Search Results (442)

This study addresses the challenge of missing numerical values in healthcare datasets by proposing a Particle Swarm Optimization (PSO)-optimized stacking ensemble model for data imputation. The framework combines Random Forest, XGBoost, and Linear Regression within a stacking architecture, with PSO used to optimize model selection and hyperparameters for improved accuracy. The approach was evaluated on the Breast Cancer Wisconsin and Heart Disease datasets under Missing Completely at Random (MCAR) conditions at 30%, 20%, and 10% missingness levels, using RMSE, MAE, R², and processing time as performance metrics. Experimental results show that the proposed model consistently outperforms individual learners across all missingness scenarios, achieving an RMSE of 0.0446, MAE of 0.0303, and R² of 86.56% on the Breast Cancer dataset at 10% MCAR, and an RMSE of 0.1388 with an R² of 75.19% on the Heart Disease dataset. Compared with a MissForest-based existing approach, the proposed framework demonstrates substantial reductions in imputation error, confirming the effectiveness of combining ensemble learning with evolutionary optimization. Although the PSO-based stacking model incurs higher computational cost, the findings indicate that it provides a robust, accurate, and generalizable solution for numerical data imputation in healthcare applications under varying levels of missingness. Full article

To address the data quality challenges in ship maintenance data, such as high missing rates, anomalous noise, and multi-source heterogeneity, this paper proposes a data quality enhancement method based on a multi-strategy enhanced Harris Hawks Optimization algorithm for optimizing the Kolmogorov–Arnold Stacked Denoising Autoencoder. First, leveraging the Kolmogorov–Arnold theory, the fixed activation functions of the traditional Stacked Denoising Autoencoder are reconstructed into self-learnable B-spline basis functions. Combined with a grid expansion technique, the KASDAE model is constructed, significantly enhancing its capability to represent complex nonlinear features. Second, the Harris Hawks Optimization algorithm is enhanced by incorporating a Logistic–Tent compound chaotic map, an elite hierarchy strategy, and a nonlinear logarithmic decay mechanism. These improvements effectively balance global exploration and local exploitation, thereby increasing the convergence accuracy and stability for hyperparameter optimization. Building on this, an IHHO-KASDAE collaborative cleaning framework is established to achieve the repair of anomalous data and the imputation of missing values. Experimental results on a real-world ship maintenance dataset demonstrate the effectiveness of the proposed method: it achieves an 18.3% reduction in reconstruction mean squared error under a 20% missing rate compared to the best baseline method; attains an F1-score of 0.89 and an AUC value of 0.929 under a 20% anomaly rate; and stabilizes the final fitness value of the IHHO optimizer at 0.0216, which represents improvements of 31.7%, 25.6%, and 12.2% over the Particle Swarm Optimization, Differential Evolution, and the original HHO algorithm, respectively. The proposed method outperforms traditional statistical methods, deep learning models, and other intelligent optimization algorithms in terms of reconstruction accuracy, anomaly detection robustness, and algorithmic convergence stability, thereby providing a high-quality data foundation for subsequent applications such as maintenance cost prediction and fault diagnosis. Full article

Solution-processed OLEDs represent a low-cost, scalable alternative to vacuum-deposited devices, particularly for flexible and large-scale applications. However, selecting compatible materials for each layer remains a complex task, further complicated by inconsistent documentation, solvent interactions, and limited reproducibility across the literature. This work presents a literature review and critical analysis of materials, solvents, and fabrication methods involved in solution-processed OLEDs, with particular attention to layer formulation, solvent orthogonality, and processing constraints. A Monte Carlo-based optimization framework is introduced as a proof of concept, aiming to formalize stack selection and explore viable combinations based on empirical constraints. The critical analysis highlights recurring issues in the field and advocates for a more structured, reproducibility-oriented approach to OLED design. Full article

Accurate and non-destructive assessment of plant nutritional status remains a key challenge in precision agriculture, particularly under dynamic physiological conditions such as dehydration. Therefore, this study focused on developing an integrated nutritional assessment framework for avocado (Persea americana Mill.) leaves across progressive dehydration stages using spectral analysis. A novel nutritional function index (NFI) was innovatively constructed using an entropy-weighted multi-criteria decision-making approach. This unified assessment metric integrated critical physiological indicators, such as moisture content, nitrogen content, and chlorophyll content estimated from soil and plant analyzer development (SPAD) readings. To enhance the prediction accuracy and interpretability of NFI, innovative vegetation indices (VIs) specifically tailored to NFI were systematically constructed using exhaustive wavelength-combination screening. Optimal wavelengths identified from short-wave infrared regions (1446, 1455, 1465, 1865, and 1937 nm) were employed to build physiologically meaningful VIs, which were highly sensitive to moisture and biochemical constituents. Feature wavelengths selected via the successive projections algorithm and competitive adaptive reweighted sampling further reduced spectral redundancy and improved modeling efficiency. Both feature-level and algorithm-level data fusion methods effectively combined VIs and selected feature wavelengths, significantly enhancing prediction performance. The stacking algorithm demonstrated robust performance, achieving the highest predictive accuracy (R2V = 0.986, RMSEV = 0.032) for NFI estimation. This fusion-based modeling approach outperformed conventional single-model schemes in terms of accuracy and robustness. Unlike previous studies that focused on isolated spectral predictors, this work introduces an integrative framework combining entropy-weighted feature synthesis and multiscale fusion learning. The developed strategy offers a powerful tool for real-time plant health monitoring and supports precision agricultural decision-making. Full article

This study presents a hybrid analytical framework that enhances project selection by achieving reasonable predictive accuracy through the integration of expert judgment and modern artificial intelligence (AI) techniques. Using an enterprise-level dataset of 10,000 completed software projects with verified real-world statistical characteristics, we develop a three-step architecture for intelligent decision support. First, we introduce an extended Analytic Hierarchy Process (AHP) that incorporates organizational learning patterns to compute expert-validated criteria weights with a consistent level of reliability ($CR=0.04$), and Linear Programming is used for portfolio optimization. Second, we propose a machine learning architecture that integrates expert knowledge derived from AHP into models such as Transformers, TabNet, and Neural Oblivious Decision Ensembles through mechanisms including attention modulation, split criterion weighting, and differentiable tree regularization. Third, the hybrid AHP-Stacking classifier generates a meta-ensemble that adaptively balances expert-derived information with data-driven patterns. The analysis shows that the model achieves 97.5% accuracy, a 96.9% F1-score, and a 0.989 AUC-ROC, representing a 25% improvement compared to baseline methods. The framework also indicates a projected 68.2% improvement in portfolio value (estimated incremental value of USD 83.5 M) based on post factum financial results from the enterprise’s ventures.This study is evaluated retrospectively using data from a single enterprise, and while the results demonstrate strong robustness, generalizability to other organizational contexts requires further validation. This research contributes a structured approach to hybrid intelligent systems and demonstrates that combining expert knowledge with machine learning can provide reliable, transparent, and high-performing decision-support capabilities for project portfolio management. Full article

In pellet production, the uniformity of material distribution directly affects the subsequent roasting effect and the quality of finished products. Aiming at the problems of uneven distribution in traditional shuttle distribution systems, such as material stacking at both ends of the wide belt, insufficient parameter matching leading to uneven distribution, and reliance on manual adjustment which makes it difficult to adapt to dynamic working conditions, this paper proposes an intelligent control method based on Integral Simulation and Gradient Descent optimization (IS-GD). Firstly, this method combines the structure and operating parameters of the distribution equipment and accurately simulates the material distribution law on the wide belt during the reciprocating movement of the shuttle through integral technology. Based on the simulation results, longitudinal and lateral uniformity discriminant functions are constructed, and a phased gradient descent optimization strategy is adopted to dynamically adjust the shuttle belt speed, walking speed, and operating parameters of each stage with the goal of minimizing the uniformity index. Experimental results show that this method achieves a significant improvement in lateral distribution uniformity without affecting the stability of longitudinal distribution. This research provides reliable technical support for intelligent distribution control in pellet production and helps to improve the roasting quality and production efficiency of pellets. Full article

Ge-doped CIGSe absorbers were fabricated using a two-step process of depositing sputtered stacked Ge-doped CIGSe precursors and selenization annealing. The effects of Ge doping on the crystallinity as well as defects of CIGSe absorbers and the performance of CIGSe buffer-free solar cells were investigated. The results show that Ge doping significantly promotes the grain growth of CIGSe absorbers. Due to Ge loss via volatilization during selenization annealing, Ge residue is undetectable in Ge-doped absorbers. Ge doping offers an effective approach to improve CIGSe crystallinity without introducing notable impurity phases or Ge-related defects. However, Ge doping also induces Se loss, and excessive Se vacancy defects adversely affect the performance of the absorber. In addition, Ge doping increases the contact potential difference at CIGSe grain boundaries and is beneficial for reducing carrier recombination at these sites. Analysis of recombination rates in Ge-doped CIGSe buffer-free solar cells reveals that the combined effects of enhanced crystallinity and optimized electrical properties at grain boundaries effectively suppress the recombination in the space charge region, at the interface, and in the quasi-neutral region, leading to improved device performance. 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

Accurate lithologic maps derived from satellite imagery underpin structural interpretation, mineral exploration, and geohazard assessment. However, automated mapping in complex terranes remains challenging because spectrally similar units, narrow anisotropic bodies, and ambiguous contacts can degrade boundary fidelity. In this study, we propose SegNeXt-HFCA, a hierarchical multiscale fusion network with coordinate attention for lithologic segmentation from a Sentinel-2/DEM feature stack. The model builds on SegNeXt and introduces a hierarchical multiscale encoder with coordinate attention to jointly capture fine textures and scene-level structure. It further adopts a class-frequency-aware hybrid loss that combines boundary-weighted online hard-example mining cross-entropy with Lovász-Softmax to better handle long-tailed classes and ambiguous contacts. In addition, we employ a robust training and inference scheme, including entropy-guided patch sampling, exponential moving average of parameters, test-time augmentation, and a DenseCRF-based post-refinement. Two study areas in the Beishan orogen, northwestern China (Huitongshan and Xingxingxia), are used to evaluate the method with a unified 10-channel Sentinel-2/DEM feature stack. Compared with U-NetFormer, PSPNet, DeepLabV3+, DANet, LGMSFNet, SegFormer, BiSeNetV2, and the SegNeXt backbone, SegNeXt-HFCA improves mean intersection-over-union (mIoU) by about 3.8% in Huitongshan and 2.6% in Xingxingxia, respectively, and increases mean pixel accuracy by approximately 3–4%. Qualitative analyses show that the proposed framework better preserves thin-unit continuity, clarifies lithologic contacts, and reduces salt-and-pepper noise, yielding geologically more plausible maps. These results demonstrate that hierarchical multiscale fusion with coordinate attention, together with class- and boundary-aware optimization, provides a practical route to robust lithologic mapping in structurally complex regions. Full article

This study proposes a circular economy strategy to recover phenolic compounds by valorizing shrimp shell waste into a chitosan biosorbent (CH-B). Its adsorption efficiency was evaluated compared to commercial activated carbon (AC) and synthetic XAD-4 resin. Kinetic analysis revealed that while both pseudo-first-order (PFO) and pseudo-second-order (PSO) models exhibited high correlations (R²$\ge$ 0.96), both CH-B and XAD-4 resin were best described by the PFO model. This aligns with diffusion-controlled processes consistent with the porous and physical nature of these adsorbents. In contrast, AC followed the PSO model. Isotherm modeling indicated that CH-B and AC fit the Temkin model, reflecting heterogeneous surfaces, whereas XAD-4 followed the Langmuir model (monolayer adsorption). Notably, CH-B exhibited a maximum adsorption capacity (q_m) of 229.2 mg/g, significantly outperforming XAD-4 (104.8 mg/g) and AC (90.2 mg/g). Thermodynamic and kinetic modeling confirmed that the adsorption mechanism was governed by a combination of electrostatic interactions, π–π stacking, and hydrogen bonding between the hydroxyl/amine groups of chitosan and phenolic compounds. Optimization using Box–Behnken design for CH-B showed optimal acidic pH and moderate temperature but non-significant effect of CH-B dose in the experimental domain. Optimisation results showed unexpected high removal efficiency at low CH-B dosages. A tentative explanation may be adsorbent aggre-gation, which needs to be confirmed by further experimental evidence. Full article

The V/G criterion is a critical indicator for monitoring dynamic changes during Czochralski silicon single crystal (Cz-SSC) growth. However, the inability to measure it in real time forces reliance on offline feedback for process regulation, leading to imprecise control and compromised crystal quality. To overcome this limitation, this paper proposes a novel soft sensor modeling framework that integrates both mechanism-based knowledge and data-driven learning for the real-time prediction of the crystal quality parameter, specifically the V/G value (the ratio of growth rate to axial temperature gradient). The proposed approach constructs a hybrid prediction model by combining a data-driven sub-model with a physics-informed mechanism sub-model. The data-driven component is developed using an attention-based dynamic stacked enhanced autoencoder (AD-SEAE) network, where the SEAE structure introduces layer-wise reconstruction operations to mitigate information loss during hierarchical feature extraction. Furthermore, an attention mechanism is incorporated to dynamically weigh historical and current samples, thereby enhancing the temporal representation of process dynamics. In addition, a robust ensemble approach is achieved by fusing the outputs of two subsidiary models using an adaptive weighting strategy based on prediction accuracy, thereby enabling more reliable V/G predictions under varying operational conditions. Experimental validation using actual industrial Cz-SSC production data demonstrates that the proposed method achieves high-prediction accuracy and effectively supports real-time process optimization and quality monitoring. Full article

Land seismic data are always contaminated by surface waves, which demonstrate strong energy, low velocity, and long vibrations. Such noises often mask deep effective reflections, seriously reducing the data’s signal-to-noise ratio while limiting the imaging accuracy of complex deep structures and the efficiency of hydrocarbon reservoir identification. To address this critical technical bottleneck, this paper proposes a surface wave joint reconstruction method based on stationary phase analysis, combining the cross-correlation seismic interferometry method with the convolutional seismic interferometry method. This approach integrates cross-correlation and convolutional seismic interferometry techniques to achieve coordinated reconstruction of surface waves in both shot and receiver domains while introducing adaptive weight factors to optimize the reconstruction process and reduce interference from erroneous data. As a purely data-driven framework, this method does not rely on underground medium velocity models, achieving efficient noise reduction by adaptively removing reconstructed surface waves through multi-channel matched filtering. Application validation with field seismic data from the piedmont regions of western China demonstrates that this method effectively suppresses high-energy surface waves, significantly restores effective signals, improves the signal-to-noise ratio of seismic data, and greatly enhances the clarity of coherent events in stacked profiles. This study provides a reliable technical approach for noise reduction in seismic data under complex near-surface conditions, particularly suitable for hydrocarbon exploration in regions with developed scattering sources such as mountainous areas in western China. It holds significant practical application value and broad dissemination potential for advancing deep hydrocarbon resource exploration and improving the quality of complex structural imaging. Full article

Tylorrhynchus heterochaetus is an aquatic food with both edible and medicinal value in China. With a protein-rich body wall, it has strong potential for producing bioactive peptides. To explore its potential as a source of immunomodulatory peptides, in this study, flavor enzymes were selected as the optimal hydrolases, and the hydrolyzed products were subjected to ultrafiltration fractionation. The <3000 Da portion exhibited the most effective immune-stimulating activity in RAW 264.7 macrophages, enhancing phagocytosis and promoting the secretion of tumor necrosis factor-alpha (TNF-α), interleukin-6 (IL-6) and nitric oxide (NO) in a concentration dependent manner. Peptide omics analysis, combined with the activity and safety screened by bioinformatics, identified 43 candidate peptides. Molecular docking predicts that three novel peptides, LPWDPL, DDFVFLR and LPVGPLFN, exhibit strong binding affinity with toll-like receptor 4/myeloid differentiation factor-2 (TLR4/MD-2) receptors through hydrogen bonding and hydrophobic/π stacking interactions. Synthetic verification confirmed that these peptides were not only non-toxic to cells at concentrations ranging from 62.5 to 1000 µg/mL, but also effective in activating macrophages and stimulating the release of immune mediators. This study successfully identified the specific immunomodulatory peptides of the Tylorrhynchus heterochaetus, supporting its high-value utilization as a natural source of raw materials for immunomodulatory functional foods. Full article

Effective and transparent medical diagnosis relies on accurate and interpretable classification of medical images across multiple modalities. This paper introduces an explainable multi-modal image analysis framework based on a dual-stream architecture that fuses handcrafted descriptors with deep features extracted from a custom MobileNet. Handcrafted descriptors include frequency-domain and texture features, while deep features are summarized using 26 statistical metrics to enhance interpretability. In the fusion stage, complementary features are combined at both the feature and decision levels. Decision-level integration combines calibrated soft voting, weighted voting, and stacking ensembles with optimized classifiers, including decision trees, random forests, gradient boosting, and logistic regression. To further refine performance, a hybrid class-specific feature selection strategy is proposed, combining mutual information, recursive elimination, and random forest importance to select the most discriminative features for each class. This hybrid selection approach eliminates redundancy, improves computational efficiency, and ensures robust classification. Explainability is provided through Local Interpretable Model-Agnostic Explanations, which offer transparent details about the ensemble model’s predictions and link influential handcrafted features to clinically meaningful image characteristics. The framework is validated on three benchmark datasets, i.e., BTTypes (brain MRI), Ultrasound Breast Images, and ACRIMA Retinal Fundus Images, demonstrating generalizability across modalities (MRI, ultrasound, retinal fundus) and disease categories (brain tumor, breast cancer, glaucoma). Full article

Nitrogen control in steel production critically influences mechanical properties and product quality, yet traditional mechanistic models struggle to capture complex multivariable interactions across the complete steelmaking chain. This study developed and validated automated machine learning (AutoML) models using Microsoft Azure Machine Learning Studio to predict nitrogen content at four critical stages: desulfurization of pig iron (Stage 1), basic oxygen furnace prior to tapping (Stage 2), secondary steelmaking initiation (Stage 3), and secondary steelmaking finishing (Stage 4). Industrial data from 291 metal samples across 76 heats were collected and processed, with stage-specific models employing stack ensemble architectures combining 4–7 algorithms with feature sets ranging from 12 to 35 variables. The models achieved normalized root mean squared errors between 0.112–0.149, mean absolute percentage errors of 14.6–21.1%, and Spearman correlations of 0.310–0.587, with secondary steelmaking models demonstrating superior performance due to more controlled thermodynamic conditions. All models achieved sub-second prediction latencies suitable for real-time industrial implementation. This research demonstrates that AutoML effectively captures complex physicochemical relationships governing nitrogen behavior throughout the steelmaking process, providing practical solutions for Industry 4.0 applications in steelmaking process control and quality optimization. Full article