blind image quality assessment remains challenging due to the high dimensionality of UHD images, which exceeds the input capacity of deep learning networks. Motivated by the visual discrepancies observed between high- and low-quality images after down-sampling and Super-Resolution (SR) reconstruction, we propose a SUper-Resolved Pseudo References In Dual-branch Embedding (SURPRIDE) framework tailored for UHD image quality prediction. SURPRIDE employs one branch to capture intrinsic quality features from the original patch input and the other to encode comparative perceptual cues from the SR-reconstructed pseudo-reference. The fusion of the complementary representation, guided by a novel hybrid loss function, enhances the network’s ability to model both absolute and relational quality cues. Key components of the framework are optimized through extensive ablation studies. Experimental results demonstrate that the SURPRIDE framework achieves competitive performance on two UHD benchmarks (AIM 2024 Challenge, PLCC = 0.7755, SRCC = 0.8133, on the testing set; HRIQ, PLCC = 0.882, SRCC = 0.873). Meanwhile, its effectiveness is verified on high- and standard-definition image datasets across diverse resolutions. Future work may explore positional encoding, advanced representation learning, and adaptive multi-branch fusion to align model predictions with human perceptual judgment in real-world scenarios. Full article

Habitat fragmentation represents a significant threat to biodiversity, particularly the survival of wild species. Constructing and optimizing ecological networks are critical for promoting sustainable biodiversity, especially in the conservation of unmanaged wildlife. To address this, this study focused on designing and optimizing an ecological network tailored to the preservation of the Xinjiang desert lacertid lizard (Eremias multiocellata). This study integrated a dual-model approach, applying the InVEST model for habitat quality assessment and the MaxEnt model for suitable habitat prediction. An overlay analysis identified 15 core ecological source areas spanning 126,044 km², primarily located in the desert–grassland transition zones of the central and western study areas. A total of 34 ecological corridors were established utilizing the minimum cumulative resistance model, totaling 3764 km in length. These include 11 long corridors, 17 short corridors, and 6 potential corridors. Additionally, 100 strategic points were identified: 41 pinch points, 38 barrier points, and 21 stepping stones. This study identifies priority areas and obstacles affecting the ecological connectivity of the species’ habitats and highlights the importance of small habitat patches for long-term species dispersal and habitat expansion, providing more comprehensive guidance for sustainable development and species conservation. Furthermore, the methodology provides valuable insights into biodiversity conservation and the optimization of the natural habitat spatial layout in desert ecosystems, along with novel methods for managing and conserving other unmonitored animal species in various ecosystems. Full article

Background: Plantago asiatica (P. asiatica) is an important Chinese traditional medicinal plant of the family Plantaginaceae and widely used in pharmaceutical industries. TCP transcription factors play an important role in plant development, but a limited number of studies on this have been reported in P. asiatica.Methods: Since genome assembly was not available, in this study, we used the de novo transcriptome assembly method to genome-wide-characterize the TCP gene family in P. asiatica. Up to 70.7 M high-quality paired-end reads were generated after sequencing and a total of 12 TCP genes were cloned by the predicted bioinformatic results, which were named PaTCP1-12. Results: Phylogenetic tree, motif analysis and subcellular localization results revealed that these PaTCPs were conserved compared to those from the model plant, Arabidopsis. Expression analysis suggested that most of the TCPs were highly expressed in both the leaf and root, while PaTCP1, PaTCP6 and PaTCP9 could also be detected in the seed. Conclusions: Since seed characteristics are one of the main agronomical traits in P. asiatica, the finding of PaTCP1, PaTCP6 and PaTCP9 expression patterns in the stem suggested an important role for further plant improvement. Full article

This study examines the relationship between attitudes toward artificial intelligence (AI) and AI dependency among Ecuadorian university students. A cross-sectional design was used, applying two validated instruments: the Artificial Intelligence Dependence Scale (DAI) and the General Attitudes Toward Artificial Intelligence Scale (GAAIS), with a sample of 540 students. Structural equation modeling (SEM) assessed how both positive and negative attitudes predict dependency levels. Results indicate a moderate level of AI dependency and an ambivalent attitudinal profile. Both attitudinal dimensions significantly predicted dependency, suggesting dual-use behaviors shaped by perceived utility and ethical concerns. Urban students reported higher dependency and greater sensitivity to AI-related risks, highlighting digital inequalities. Although the SEM model showed adequate comparative fit (CFI = 0.976; TLI = 0.973), residual indicators (RMSEA = 0.075) suggest further refinement is needed. This study contributes to underexplored Latin American contexts and emphasizes the need for equity-driven digital literacy strategies in higher education. Findings support pedagogical frameworks promoting critical thinking, ethical reasoning, and responsible AI use. The study aligns with Sustainable Development Goals 4 (Quality Education) and 10 (Reduced Inequalities), reinforcing the importance of inclusive, learner-centered approaches to AI integration. Full article

Rapid and accurate assessment of nutritional quality, particularly crude protein content and essential nutrient concentrations, remains a major challenge in the food and feed industries. In this study, laser-induced breakdown spectroscopy (LIBS) was combined with advanced chemometric modeling to predict the levels of crude protein and key macro- and micronutrients (Ca, Mg, K, Na, Fe, Mn, P, Zn) in 61 barley forage samples composed of whole aerial plant parts ground prior to analysis. LIBS offers a compelling alternative to traditional analytical methods by enabling real-time analysis with minimal sample preparation. To minimize interference from atmospheric nitrogen, nitrogen spectral lines were excluded from the protein calibration model in favor of spectral lines from elements biochemically associated with proteins. We compared the performance of Partial Least Squares (PLSR) regression and Extreme Learning Machine (ELM) using fivefold cross-validation. ELM outperformed PLS in terms of prediction, achieving a coefficient of determination (R²) close to 1 and a ratio of performance to deviation (RPD) exceeding 2.5 for proteins and several nutrients. These results underscore the potential of LIBS-ELM integration as a robust, non-destructive, and in situ tool for rapid forage quality assessment, particularly in complex and heterogeneous plant matrices. Full article

The inspection of the appearance quality of tea leaves is vital for market classification and value assessment within the tea industry. Nevertheless, many existing detection approaches rely on sophisticated model architectures, which hinder their practical use on devices with limited computational resources. This study proposes a lightweight object detection network, TeaAppearanceLiteNet, tailored for tea leaf appearance analysis. A novel C3k2_PartialConv module is introduced to significantly reduce computational redundancy while maintaining effective feature extraction. The CBMA_MSCA attention mechanism is incorporated to enable the multi-scale modeling of channel attention, enhancing the perception accuracy of features at various scales. By incorporating the Detect_PinwheelShapedConv head, the spatial representation power of the network is significantly improved. In addition, the MPDIoU_ShapeIoU loss is formulated to enhance the correspondence between predicted and ground-truth bounding boxes across multiple dimensions—covering spatial location, geometric shape, and scale—which contributes to a more stable regression and higher detection accuracy. Experimental results demonstrate that, compared to baseline methods, TeaAppearanceLiteNet achieves a 12.27% improvement in accuracy, reaching a mAP@0.5 of 84.06% with an inference speed of 157.81 FPS. The parameter count is only 1.83% of traditional models. The compact and high-efficiency design of TeaAppearanceLiteNet enables its deployment on mobile and edge devices, thereby supporting the digitalization and intelligent upgrading of the tea industry under the framework of smart agriculture. Full article

Geosynchronous satellite maneuver detection is critical for enhancing space situational awareness and inferring satellite intent. However, traditional methods often require high-quality orbital sequence data and heavily rely on hand-crafted features, limiting their effectiveness in complex real-world environments. While recent neural network-based approaches have shown promise, they are typically trained in scene or task-specific settings, resulting in limited generalization and adaptability. To address these challenges, we propose MC-MD, a pre-training framework that integrates Masked and Clustered learning strategies to improve the robustness and transferability of geosynchronous satellite Maneuver Detection. Specifically, we introduce a masked prediction module that applies both time- and frequency-domain masking to help the model capture temporal dynamics more effectively. Meanwhile, a cluster-based module guides the model to learn discriminative representations of different maneuver patterns through unsupervised clustering, mitigating the negative impact of distribution shifts across scenarios. By combining these two strategies, MC-MD captures diverse maneuver behaviors and enhances cross-scenario detection performance. Extensive experiments on both simulated and real-world datasets demonstrate that MCMD achieves significant performance gains over the strongest baseline, with improvements of 8.54% in Precision and 7.8% in F1-Score. Furthermore, reconstructed trajectories analysis shows that MC-MD more accurately aligns with the ground-truth maneuver sequence, highlighting its effectiveness in satellite maneuver detection tasks. Full article