Search Results (269)

To establish a rapid traceability method for tea varieties and address the limitations of traditional identification techniques, this study focused on four types of tea—Longjing, Maofeng, Zhuyeqing, and Biluochun—using near-infrared (NIR) spectroscopy. A total of 84 sets of NIR spectra were collected and preprocessed using Savitzky–Golay smoothing (S-G), multiplicative scatter correction (MSC), standard normal variate transformation (SNV), and first derivative (1stDer) methods. Dimensionality reduction and feature selection were then performed using principal component analysis (PCA), linear discriminant analysis (LDA), their combination (PCA-LDA), and the successive projections algorithm (SPA). Classification models based on multiple linear regression (MLR) and support vector machine (SVM) were constructed and evaluated via five-fold cross-validation to assess generalization ability and stability. The results indicated that the SVM model significantly outperformed the MLR model in overall classification and generalization. The PCA-LDA combined approach proved to be the most effective feature selection method. The optimal classification model for tea variety traceability was achieved using MSC or SNV preprocessing combined with PCA-LDA-SVM, yielding a mean five-fold cross-validation accuracy of 96.67%. The confusion matrix revealed that misclassifications mainly occurred between Longjing and Biluochun and between Maofeng and Zhuyeqing, which can be attributed to similarities in processing techniques and chemical composition among these tea varieties. This study provides a rapid, non-destructive, and accurate spectroscopic detection method for tea quality control and traceability, offering a valuable reference for the rapid identification of agricultural products. Full article

Background: Gestational diabetes mellitus (GDM) poses a growing public health challenge worldwide due to its increasing prevalence, associated pregnancy complications, and long-term metabolic risks for both mothers and offspring. Genetic factors are known to contribute to GDM susceptibility, yet little is known about their relevance in ethnic Kazakh population. The primary objective of this study was to evaluate associations between selected candidate SNPs involved in β-cell function and the risk of GDM in a Kazakh cohort. Secondary objectives included the assessment of potential gene–gene interactions. Methods: We conducted a case–control study among 365 pregnant Kazakh women. Of these, 217 were diagnosed with GDM, and 148 had normal glucose tolerance. Clinical and genealogical data were collected. Eight candidate SNPs that were previously associated with GDM or glucose metabolism were genotyped. Logistic regression was used to assess associations between SNPs and GDM risk. Gene–gene interactions were evaluated using multifactor dimensionality reduction (MDR). Results: In univariate analysis, MTNR1B rs10830963 demonstrated a statistically significant association under the additive model (OR 0.61, 95% CI 0.42–0.89), indicating a potential protective effect of the C allele. However, this association was not statistically significant after multivariable adjustment (adjusted OR 0.58, 95% CI 0.32–1.03) and correction for multiple testing. In the adjusted analysis, TCF7L2 rs7903146 showed a significant association under the dominant model (adjusted OR 2.29, 95% CI 1.01–5.46); however, this finding did not remain significant following FDR correction. MDR analysis showed that the best two-locus model included IGF2BP2 rs4402960 and CDKAL1 rs7754840 (CVC = 6/10; testing accuracy = 0.558; permutation p < 0.001). The most stable interaction was observed for the three-locus model comprising IGF2BP2 rs4402960, MTNR1B rs10830963, and PPARG rs1801282 (CVC = 9/10; testing accuracy = 0.576; permutation p < 0.001). Conclusions: The findings suggest that common variants in IGF2BP2, CDKAL1, MTNR1B, TCF7L2, PPARG, and GCK do not exert strong individual effects on GDM susceptibility in this cohort of ethnic Kazakh women. Instead, the results are more consistent with a modest polygenic architecture characterized by small effect sizes and possible weak gene–gene interactions. MDR analysis identified statistically significant interaction models; however, their limited predictive accuracy indicates that these findings should be interpreted as exploratory. Full article

High-dimensional structured datasets are common in fields such as semiconductor manufacturing, healthcare, and finance, where redundant and irrelevant features often increase computational cost and reduce predictive accuracy. Feature selection mitigates these issues by identifying a compact, informative subset of features, enhancing model efficiency, performance, and interpretability. This study proposes Maximal Information Coefficient–Simplified Swarm Optimization (MIC-SSO), a two-stage hybrid feature selection method that combines the MIC as a filter with SSO as a wrapper. In Stage 1, MIC ranks feature relevance and removes low-contribution features; in Stage 2, SSO searches for an optimal subset from the reduced feature space using a fitness function that integrates the Matthews Correlation Coefficient (MCC) and feature reduction rate to balance accuracy and compactness. Experiments on five public datasets compare MIC-SSO with multiple hybrid, heuristic, and literature-reported methods, with results showing superior predictive accuracy and feature compression. The method’s ability to outperform existing approaches in terms of predictive accuracy and feature compression underscores its broader significance, offering a powerful tool for data analysis in fields like healthcare, finance, and semiconductor manufacturing. Statistical tests further confirm significant improvements over competing approaches, demonstrating the method’s effectiveness in integrating the efficiency of filters with the precision of wrappers for high-dimensional tabular data analysis. Full article

Accurate identification of building structural types (BSTs) is essential for seismic vulnerability assessment and disaster risk management. Traditional field survey methods are constrained by high costs, low efficiency, and limited scalability. Although remote sensing-based approaches offer strong potential for large area applications, they are often hindered by limited spatial resolution, spectral confusion, and difficulties in capturing information related to internal building structures. To address these limitations, this study proposes a BST classification approach that integrates remote sensing image features with multisource prior knowledge. In addition to conventional remote sensing features derived from building shape, spectral, and texture, multiple types of prior information are incorporated to compensate for the insufficient structural discriminative capability of remote sensing imagery alone. These include distance to roads, terrain conditions, building height, population, gross domestic product (GDP), and nighttime light intensity. Considering the limited number of labeled samples and the high dimensionality of features, fourteen mainstream machine learning algorithms are systematically evaluated. Through feature selection and model optimization, XGBoost is identified as the most effective classifier, achieving the highest weighted F1 score of 78.62%. The results demonstrate that, under the same machine learning model settings, models trained solely on remote sensing features consistently underperform those integrating multisource features combined with feature selection, confirming the effectiveness of synergistically fusing remote sensing features with prior knowledge for improving overall BST classification performance. Further analyses demonstrate that different groups of remote sensing features and prior knowledge are associated with reductions in misclassification between specific BSTs. Compared with approaches based exclusively on remote sensing imagery, the proposed method exhibits higher and more balanced classification performance across different BSTs, with particularly notable advantages for structure categories that are difficult to distinguish using single-source remote sensing features. This study provides the foundation for subsequent seismic vulnerability analysis and related risk studies. Full article

Unidirectional glass fiber-reinforced thermoplastic (UGFT) composite tapes are promising recyclable structural materials for applications such as composite pressure pipes. However, their durability under hydrothermal environments remains a critical concern. This study emphasizes metrology-driven evaluation of aging behavior in polypropylene-based UGFT tapes. Specimens were conditioned at 95 °C in a deionized-water environment for up to 4 weeks, and multiple complementary measurement techniques were applied to quantify degradation. Mass-change metrology was performed to characterize water uptake kinetics and establish diffusion-driven aging progression. Tensile testing enabled quantitative assessment of mechanical strength retention, defining a >25% reduction in strength as a threshold for significant deterioration. Acoustic emission (AE) acted as the central non-destructive monitoring method, capturing high-fidelity waveforms generated during loading. AE waveform descriptors, such as amplitude, rise time, and frequency content, served as measurable indicators of internal damage mechanisms including matrix cracking, interfacial debonding and fiber breakage. To process large AE datasets, principal component analysis was used for dimensionality reduction, followed by k-means clustering to group signals by damage type. Optical microscopy provided microstructural verification of these classifications. The integrated metrological framework demonstrates a reliable pathway to monitor, identify, and quantify damage evolution in hydrothermally aged UGFT structures. Full article

Efficient target detection in hyperspectral images faces significant deployment challenges on resource-constrained edge platforms due to the large data volume and high computational complexity of detection algorithms. This paper proposes a CEM target detection method based on 1D-CNN feature dimensionality reduction. A lightweight 1D-CNN reduces spectral dimensions from L bands to 16 features, decreasing the core matrix inversion complexity from $O\left(L^3\right)$ to $O\left({16}^3\right)$. Unlike PCA-based dimensionality reduction requiring online eigenvalue decomposition, the proposed approach employs fixed pre-trained weights with simple convolution operations, enabling high parallelizability for FPGA implementation. A Zynq-based PS + PL collaborative acceleration scheme is designed, deploying CNN on the PL side through RTL implementation and CEM on the PS side using double-precision floating-point computation. Experimental validation on multiple hyperspectral datasets demonstrates that the proposed method achieves an AUC of 0.9953 with less than 1% difference compared to traditional CEM, processes 40,000 pixels in approximately 10.8 s, and consumes only 2.067 W, making it suitable for power-sensitive edge applications such as UAV reconnaissance and satellite on-board processing. The system achieves a processing rate of 3704 pixels/s. Full article

Artificial intelligence models, which have begun to be used in every field of science in recent years, have also started to come to the forefront in the classification of avians using bones. This study aimed to identify breeds of domestic fowl (Gallus gallus domesticus L. 1758) using morphometric measurements obtained from the tarsometatarsus bone and machine learning. A total of 328 tarsometatarsus specimens from two different modern domestic fowl breeds were used. A model was developed by performing 10 different morphometric measurements on each tarsometatarsus, and 3280 data points were obtained. Before model development, data cleaning and necessary assessments were carried out, and gaps were identified. In pre-processing and data partitioning, 70% of the data was used for training, and 30% was reserved for testing the developed model. To determine the differences between breeds, evaluations were performed using classical supervised learning algorithms in machine learning. Random forest (RF), support vector machine with radial kernel (SVM-RBF), and the generalized linear model (GLM, logistic regression) were used for model development, while model validation was performed using cross-validation (CV) metrics. After model validation, variable importance, feature selection, correlation analysis, dimensionality reduction, and multicollinearity were performed. The developed model, using morphological measurements obtained from the tarsometatarsus, distinguishes between breeds with high accuracy. The discriminative signal is extremely strong, allowing multiple modeling strategies (tree-based, kernel-based, and linear) to perfectly distinguish between the two breeds. Among the morphometric measurements, Ac (extension of the trochlea metatarsi IV) and Bmit (breadth of the middle trochlea) were found to be the strongest distinguishing features. This developed model combines morphometric data and artificial intelligence to offer an innovative method for scaling, accelerating, or improving applications in science. By expanding the model’s database with measurements obtained from the tarsometatarsus bones of different breeds, it was demonstrated that breed differences can be quickly and accurately determined using a minimal number of measurements from tarsometatarsus bones. Full article

Background: Insufficient physical exercise is a growing public health concern in China, where only 30.3% of adults exercise regularly. Exploring the key factors associated with physical exercise participation is essential for promoting healthier lifestyles. Method: This study utilized data from the 2021 China General Social Survey (CGSS) to apply a progressive framework of dimensionality reduction, machine learning prediction, and SHAP-based interpretability analysis. A total of 19 potential factors were considered, with LassoCV used for feature selection and multiple models constructed for comparison. Results: The SVM model showed the best predictive performance. SHAP analysis revealed that watching sports events, household registration, educational attainment, subjective well-being, smoking, age, sleep quality, social activities, and residence suitability for physical exercise are the most important factors influencing participation. Higher education, greater subjective well-being, urban residency, frequent sports viewing, and residence suitability for physical exercise were positively associated with participation, while smoking and poor sleep quality were negatively associated with it. Conclusion: This study highlights the value of combining machine learning with interpretability methods to uncover the key predictors of physical exercise. The findings provide new evidence on the social, psychological, and environmental factors associated with Chinese adults’ exercise behavior, offering insights for targeted health promotion strategies. Full article

The prediction of chiller performance parameters is crucial for optimal control and fault diagnosis. Numerous efficient and accurate data-driven models have been developed and implemented. These models are normally trained on historical operational data of chiller units. However, the distribution of operational data may shift due to accumulated operating hours or changes in control strategies. Under new operating conditions, models trained on historical data often generalize poorly, leading to prediction deviations. To address this issue, this study integrates a one-dimensional convolutional neural network with a domain adaptation method that extracts features from both the source and target domains and aligns their inverse Gram matrices in terms of angle and scale. A predictive model applicable to multiple chiller performance parameters is established using limited historical data, enhancing the model’s generalization ability. Compared to the baseline model (MLP), the proposed method achieves an average reduction of 74.3% in mean absolute error (MAE) and 76.1% in root mean square error (RMSE), while the R² values exceed 0.96 (for certain scenarios). Additionally, this paper analyzes the data distribution between the source and target domains, investigates key factors affecting the model’s generalization capability, and provides insights for evaluating the quality of modeling data. Full article

Amid the growing global environmental challenges, precise and efficient vehicle emission management plays a critical role in achieving energy-saving and emission reduction goals. At the same time, the rapid development of connected vehicles and autonomous driving technologies has generated a large amount of high-dimensional vehicle operation data. This not only provides a rich data foundation for refined emission accounting but also raises higher demands for the construction of accounting models. Therefore, this study aims to develop an accurate and efficient emission accounting model to contribute to the precise nitrogen oxide (NO_x) emission accounting for hybrid electric vehicles (HEVs). A systematic approach is proposed that combines incremental dimensionality reduction with advanced regression algorithms to achieve refined and efficient emission accounting based on multiple variables. Specifically, the dimensionality of the real driving emission (RDE) data is first reduced using the feature selection and t-distributed stochastic neighbor embedding (t-SNE) feature extraction method to capture key parameter information and reduce subsequent computational complexity. Next, an incremental dimensionality reduction method based on dictionary learning is employed to efficiently embed new data into a low-dimensional space through straightforward matrix operations. Given the computational cost of the dictionary learning training process, this study introduces the FISTA (Fast Iterative Shrinkage-Thresholding Algorithm) for accelerated iterative optimization and enhances the computational efficiency through parameter optimization, while maintaining the accuracy of dictionary learning. Subsequently, an NO_x emission factor correction factor prediction model is trained using the low-dimensional data obtained from t-SNE embeddings, enabling direct computation of the corresponding correction factor when presented with new incremental low-dimensional embeddings. Finally, validation on independent HEV datasets shows that parameter K improves to 1 ± 0.05 and R² increases up to 0.990, laying a foundation for constructing an emission accounting model with broad applicability based on multiple variables. Full article

The cyclic adamantane framework possesses unique properties such as bulkiness, symmetry, and high lipophilicity. Research aimed at discovering new pharmaceutical agents within the adamantane series continues. In the present work, a targeted modification was carried out to combine two pharmacophore fragments—adamantane and piperidine—within a single molecule. Based on a series of N-substituted piperidin-4-ones, the corresponding secondary alcohols were obtained by reduction with sodium borohydride in isopropanol and subsequent acylation of these alcohols with adamantane carbonyl chloride yielded the corresponding adamantane-carboxylate esters. The structure of the synthesized compounds was studied by NMR methods, including COSY (¹H-¹H), HMQC (¹H-¹³C) and HMBC (¹H-¹³C) techniques. The values of chemical shifts, multiplicities, and integrated intensities of ¹H and ¹³C signals in one-dimensional NMR spectra were determined. The results of COSY (¹H-¹H), HMQC (¹H-¹³C), and HMBC (¹H-¹³C) revealed homo- and heteronuclear interactions, confirming the structure of the studied compounds. The cytotoxic activities of the synthesized compounds were studied. It was found that the synthesized substituted piperidines bearing an adamantane fragment exhibit in vitro antimicrobial and antifungal activity against museum microbial strains (Escherichia coli ATCC 8739, Staphylococcus aureus ATCC 6538-P, Candida albicans ATCC 10231, Cryptococcus neoformans) and demonstrate significant advantages over the reference drugs used in clinical practice, such as fluconazole and ampicillin. These compounds are therefore recommended for further in-depth studies. Full article

We aimed to establish a rapid and precise method for identifying and quantifying multi-species vegetable oil (corn oil, olive oil (OLO), soybean oil, and sunflower oil (SUO)) adulterations in camellia oil (CAO), using soft ionization by chemical reaction in transfer–high-resolution mass spectrometry (SICRIT-HRMS) and machine learning methods. The results showed that SICRIT-HRMS could effectively characterize the volatile profiles of pure and adulterated CAO samples, including binary, ternary, quaternary, and quinary adulteration systems. The low m/z region (especially 100–300) exhibited importance to oil classification in multiple feature-selection methods. For qualitative detection, binary classification models based on convolutional neural networks (CNN), Random Forest (RF), and gradient boosting trees (GBT) algorithms showed high accuracies (98.70–100.00%) for identifying CAO adulteration under no dimensionality reduction (NON), principal component analysis (PCA), and uniform manifold approximation and projection (UMAP) strategies. The RF algorithm exhibited relatively high accuracy (96.25–99.45%) in multiclass classification. Moreover, the five models, including CNN, RF, support vector machines (SVM), logistic regression (LR), and GBT, exhibited different performances in distinguishing pure and adulterated CAO. Among 1093 blind oil samples, under NON, PCA, and UMAP: 10, 5, and 67 samples were misclassified by CNN model; 6, 7, and 41 samples were misclassified by RF model; 8, 9, and 82 samples were misclassified by SVM model; 17, 18, and 78 samples were misclassified by LR model; 7, 9, and 43 samples were misclassified by GBT model. For quantitative prediction, the PCA-CNN model performed optimally in predicting adulteration levels in CAO, especially with respect to OLO and SUO, exhibiting a high coefficient of determination for calibration ($R_C^2$, 0.9664–0.9974) and coefficient of determination for prediction ($R_p^2$, 0.9599–0.9963) values, low root mean square error of calibration (RMSEC, 0.9–5.3%) and root mean square error of prediction (RMSEP, 1.1–5.8%) values, and RPD (5.0–16.3) values greater than 3.0. These results indicate that SICRIT-HRMS combined with machine learning can rapidly and accurately identify and quantify multi-species vegetable oil adulterations in CAO, which provides a reference for developing non-targeted and high-throughput detection methods in edible oil authenticity. Full article

Electroencephalography (EEG) provides valuable information about a subject’s mental state; however, developing reliable classification models remains challenging. One major difficulty lies in defining an effective feature representation, as the wide range of features proposed in the literature often leads to high-dimensional inputs, increasing the risk of overfitting, reducing generalization, and raising computational cost. A further critical challenge is the strong inter-subject variability inherent to EEG data, where distributional shifts frequently cause models trained on one individual to perform poorly on unseen subjects. This work proposes a novel family of correlation-based feature selection methods that explicitly models inter-feature relationships through correlation structures. The objective is to identify features that are simultaneously discriminative across mental states (relaxed and concentrated) and invariant across subjects, thereby improving cross-subject generalization. The proposed methods are evaluated against established feature selection and dimensionality reduction techniques using a leave-one-subject-out experimental protocol, in which models are trained on multiple participants and tested on unseen individuals. Experimental results demonstrate that the proposed approach consistently achieves superior or competitive performance compared to existing methods, particularly under strong inter-subject distribution shifts. In addition, the analysis reveals how preprocessing parameters—such as window length, overlap, and frequency band decomposition—affect classification performance and generalization. Unlike previous EEG feature selection approaches that primarily focus on feature relevance or redundancy, the proposed framework explicitly promotes domain invariance while preserving feature interpretability, without relying on subject-specific calibration. Full article

This study presents an optimal design combined with comprehensive multiphysics validation to enhance the torque density of a coaxial magnetic gear (CMG) incorporating an overhang structure. Four high non-integer gear-ratio CMG configurations exceeding 1:10 were designed using different pole-pair combinations, and three-dimensional finite element method (3D FEM) was employed to accurately capture axial leakage flux and overhang-induced three-dimensional effects. Eight key geometric design variables were selected within non-saturating limits, and 150 sampling points were generated using an Optimal Latin Hypercube Design (OLHD). Multiple surrogate models were constructed and evaluated using the root-mean-square error (RMSE), and the Kriging model was selected for multi-objective optimization using a genetic algorithm. The optimized CMG with a 1:10.66 gear ratio achieved a 130.76% increase in average torque (65.75 Nm) and a 162.51% improvement in torque density (117.14 Nm/L) compared with the initial design. Harmonic analysis revealed a strengthened fundamental component and a reduction in total harmonic distortion, indicating improved waveform quality. To ensure the feasibility of the optimized design, comprehensive multiphysics analyses—including electromagnetic–thermal coupled simulation, high-temperature demagnetization analysis, and structural stress evaluation—were conducted. The results confirm that the proposed CMG design maintains adequate thermal stability, magnetic integrity, and mechanical robustness under rated operating conditions. These findings demonstrate that the proposed optimal design approach provides a reliable and effective means of enhancing the torque density of high gear-ratio CMGs, offering practical design guidance for electric mobility, robotics, and renewable energy applications. Full article

Feed formulation is a typical multi-objective optimization problem that aims to minimize cost while satisfying multiple nutritional constraints. However, existing methods often suffer from limitations in handling nonlinear constraints, high-dimensional decision spaces, and solution feasibility. To address these challenges, this study proposes a multi-objective feed formulation method based on an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II). A hybrid Dirichlet–Latin Hypercube Sampling (Dirichlet-LHS) strategy is introduced to generate an initial population with high feasibility and diversity, together with an iterative normalization-based dynamic repair operator to efficiently handle ingredient proportion and nutritional constraints. In addition, an adaptive termination mechanism based on the hypervolume improvement rate (Hypervolume Termination, HVT) is designed to avoid redundant computation while ensuring effective convergence of the Pareto front. Experimental results demonstrate that the Dirichlet–LHS strategy outperforms random sampling, Dirichlet sampling, and Latin hypercube sampling in terms of hypervolume and solution diversity. Under identical nutritional constraints, the improved NSGA-II reduces formulation cost by 1.52% compared with multi-objective Bayesian optimization and by 2.17% relative to conventional feed formulation methods. In a practical application to meat sheep diet formulation, the optimized feed cost is reduced to 1162.23 CNY per ton, achieving a 4.83% cost reduction with only a 1.09 s increase in computation time. These results indicate that the proposed method effectively addresses strongly constrained multi-objective feed formulation problems and provides reliable technical support for precision feeding in intelligent livestock production. Full article