Search Results (17,915)

The K-means clustering algorithm is widely applied in various clustering tasks due to its high computational efficiency and simple implementation. However, its performance significantly deteriorates when dealing with non-convex structures, fuzzy boundaries, or noisy data, as it relies on the assumption that clusters are spherical or linearly separable. To address these limitations, this paper proposes a Gaussian membership-driven fuzzy granular K-means clustering method. In this approach, multi-function Gaussian membership functions are used for fuzzy granulation at the single-feature level to generate fuzzy granules, while fuzzy granule vectors are constructed in the multi-feature space. A novel distance metric for fuzzy granules is defined along with operational rules, for which axiomatic proof is provided. This Gaussian-based granulation enables effective modeling of nonlinear separability in complex data structures, leading to the development of a new fuzzy granular K-means clustering framework. Experimental results on multiple public UCI datasets demonstrate that the proposed method significantly outperforms traditional K-means and other baseline methods in clustering tasks involving complex geometric data (e.g., circular and spiral structures), showing improved robustness and adaptability. This offers an effective solution for clustering data with intricate distributions. Full article

The mapping of vineyard cultivars presents a substantial challenge in digital agriculture due to the crop’s high intra-class heterogeneity and low inter-class variability. High-dimensional spectral datasets, such as hyperspectral or spectrometry data, can overcome these difficulties. However, research has yet to fully address the need for optimal spectral feature subsets tailored for grapevine cultivar discrimination, while few studies have systematically examined waveband subsets that transfer effectively across different learning algorithms. This study sets out to address these gaps by introducing a Partial Least Squares (PLS)-based ensemble feature selection framework with Weighted Borda Count aggregation for cultivar discrimination. Using in-field spectrometry data, collected for six cultivars, and 18 PLS-based feature selection methods spanning filter, wrapper, and hybrid approaches, the PLS–ensemble identified 100 wavebands most relevant for cultivar discrimination, reducing dimensionality by ~95%. The efficacy and transferability of this subset were evaluated using five classification algorithms: Oblique Random Forest (oRF), Multinomial Logistic Regression (Multinom), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (CNN). For oRF, Multinom, SVM, and MLP, the PLS–ensemble subset improved accuracy by 0.3–12% compared with using all wavebands. The subset was not optimal for the 1D-CNN, where accuracy decreased by up to 5.7%. Additionally, this study investigated waveband binning to transform narrow hyperspectral bands into broadband spectral features. Using feature multicollinearity and wavelength position, the 100 selected wavebands were condensed into 10 broadband features, which improved accuracy over both the full dataset and the original subset, delivering gains of 4.5–19.1%. The SVM model with this 10-feature subset outperformed all other models (F1: 1.00; BACC: 0.98; MCC: 0.78; AUC: 0.95). Full article

Magnetorheological (MR) materials, with the ability of vectorial response, offer exciting opportunities for next-generation wearables and soft robotic systems. Although some existing MR materials and fiber designs can produce directional responses, they typically rely on strategies—such as hard-magnetic loading or pre-magnetization—that constrain safety and large-scale manufacturability. This Communication highlights a paradigm-shifting advance reported by Pu et al., that a soft-magnetic fibrous architecture achieves genuine vector-stimuli-responsiveness under low, safe magnetic fields without pre-magnetization. We articulate the great breakthrough of this work through a hierarchical design framework, demonstrating how the synergistic innovation at the material (magnetic dipole aligned in low-density polyethylene), fiber (drawing-induced magnetic easy axis), yarn (twist-induced cooperative effects), and fabric (vertical or horizontal magnetic field response capability) levels collectively resolves the longstanding trade-offs between performance, manufacturability, and safety. As a result, this strategy demonstrates strong universality in terms of materials, although only the carbonyl iron particles were used. This approach not only enables programmable bending, stiffening, shear, and compression in textiles but also establishes a versatile platform for magneto-programmable systems. Furthermore, we delineate the critical challenges and future trajectories—from theoretical modeling and integration of complementary stimuli to the development of three-dimensional textile architectures—that this new platform opens for the fields of haptics, soft robotics, and adaptive wearables. Full article

This paper examines how data preparation affects machine-learning classifiers for diabetes-risk prediction using the Pima Indians Diabetes Database. Three preprocessing methods are considered: imputing invalid zeros, handling outliers, and data scaling. Nine algorithms are evaluated on this dataset: linear/probabilistic baselines (Logistic Regression, Gaussian Naive Bayes), distance-based methods (KNN, Support Vector Machines), a single tree-based model (Decision Tree), and tree ensembles (Random Forest, Gradient Boosting, XGBClassifier, LightGBM). Median imputation of invalid zeros yields the largest and most consistent gains in accuracy and AUC. Outlier handling uses interquartile-range filtering, with Local Outlier Factor as an auxiliary indicator; effects are modest for accuracy and small, model-dependent for AUC. Scaling offers targeted benefits: for KNN, robust scaling can slightly alter performance and may reduce AUC relative to median-only imputation in this setup; SVM shows modest gains, while tree ensembles are comparatively insensitive overall. Ensembles achieve the highest performance and remain robust under minimal preparation, while simpler models benefit most from pipelines combining median imputation, careful outlier handling, and appropriate scaling. Hyperparameter tuning yields small to substantial gains—large for Decision Trees—while leaving ensemble rankings largely unchanged. Overall, results highlight the centrality of median imputation and the selective value of scaling for distance-based classifiers in diabetes-risk prediction. Full article

Particulate Matter (PM) is a type of air pollution that poses risks to human health, the environment, and property. Among the various PM types, PM₁₀ is particularly significant, as it acts as a vector for numerous hazardous trace elements that can negatively impact human health and the ecosystem. Identifying potential sources of PM₁₀ and quantifying their impact on ambient concentrations is crucial for developing efficient control strategies to meet threshold values. Receptor modeling, which identifies sources using chemical species information derived from PM samples, has been widely used for source apportionment. In this study, PM₁₀ samples were collected over three periods (April, May, and June 2021), each lasting 16 days, using semi-automatic dust sampling systems at two sites in Biga, Canakkale, Turkiye. The relative contributions of different source types were quantified using EPA PMF (Positive Matrix Factorization) based on 35 elements comprising PM₁₀. As a result of the analysis, five source types were identified: crustal elements/limestone/calcite quarry (64.9%), coal-fired power plants (11.2%), metal industry (9%), sea salt and ship emissions (8.5%), and road traffic emissions and road dust (6.3%). The distribution of source contributions aligned with the locations of identified sources in the region. Full article

This work implements deep learning models to capture non-linear and complex data behavior in aluminum price data. Deep learning models include the long short-term memory (LSTM) and deep feedforward neural networks (FFNN). The support vector regression (SVR) is employed as a base model for comparison. Each predictive model is tuned by using two different optimization methods: Bayesian optimization (BO) and random search (RS). All models are tested on daily, weekly, and monthly data. Three performance metrics are used to evaluate each forecasting model: the root mean squared error (RMSE), mean absolute error (MAE), and the coefficient of determination (R²). The experimental results show that the LSTM-BO is the best-performing model across the time horizons (daily, weekly, and monthly). By consistently achieving the lowest RMSE, MAE, and highest R², the LSTM-BO outperformed all the other models, including SVR-BO, FFNN-BO, LSTM-RS, SVR-RS, and FFNN-RS. In addition, predictive models utilizing BO regularly outperformed those using RS. In summary, LSTM-BO is highly beneficial for aluminum spot price forecasting. Full article

This study proposes and evaluates a data-driven framework for short-term System Marginal Price (SMP) forecasting in the Chilean National Electric System (NES), a power system characterized by high penetration of variable renewable generation and persistent transmission congestion. Using publicly available hourly operational data for 2024, multiple machine learning regressors including Linear Regression (base case), Bayesian Ridge, Automatic Relevance Determination, Decision Trees, Random Forests, and Support Vector Regression are implemented under a node-specific modeling strategy. Two alternative approaches for predictor selection are compared: a system-wide methodology that exploits lagged SMP information from all network nodes; and a spatially filtered methodology that restricts SMP inputs to correlated subsystems identified through nodal correlation analysis. Model robustness is explicitly assessed by reserving January and July as out-of-sample test periods, capturing contrasting summer and winter operating conditions. Forecasting performance is analyzed for representative nodes located in the northern, central, and southern zones of the NES, which exhibit markedly different congestion levels and generation mixes. Results indicate that non-linear and ensemble models, particularly Random Forest and Support Vector Regression, provide the most accurate forecasts in well-connected areas, achieving mean absolute errors close to 10 USD/MWh. In contrast, forecast errors increase substantially in highly congested southern zones, reflecting the structural influence of transmission constraints on price formation. While average performance differences between M1 and M2 are modest, a paired Wilcoxon signed-rank test reveals statistically significant improvements with M2 in highly congested zones, where M2 yields lower absolute errors for most models, despite relying on fewer inputs. These findings highlight the importance of congestion-aware feature selection for reliable price forecasting in renewable-intensive systems. Full article

Non-invasive electrocardiogram (ECG) and respiratory signals are easy to acquire via low-cost sensors, making them promising alternatives for sleep staging. However, existing methods using these signals often yield insufficient accuracy. To address this challenge, we incrementally optimized the sleep staging model by designing a structured experimental workflow: we first preprocessed respiratory and ECG signals, then extracted fused features using an enhanced feature selection technique, which not only reduces redundant features, but also significantly improves the class discriminability of features. The resulting fused features serve as a reliable feature subset for the classifier. In the meantime, we proposed a hybrid optimization algorithm that integrates the snake optimization algorithm (SO) and ant colony optimization algorithm (ACO) for automated hyperparameter optimization of support vector machines (SVMs). Experiments were conducted using two PSG-derived public datasets, the Sleep Heart Health Study (SHHS) and MIT-BIH Polysomnography Database (MIT-BPD), to evaluate the classification performance of multimodal features compared with single-modal features. Results demonstrate that the bimodal staging using SHHS multimodal signals significantly outperformed single-modal ECG-based methods, and the overall accuracy of the SHHS dataset was improved by 12%. The SVM model optimized using the hybrid Snake–ACO algorithm achieved an average accuracy of 89.6% for wake versus sleep classification on the SHHS dataset, representing a 5.1% improvement over traditional grid search methods. Under the subject-independent partitioning experiment, the wake versus sleep classification task maintained good stability with only a 1.8% reduction in accuracy. This study provides novel insights for non-invasive sleep monitoring and clinical decision support. Full article

It is a challenge to identify food waste sources in all-weather industrial environments, as variable lighting conditions can compromise the effectiveness of visual recognition models. This study proposes and validates a robust, interpretable, and adaptive multimodal logic fusion method in which sensor dominance is dynamically assigned based on real-time illuminance intensity. The method comprises two foundational components: (1) a lightweight MobileNetV3 + EMA model for image recognition; and (2) an audio model employing Fast Fourier Transform (FFT) for feature extraction and Support Vector Machine (SVM) for classification. The key contribution of this system lies in its environment-aware conditional logic. The image model MobileNetV3 + EMA achieves an accuracy of 99.46% within the optimal brightness range (120–240 cd m⁻²), significantly outperforming the audio model. However, its performance degrades significantly outside the optimal range, while the audio model maintains an illumination-independent accuracy of 0.80, a recall of 0.78, and an F1 score of 0.80. When light intensity falls below the threshold of 84 cd m⁻², the audio recognition results take precedence. This strategy ensures robust classification accuracy under variable environmental conditions, preventing model failure. Validated on an independent test set, the fusion method achieves an overall accuracy of 90.25%, providing an interpretable and resilient solution for real-world industrial deployment. Full article

In this study, linear and nonlinear parametric models (M1–M6) were jointly evaluated alongside machine learning (ML)-based approaches to achieve reliable and interpretable prediction of the penetration rate (ROP) of tunnel boring machines (TBMs). The analyses incorporate key geomechanical and structural variables, including the brittleness index (BI), uniaxial compressive strength (UCS), mean spacing of weakness planes (DPW), the angle between the tunnel axis and weakness planes (α), and Brazilian tensile strength (BTS). The coefficients of the parametric models were optimized using the Differential Evolution (DE) algorithm. Variable effects were systematically examined through Jacobian-based elasticity analysis under both original and standardized data scenarios. The results indicate that the M6 model, which explicitly incorporates interaction terms, delivers superior predictive accuracy and a more balanced, physically meaningful representation of variable contributions compared to widely used parametric formulations reported in the literature. While the dominant influence of BI and UCS on ROP is consistently preserved across all models, the indirect contributions of variables such as DPW and BTS are more clearly revealed in M6 owing to its interaction-based structure. Model performance improves systematically with increasing complexity, with the coefficient of determination (R²) rising from 0.62 for M1 to 0.69 for M6. Relative to the linear model, M6 achieves a 9.07% reduction in RMSE and a 10.48% increase in R², while providing additional improvements of 2.47% in RMSE and 2.37% in R² compared with the closest competing model. ML-based variable importance analyses are largely consistent with the parametric findings, highlighting BI and α in tree-based models, and UCS and α in SVM and GAM frameworks. Notably, the GAM exhibits the highest predictive performance under both data scenarios. Overall, the integrated use of parametric and ML approaches establishes a robust hybrid modeling framework that enables highly accurate and engineering-interpretable prediction of TBM penetration rate. Full article

The pressure-gradient Micro-Electro-Mechanical Systems (MEMS) vector hydrophone is a novel type of sensor capable of simultaneously acquiring both scalar and vectorial information within an acoustic field. Conventional azimuth estimation methods struggle to achieve high-resolution localization using a single pressure-gradient MEMS vector hydrophone. In practical marine environments, the multiple signal classification (MUSIC) algorithm is hampered by significant resolution performance loss. Similarly, the complex acoustic intensity (CAI) method is constrained by a high-resolution threshold for multiple targets, often resulting in inaccurate azimuth estimates. Therefore, a cross-spectral model between the acoustic pressure and the particle velocity for the pressure-gradient MEMS vector hydrophone was established. Integrated with an improved particle swarm optimization (IPSO) algorithm, a high-resolution azimuth estimation method utilizing this hydrophone is proposed. Furthermore, the corresponding Cramér-Rao Bound is derived. Simulation results demonstrate that the proposed algorithm accurately resolves two targets separated by only 5° at a low signal-to-noise ratio (SNR) of 5 dB, boasting a root mean square error of approximately 0.35° and a 100% success rate. Compared with the CAI method and the MUSIC algorithm, the proposed method achieves a lower resolution threshold and higher estimation accuracy, alongside low computational complexity that enables efficient real-time processing. Field tests in an actual seawater environment validate the algorithm’s high-resolution performance as predicted by simulations, thus confirming its practical efficacy. The proposed algorithm addresses key limitations in underwater detection by enhancing system robustness and offering high-resolution azimuth estimation. This capability holds promise for extending to multi-target scenarios in complex marine settings. Full article

Radiation-induced transient faults pose a growing challenge for safety-critical embedded systems, yet traditional radiation testing and large-scale statistical fault injection (SFI) remain costly and impractical during early design stages. This paper presents a predictive approach for early reliability assessment that replaces handcrafted feature engineering with automatically learned vector representations of source code and execution traces. We derive multiple embeddings for traces and source code, and use them as inputs to a family of regression models, including ensemble methods and linear baselines, to build predictive models for reliability. Experimental evaluation shows that embedding-based models outperform prior approaches, reducing the mean absolute percentage error (MAPE) from 6.24% to 2.14% for correct executions (unACE), from 20.95% to 10.40% for Hangs, and from 49.09% to 37.69% for silent data corruptions (SDC) after excluding benchmarks with SDC below 1%. These results show that source code and trace embeddings can serve as effective estimators for expensive fault injection campaigns, enabling early-stage reliability assessment in radiation-exposed embedded systems without requiring any manual feature engineering. This capability provides a practical foundation for supporting design-space exploration during early development phases. Full article

Refill Friction Stir Spot Welding (RFSSW) provides significant advantages over competing spot joining technologies, but detecting RFSSW’s often small and subtle defects remains challenging. In this study, kinematic feedback data from a RFSSW machine’s factory-installed sensors was used to successfully predict defect presence with 96% accuracy (F1 = 0.92) and preliminary multi-class defect diagnosis with 84% accuracy (F1 = 0.82). Thirty adverse treatments (e.g., contaminated coupons, worn tools, and incorrect material thickness) were carried out to create 300 potentially defective welds, plus control welds, which were then evaluated using profilometry, computed tomography (CT) scanning, cutting and polishing, and tensile testing. Various machine learning (ML) models were trained and compared on statistical features, with support vector machine (SVM) achieving top performance on final quality prediction (binary), random forest outperforming other models in classifying welds into six diagnosis categories (plus a control category) based on the adverse treatments. Key predictors linking process signals to defect formation were identified, such as minimum spindle torque during the plunge phase. In conclusion a framework is proposed to integrate these models into a manufacturing setting for low-cost, full-coverage evaluation of RFSSWs. Full article

Accurate estimation of crop evapotranspiration (ET) is essential for achieving efficient agricultural water use in the North China Plain. Although machine learning techniques have demonstrated considerable potential for ET simulation, a systematic evaluation of model-architecture suitability and hyperparameter optimization strategies specifically for summer soybean ET estimation in this region is still lacking. To address this gap, we systematically compared several machine learning architectures and their hyperparameter optimization schemes to develop a high-accuracy daily ET model for summer soybean in the North China Plain. Synchronous observations from a large-scale weighing lysimeter and an automatic weather station were first used to characterize the day-to-day dynamics of soybean ET and to identify the key driving variables. Four algorithms—support vector regression (SVR), Random Forest (RF), extreme gradient boosting (XGBoost), and a stacking ensemble—were then trained for ET simulation, while Particle Swarm Optimization (PSO), Genetic Algorithms (GAs), and Randomized Grid Search (RGS) were employed for hyperparameter tuning. Results show that solar radiation (R_S), maximum air temperature (T_max), and leaf area index (LAI) are the dominant drivers of ET. The Stacking-PSO-F3 combination, forced with Rs, T_max, LAI, maximum relative humidity (RH_max), and minimum relative humidity (RH_min), achieved the highest accuracy, yielding R² values of 0.948 on the test set and 0.900 in interannual validation, thereby demonstrating excellent precision, stability, and generalizability. The proposed model provides a robust technical tool for precision irrigation and regional water resource optimization. Full article

In this paper, two improvements in precipitation classification have been performed. Supervised machine learning has demonstrated considerable performances in classification tasks. However, supervised machine learning can only be applied to labeled data. In some cases, large amounts of unlabeled data contain valuable information for better classification. In the classification of precipitation intensities from satellite images, unlabeled data constitute the majority and remain largely unexplored. To exploit both labeled and unlabeled data, a Semi-Supervised Support Vector Machine (S3VM) is implemented as the first improvement for classification results. The labeling of the limited available data is derived from radar measurements covering a small portion of the Meteosat Second Generation Satellite observations. The results show that the S3VM model outperforms the standard SVM model, with up to a 15% improvement in classification accuracy compared to the standard SVM. To achieve the second improvement, the S3VM was combined with the Firefly Algorithm (FFA) to optimize its hyperparameters. This hybridization (S3VM-FFA) enabled an even more robust performance. A comparative study showed that the S3VM-FFA approach yielded highly satisfactory results, achieving a 17% improvement in classification compared to the SVM results. Based on these classifications, precipitation quantities at different scales are estimated. Similarly to the classification results, statistical evaluation parameters indicate that the S3VM-FFA outperforms both the standard SVM and the conventional S3VM. Full article