Search Results (2,100)

The increasing diffusion of plant-based milk alternatives poses new challenges at the intersection of food safety and consumer experience, particularly regarding allergen cross-contamination and beverage performance during preparation. Traditional quality control strategies are typically confined to upstream production stages and are unable to address individualized risks and sensory variability at the point of consumption. In this study, we propose an embedded volatilomic sensing approach that combines metal oxide semiconductor (MOX) sensor arrays with lightweight artificial intelligence algorithms to enable real-time, on-device decision-making. The volatilome of four commercially available plant-based milk beverages (oat, almond, soy, and coconut) was characterized using GC–MS/SPME as a reference method, while a MOX-based electronic nose provided rapid, non-destructive sensing of volatile fingerprints. Linear Discriminant Analysis demonstrated clear discrimination among beverage types based on their volatile signatures, supporting the use of MOX sensor arrays as functional descriptors of compositional identity and process-related variability. Beyond beverage classification, the proposed framework is designed to support future implementation of (i) screening for anomalous volatilomic patterns potentially compatible with accidental cow’s milk carryover in shared preparation settings and (ii) adaptive tuning of preparation parameters (e.g., foaming-related settings) in smart beverage systems. The results highlight the role of embedded volatilomic intelligence as a unifying layer between personalized risk-aware screening and sensory-oriented process control, paving the way for intelligent food-processing appliances capable of autonomous, real-time adaptation at the point of consumption. Full article

Effective integrated pest management (IPM) relies on precise knowledge of pest developmental biology, particularly the identification of larval instars, which is fundamental for predicting population dynamics and timing control interventions. This study established a morphometric framework for the larval staging of a sap beetle pest infesting pear orchards. Specimens were collected and reared under laboratory conditions, with their identity confirmed as Urophorus humeralis through integrated morphological and molecular (COI barcoding) analysis. To determine the number of larval instars, head capsule width (HCW), inter-antennal distance (IAD), and inter-caudal distance (ICD) were measured. Frequency distribution analysis and validation using Dyar’s rule via linear regression revealed three distinct larval instars. Head capsule width was identified as the most reliable and consistent morphological character for instar discrimination. This study reports for the first time the infestation of pear fruits by U. humeralis and provides detailed morphometric criteria for larval staging, delivering essential baseline data for the biology of Nitidulidae and a scientific basis for developing stage-specific pest management strategies. Full article

Data-driven approaches are increasingly required to optimize biofertilization strategies in forage systems. Machine learning (ML) provides an efficient tool for identifying functional drivers in complex plant–soil–microbe systems, offering important perspectives for precision data-driven agriculture. However, despite its potential, ML remains data-driven in studies involving diazotrophic inoculation using biochar as a pelletizing material, particularly in forage grasses. This study applied ML to predict the key drivers controlling Brachiaria brizantha performance and soil quality under biochar-pelletized diazotrophic bacteria (DB). Five isolates were inoculated with or without biochar, and plant traits and soil attributes, including pH, potassium, phosphorus, sodium, and urease activity were evaluated. These data were integrated into multivariate analyses and ML algorithms, including Linear Discriminant Analysis, Random Forest, and Support Vector Machine, to identify the functional drivers that best discriminate treatment performance and uncover mechanistic functional drivers. All isolates increased soil potassium content, with the highest values in the biochar amended treatments, and a 39% increase. Soil pH and urease activity were significantly modulated by isolate identity, while biomass allocation patterns differed among treatments. Overall, the results highlight that biochar pelletization can enhance the effectiveness of DB inoculants. ML revealed that dry foliar biomass, soil pH, and fresh root weight were the most predictive variables, highlighting consistent signatures explaining plant–soil responses to biochar-pelletized DB. These findings demonstrate that interpretable ML can disentangle complex plant–soil–microbe interactions, support precision biofertilization design, and serve as an efficient decision-support tool for sustainable pasture management. Beyond the present system, this study establishes a transferable and scalable analytical framework for precision biofertilization strategies in forage systems and other biochar-mediated agroecosystems, advancing predictive and data-driven approaches in sustainable agricultural engineering. Full article

Accurately tracing the geographical origin of Zanthoxylum schinifolium Sieb. et Zucc. is important for brand authentication, quality control, and food safety assurance. In this study, the stable isotope ratios (δ¹³C, δ¹⁵N, δ²H, δ¹⁸O) and the contents of 20 elements were analyzed in samples from three major production regions. Significant differences (p < 0.05) were observed in δ¹³C, δ²H, δ¹⁸O and most elemental profiles across origins. Chemometric methods—including principal component analysis (PCA), orthogonal partial least squares-discriminant analysis (OPLS-DA), and linear discriminant analysis (LDA)—were applied to classify samples by geographical origin. OPLS-DA identified key discriminators (VIP > 1) such as Ca, δ¹³C, Mg, δ²H, B, δ¹⁸O, Cr, Ni, Na, Pb, As, Co, Se, and Zn, achieving a classification accuracy of 96.8%. LDA based on the combined isotope and element datasets showed even higher performance, with an original discrimination rate of 98.4% and a cross-validated rate of 92.8%. The results demonstrate that integrating stable isotope and multi-element fingerprints with supervised classification models provides a reliable and effective approach for verifying the geographical origin of Zanthoxylum schinifolium, supporting its use in traceability systems and fair trade practices. Full article

Rapid and accurate identification of water inrush sources is essential for the prevention and control of coal mine water hazards. Fisher discriminant analysis and random forest are widely applied, but their performance comparison and applicability under single-mine and multi-mine scenarios remain to be investigated. This study takes the Tunlan Mine in Shanxi Province, China, as an example and evaluates both models using accuracy, precision, recall, F1-score, and confusion matrix. A joint discrimination scheme is used to explore their generalization ability. In the single-mine scenario, the improved Fisher algorithm achieves an overall accuracy of 93% and the random forest model achieves 87%, indicating that the former has greater advantages when data distribution is relatively linear. In the multi-mine joint discrimination scenario, the random forest model yields accuracies of 77–98%, far exceeding those of the Fisher algorithm and demonstrating clear superiority in handling complex nonlinear data. The results show that model performance depends primarily on data quality and feature distribution rather than solely on sample size. This study provides a scientific basis for selecting water source identification algorithms in different scenarios and has practical value for improving coal mine water hazard prevention and control. Full article

Reliable seed accession identification underpins germplasm conservation, traceability and breeding; however, conventional assays remain destructive, labour-intensive and difficult to scale. Here, visible–near-infrared–shortwave infrared (VIS–NIR–SWIR) hyperspectral imaging (HSI; 449.54–2399.17 nm; 563 bands) was used to classify 32 grain–legume accessions (n = 3200 seeds; 100 seeds per accession), comprising 30 common bean (Phaseolus vulgaris L.) landraces plus two outgroup legumes (Vigna angularis (Willd.) Ohwi & Ohashi and Cajanus cajan (L.) Huth). Each seed was represented by one ROI-averaged spectrum obtained from mean representative pixels within a standardised 10 × 10 pixel window at the centre of each seed. A fixed stratified 70:30 seed-level training:test partition was used, with 70 seeds per accession (n = 2240) reserved for fully independent training and 30 seeds per accession (n = 960) reserved as a fully independent test set. Principal component analysis (PCA) captured 97.42% of the spectral variance in the first three components (PC1 = 63.34%, PC2 = 23.78%, and PC3 = 10.31%). One-versus-rest wavelength association mapping revealed a maximum R² of 0.775 at 461.37 nm, and ReliefF concentrated the strongest reduced-band signal within 449.54–456.30 nm and 577.02–597.54 nm. In the original ReliefF-selected 16-band benchmark, the subspace discriminant reached 68.25% macro-F1 and 68.54% balanced accuracy; after edge-band trimming, the alternative 16-band configuration decreased to 60.67% and 60.94%, respectively. With respect to the full-spectrum sensitivity benchmark, linear discriminant analysis achieved 96.35% balanced accuracy, followed by linear SVM (94.17%). Deep learning trained directly on the full 563-band spectra reached 84.90% test accuracy, 84.47% macro-F1, 86.27% precision and 84.90% recall, with MLP_Wide outperforming the convolutional, recurrent and attention-based alternatives. Overall, under controlled laboratory conditions, this benchmark shows that accession discrimination is driven mainly by visible-domain contrasts in the most compact representations, whereas the full spectral context remains important for the most confusable accessions and for cautious future sensor design. The reduced-band findings should therefore be interpreted as exploratory guidance for sensor design rather than as a validated deployment-ready specification. Full article

This study investigates whether multi-component T₂ mapping, using bi-exponential (BE) and stretched-exponential (SE) models, enhances the early detection of knee osteoarthritis (OA) compared with the conventional mono-exponential (ME) approach. T₂ relaxation maps were derived from 26 patients with early-stage OA and 26 healthy controls. To minimize the influence of age-related cartilage changes, all model-derived parameters were adjusted for age prior to analysis. Quantitative T₂ parameters were extracted from six anatomically defined cartilage sub-regions to capture spatially heterogeneous tissue alterations characteristic of early OA. These parameters were then integrated using linear discriminant analysis to assess combined diagnostic performance. Global whole-cartilage analyses demonstrated limited discriminatory power across all models, with area under the receiver operating characteristic curve (AUC) values not exceeding 0.65, indicating that diffuse averaging obscures subtle, localized degeneration. In contrast, sub-regional analysis improved classification accuracy, highlighting the importance of regional assessment in early disease. Among the evaluated models, the BE-T₂ model showed the highest performance, achieving an AUC of 0.68, and marginally outperforming both the SE model (AUC = 0.60) and the ME model (AUC = 0.51). These findings suggest that multi-component T₂ mapping, particularly when applied at a sub-regional level, may offer improved sensitivity to early cartilage compositional changes. Overall, this approach shows strong potential as a noninvasive imaging biomarker for the early detection of knee OA. Full article

Gut microbiota dysbiosis is implicated in metabolic disorders, yet taxonomic and functional alterations in canine diabetes remain incompletely defined. Here, we performed shotgun metagenomic sequencing of fecal samples from 38 diabetic dogs and 37 healthy controls under controlled conditions (no recent antibiotic/probiotic exposure and stable commercial diets). Alpha-diversity indices did not differ between groups, whereas beta-diversity revealed significant separation of community structure at both genus and species levels (p < 0.05). Linear discriminant analysis effect size (LEfSe) identified enrichment of opportunistic-associated taxa in diabetic dogs, including Enterobacterales/Enterobacteriaceae (e.g., Escherichia coli, Klebsiella pneumoniae, Salmonella enterica) and Enterococcus faecalis. In contrast, healthy dogs were enriched for putatively beneficial taxa linked to bile acid and short-chain fatty acid (SCFA) metabolism, including Turicibacter spp. and Romboutsia spp. Functional profiling showed higher abundances of pathways related to carbohydrate/energy metabolism, membrane transport, and virulence/colonization in diabetic dogs; 17 KEGG level-3 pathways and 320 KOs differed at FDR < 0.05, with enriched modules including bacterial secretion systems, lipopolysaccharide biosynthesis, chemotaxis/flagellar assembly, and biofilm formation. Collectively, canine diabetes is associated with a remodeled gut microbiome characterized by expansion of opportunistic pathogens and elevated virulence and metabolic potential, supporting exploration of microbiota-targeted strategies as a complement to conventional management. Full article

Wavelength modulation spectroscopy (WMS) is a representative implementation of tunable diode laser absorption spectroscopy (TDLAS), enabling reliable gas component analysis with concentration-related information derived from harmonic component extraction, while offering enhanced noise immunity for trace gas sensing in open environments. However, due to the strong coupling between laser wavelength and intensity, wavelength modulation inevitably introduces residual amplitude modulation (RAM), which significantly degrades measurement accuracy. To address this issue, this study introduces a RAM suppression algorithm based on multiple harmonic component decoupling (MHCD), using the second-harmonic lateral peak inclination angle (LPIA) as a characteristic indicator. Unit harmonic operators for the first, second, and third harmonics are designed, and an original harmonic reconstruction model is established via linear superposition of harmonic components. The optimal harmonic component ratio is determined at the composite operator with the maximum cross-correlation coefficient, and RAM noise is eliminated through a multi-harmonic decoupling matrix. Repetitive measurements on 22 mm pharmaceutical vials with 4% oxygen concentration demonstrate that MHCD reduces the second-harmonic LPIA from 18.07° to 8.56°. Concentration discrimination experiments conducted on seven groups of 22 mm vials with 2% concentration steps (0–12%) show that MHCD increases the true positive rate by 6–11% and decreases the false positive rate by 4–9%, confirming its effectiveness for pharmaceutical online inspection applications. Full article

Early-stage fungal contamination in maize kernels is difficult to identify visually and it can cause severe quality and safety risks during storage and transportation. Short-wave infrared (SWIR) hyperspectral imaging offers a rapid, non-destructive approach by capturing chemical information related to water, proteins, and lipids. This study investigates the early detection and classification of Gibberella zeae contamination in maize kernels using SWIR hyperspectral imaging combined with machine learning. Two maize varieties were artificially inoculated and cultured under controlled conditions, followed by hyperspectral data collection over six contamination stages. Various preprocessing techniques including standard normal variate (SNV), second derivative (SD), multiplicative scatter correction (MSC), and derivatives were evaluated to enhance data quality. Feature wavelength selection was performed using successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and uninformative variable elimination (UVE), significantly reducing redundancy and improving classification performance. Multiple models, including linear discriminant analysis (LDA), multilayer perceptron (MLP), support vector machine (SVM), a convolutional neural network (CNN), long short-term memory (LSTM) network, and a hybrid architecture Transformer that integrated a CNN, a LSTM network, and a Transformer (abbreviated as CLT), were constructed for both binary (healthy vs. contaminated) and multiclass classification tasks. Specifically, the multiclass task consisted of six contamination stages corresponding to contamination time from Day 0 to Day 5. The best binary classification task accuracy of 100% was achieved using SNV-preprocessed data with the MLP model. For multiclass classification task, the SD-preprocessed LDA model reached a test accuracy of 92.56%. Combined with appropriate preprocessing, feature selection and modeling, these results demonstrate that hyperspectral imaging is a powerful tool for the non-destructive, early-stage identification of fungal contamination in maize kernels, offering strong support for food safety and quality monitoring. Full article

The objective of this research was to apply morphometric and chemometric techniques to analyze the influence of climate and soil type on the morphological, proximate, and fatty acid fingerprints of moringa (Moringa oleifera Lam.) seeds cultivated in different regions of Mexico. Seeds were collected from the states of Chiapas, Michoacán, Nuevo León, Oaxaca, Veracruz, and Yucatán. The morphological traits of the seeds were evaluated, while the proximate composition and fatty acid profiles of the seed flours were analyzed using gas chromatography–mass spectrometry (GC–MS). Data were assessed through analysis of variance (ANOVA) and linear discriminant analysis to develop their fingerprint profiles. The results showed that the morphological variables that constituted the climate-based morphological fingerprint were seed length, width, seed weight, and kernel weight, whereas for the soil type-based fingerprint, only seed length was significant. Regarding the proximate chemical composition, all variables (fat, ash, moisture, and protein), except fiber content, were influenced by both climate and soil type, forming the proximate chemical fingerprint. The fatty acid fingerprint consisted of 21 compounds, with oleic, behenic, stearic, palmitic, and arachidic acids present in the highest concentrations. The fingerprints obtained from the different determinations were confirmed through cross-validation values exceeding 50%, according to the linear discriminant analysis validation technique. The fatty acid and proximate composition determinations showed the highest classification values (83–100%) and contributed most significantly to ensuring the fingerprinting of moringa seeds cultivated in Mexico. Full article

This paper investigated the feasibility of snapshot multispectral fluorescence imaging for nondestructive identification of cold stress in pepper plants. Fluorescence spectra were obtained by exciting the plant with a 405 nm ultraviolet LED. The plants were grown under three temperature conditions: 17 °C (control), 10 °C (moderate cold stress), and 5 °C (severe cold stress). Raw fluorescence spectra extracted from the demosaiced snapshot images were used as inputs for a deep-learning pipeline consisting of feature extraction, an encoder–decoder GRU, and a multilayer perceptron (MLP), and the results were compared with conventional machine learning classifiers, including linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and a Gaussian support vector machine (G-SVM). Tukey’s HSD test indicated that the proposed deep-learning model achieved the highest cross-validation accuracy and consistently produced superior classification metrics (accuracy of 85.7%, precision of 85.3%, recall of 85.3%, F1-score of 85.2). The trained model was further applied to hyperspectral cubes to generate classification maps; however, moderate misclassification was observed, consistent with the overall prediction performance. Full article

Gut microbiota are integral to host health and ecological adaptation, yet their interactions with environmental microbial communities remain understudied in migratory waterbirds. Using high-throughput 16S rRNA gene sequencing, we compared gut microbiota of captive and wild Siberian cranes and their associations with soil microbiota in the Poyang Lake wetlands. Alpha diversity was significantly higher in soil than in gut microbiota, with captive cranes exhibiting greater microbial richness and evenness than wild individuals. Beta diversity analysis revealed distinct gut and soil microbiota, with partial overlap between captive and wild crane gut microbiota. Firmicutes dominated gut communities, with Ligilactobacillus and Romboutsia enriched in captive cranes, whereas Acidobacteria were predominant in soil. Escherichia-Shigella was more abundant in wild cranes and soil. Linear discriminant analysis (LDA) effect size (LEfSe) analysis identified 34 differentially enriched taxa, and microbial network analysis indicated stronger gut–soil microbial associations than those between captive and wild hosts. Network analysis further revealed distinct co-occurrence patterns between captive and wild groups, suggesting potential shifts in microbial interaction structures under different living conditions. These findings provide preliminary insights that may inform future conservation strategies for Siberian cranes. Full article

As the global aging population increases, the early detection and prevention of Alzheimer’s disease (AD) have become important in public health. To solve the problems of subjectivity and low timeliness of traditional assessment methods, this paper proposes a multimodal dementia prevention system that combines physiological sensing, a gamification interface, and a classification model. The system includes an interactive joystick to measure pulse and blood pressure. A Chinese music game app increases the participation of the elderly and reduces their sense of rejection through gamification interaction. After the physiological data were standardized by Z-score, they were input into three small sample classifiers (Gaussian Naïve Bayes, Fisher Linear Discriminant Analysis, and Logistic Regression) for the binary classification of AD. The system performance was evaluated using the Leave-One-Out cross-validation method. Experimental results show that Logistic Regression performed best in situations with extremely small samples and class imbalance, with an F1-score of 0.700, which was higher than the other two. Dynamic features and model fusion technologies need to be integrated to further enhance the clinical application potential of the system in the early prediction of dementia. Full article

Orthogonal Linear Discriminant Analysis (OLDA) has been widely studied for dimensionality reduction, as the orthogonality constraints on its projection matrix enable more effective elimination of redundant features compared to conventional Linear Discriminant Analysis (LDA). However, most existing methods for solving OLDA rely on iterative optimization to sequentially construct orthogonal components, incurring massive repeated high-cost matrix operations and thus leading to substantial computational inefficiency. To address this limitation, we propose QR decomposition-based Fast OLDA (QR-FOLDA), a method built upon a theoretical result (Theorem 1) established in this work: the optimal solutions of LDA remain valid under any full-rank linear transformation. By leveraging this property, QR-FOLDA applies QR decomposition directly to the optimal LDA solution, thereby enforcing orthogonality while avoiding the repeated high-cost matrix operations typically involved in iterative optimization procedures. Experimental evaluations conducted on nine real-world datasets across various domains show that QR-FOLDA not only achieves substantial improvements in computational efficiency compared to existing OLDA methods but also delivers superior classification performance. These findings position QR-FOLDA as a theoretically sound and practically efficient solution for orthogonal discriminant analysis. Full article