Search Results (89)

Accurate scrap forecasting is essential for advancing green manufacturing, as reducing defective output not only lowers production costs but also prevents unnecessary resource consumption and environmental impact. Effective scrap prediction enables manufacturers to take proactive measures to minimize waste generation, thereby supporting sustainability goals and improving production efficiency. This study proposes a hybrid ensemble framework that integrates CatBoost and XGBoost, combined with Particle Swarm Optimization (PSO), to enhance prediction accuracy in industrial applications. The model exploits the complementary strengths of both algorithms by applying weighted averaging and stacked generalization, allowing it to process heterogeneous datasets containing both categorical and numerical variables. A case study in the aerospace manufacturing sector demonstrates the effectiveness of the proposed approach. Compared to standalone models, the PSO-enhanced hybrid ensemble achieved more than a 30% reduction in Root Mean Squared Error (RMSE), confirming its ability to capture complex interactions among diverse process parameters. Feature importance analysis further showed that categorical attributes, such as machine type and operator, are as influential as numerical parameters, underscoring the need for hybrid modeling. Although the model requires higher computational effort, the integration of PSO significantly improves robustness and scalability. By reducing scrap and optimizing resource utilization, the proposed framework provides a data-driven pathway toward greener, more resource-efficient, and resilient manufacturing systems. Full article

Tourist reviews provide essential insights into travellers experiences and public perceptions of destinations. In Kazakhstan, however, sentiment analysis, particularly using ensemble learning, remains underexplored for evaluating such reviews. This study proposes a hybrid stacking ensemble for sentiment analysis of English-language tourist reviews about Kazakhstan, integrating four complementary approaches: VADER, TextBlob, Stanza, and Local Context Focus Mechanism with Bidirectional Encoder Representations from Transformers (LCF-BERT). Each model contributes distinct analytical capabilities, including lexicon-based polarity detection, rule-based subjectivity evaluation, generalised star-rating estimation, and contextual aspect-oriented sentiment classification. The evaluation utilised a cleaned dataset of 11,454 TripAdvisor reviews collected between February 2022 and June 2025. The ensemble aggregates model outputs through majority and weighted voting strategies to enhance robustness. Experimental results (accuracy 0.891, precision 0.838, recall 0.891, and F1-score 0.852) demonstrate that the proposed method KazSATR outperforms individual models in overall classification accuracy and exhibits superior capacity for aspect-level sentiment detection. These findings underscore the potential of the hybrid ensemble as a practical and scalable tool for the tourism sector in Kazakhstan. By leveraging multiple analytical paradigms, the model enables tourism professionals and policymakers to better understand traveller preferences, identify service strengths and weaknesses, and inform strategic decision-making. The proposed approach contributes to advancing sentiment analysis applications in tourism research, particularly in underrepresented geographic contexts. Full article

Effective waste management is important for reducing environmental harm, improving recycling operations, and building urban sustainability. However, accurate waste classification remains a critical challenge, as many deep learning models struggle with diverse waste types. In this study, classification accuracy is enhanced using transfer learning, ensemble techniques, and custom architectures. Eleven pre-trained convolutional neural networks, including ResNet-50, EfficientNet variants, and DenseNet-201, were fine-tuned to extract meaningful patterns from waste images. To further improve model performance, ensemble strategies such as weighted averaging, soft voting, and stacking were implemented, resulting in a hybrid model combining ResNet-50, EfficientNetV2-M, and DenseNet-201, which outperformed individual models. In the proposed system, two specialized architectures were developed: EcoMobileNet, an optimized MobileNetV3 Large-based model incorporating Squeeze-and-Excitation blocks for efficient mobile deployment, and EcoDenseNet, a DenseNet-201 variant enhanced with Mish activation for improved feature extraction. The evaluation was conducted on a dataset comprising 4691 images across 10 waste categories, sourced from publicly available repositories. The implementation of EcoMobileNet achieved a test accuracy of 98.08%, while EcoDenseNet reached an accuracy of 97.86%. The hybrid model also attained 98.08% accuracy. Furthermore, the ensemble stacking approach yielded the highest test accuracy of 98.29%, demonstrating its effectiveness in classifying heterogeneous waste types. By leveraging deep learning, the proposed system contributes to the development of scalable, sustainable, and automated waste-sorting solutions, thereby optimizing recycling processes and minimizing environmental impact. Full article

Abdominal fat is a key indicator of chicken meat quality. Excessive deposition not only reduces meat quality but also decreases feed conversion efficiency, making the breeding of low-abdominal-fat strains economically important. Genomic selection (GS) uses information from genome-wide association studies (GWASs) and high-throughput sequencing data. It estimates genomic breeding values (GEBVs) from genotypes, which enables early and precise selection. Given that abdominal fat is a polygenic trait controlled by numerous small-effect loci, this study combined population genetic analyses with machine learning (ML)-based feature selection. Relevant single-nucleotide polymorphisms (SNPs) were first identified using a combined GWAS and linkage disequilibrium (LD) approach, followed by a two-stage feature selection process—Lasso for dimensionality reduction and recursive feature elimination (RFE) for refinement—to generate the model input set. We evaluated multiple machine learning models for predicting genomic estimated breeding values (GEBVs). The results showed that linear models and certain nonlinear models achieved higher accuracy and were well suited as base learners for ensemble methods. Building on these findings, we developed a Dynamic Adaptive Weighted Stacking Ensemble Learning Framework (DAWSELF), which applies dynamic weighting and voting to heterogeneous base learners and integrates them layer by layer, with Ridge serving as the meta-learner. In three independent validation populations, DAWSELF consistently outperformed individual models and conventional stacking frameworks in prediction accuracy. This work establishes an efficient GEBV prediction framework for complex traits such as chicken abdominal fat and provides a reusable SNP feature selection strategy, offering practical value for enhancing the precision of poultry breeding and improving product quality. Full article

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition with diverse behavioral, genetic, and structural characteristics. Due to its heterogeneous nature, early diagnosis of ASD is challenging, and conventional unimodal approaches often fail to capture cross-modal dependencies. To address this, this study introduces an adaptive multimodal fusion framework that integrates behavioral, genetic, and structural MRI (sMRI) data, addressing the limitations of unimodal approaches. Each modality undergoes a dedicated preprocessing and feature optimization phase. For behavioral data, an ensemble of classifiers using a stacking technique and attention mechanism is applied for feature extraction, achieving an accuracy of 95.5%. The genetic data is analyzed using Gradient Boosting, which attained a classification accuracy of 86.6%. For the sMRI data, a Hybrid Convolutional Neural Network–Graph Neural Network (Hybrid-CNN-GNN) architecture is proposed, demonstrating a strong performance with an accuracy of 96.32%, surpassing existing methods. To unify these modalities, fused using an adaptive late fusion strategy implemented with a Multilayer Perceptron (MLP), where adaptive weighting adjusts each modality’s contribution based on validation performance. The integrated framework addresses the limitations of unimodal approaches by creating a unified diagnostic model. The transfer learning framework achieves superior diagnostic accuracy (98.7%) compared to unimodal baselines, demonstrating strong generalization across heterogeneous datasets and offering a promising step toward reliable, multimodal ASD diagnosis. Full article

Natural gas, a key low-emission energy source with significant strategic value in modern energy systems, necessitates accurate forecasting of its market price to ensure effective policy planning and economic stability. This paper proposes an ensemble framework to enhance natural gas price forecasting accuracy across multiple temporal scales (weekly and monthly) by constructing hybrid models and exploring diverse ensemble strategies, while balancing model complexity and computational efficiency. For weekly data, an Autoregressive Integrated Moving Average (ARIMA) model optimized via 5-fold cross-validation captures linear patterns, while the Long Short-Term Memory (LSTM) network captures nonlinear dependencies in the residual component after seasonal and trend decomposition based on LOESS (STL). For monthly data, the superior-performing model (ARIMA or SARIMA) is integrated with LSTM to address seasonality and trend characteristics. To further improve forecasting performance, three diverse ensemble techniques including stacking, bagging, and weighted averaging are individually implemented to synthesize the predictions of the two baseline models. The bagging ensemble method slightly outperforms other models on both weekly and monthly data, achieving MAPE, MAE, RMSE, and $R^2$ values of 9.60%, 0.3865, 0.5780, and 0.8287 for the weekly data, and 11.43%, 0.5302, 0.6944, and 0.7813 for the monthly data, respectively. The accurate forecasting of natural gas prices is critical for energy market stability and the realization of sustainable development goals. Full article

This study presents a unified machine learning strategy for identifying various degrees of sarcopenia severity in older adults. The approach combines three optimized algorithms (Random Forest, Gradient Boosting, and Multilayer Perceptron) into a stacked ensemble model, which is assessed with clinical data. A thorough data preparation process involved synthetic minority oversampling to ensure class balance and a dual approach to feature selection using Least Absolute Shrinkage and Selection Operator regression and Random Forest importance. The integrated model achieved remarkable performance with an accuracy of 96.99%, an F1 score of 0.9449, and a Cohen’s Kappa coefficient of 0.9738 while also demonstrating excellent calibration (Brier Score: 0.0125). Interpretability analysis through SHapley Additive exPlanations values identified appendicular skeletal muscle mass, body weight, and functional performance metrics as the most significant predictors, enhancing clinical relevance. The ensemble approach showed superior generalization across all sarcopenia classes compared to individual models. Although limited by dataset representativeness and the use of conventional multiclass classification techniques, the framework shows considerable promise for non-invasive sarcopenia risk assessments and exemplifies the value of interpretable artificial intelligence in geriatric healthcare. Full article

Background: Brain tumors can severely impair neurological function, leading to symptoms such as headaches, memory loss, motor coordination deficits, and visual disturbances. In severe cases, they may cause permanent cognitive damage or become life-threatening without early detection. Methods: To address this, we propose an interpretable deep ensemble model for tumor detection in Magnetic Resonance Imaging (MRI) by integrating pre-trained Convolutional Neural Networks—EfficientNetB7, InceptionV3, and Xception—using a soft voting ensemble to improve classification accuracy. The framework is further enhanced with a Light Gradient Boosting Machine as a meta-learner to increase prediction accuracy and robustness within a stacking architecture. Hyperparameter tuning is conducted using Optuna, and overfitting is mitigated through batch normalization, L2 weight decay, dropout, early stopping, and extensive data augmentation. Results: These regularization strategies significantly enhance the model’s generalization ability within the BR35H dataset. The framework achieves a classification accuracy of 99.83 on the MRI dataset of 3060 images. Conclusions: To improve interpretability and build clinical trust, Explainable Artificial Intelligence methods Grad-CAM++, LIME, and SHAP are employed to visualize the factors influencing model predictions, effectively highlighting tumor regions within MRI scans. This establishes a strong foundation for further advancements in radiology decision support systems. Full article

Facial emotion recognition (FER) is an evolving sub-field of computer vision and affective computing. It entails the development of algorithms and models to detect, analyze, and interpret facial expressions, thereby determining individuals’ emotional states. This paper explores the effectiveness of transfer learning using the EfficientNet-B0 convolutional neural network for FER, alongside the utilization of stacking techniques. The pretrained EfficientNet-B0 model is employed to train on a dataset comprising a diverse range of natural human face images for emotion recognition. This dataset consists of grayscale images categorized into eight distinct emotion classes. Our approach involves fine-tuning the pretrained EfficientNet-B0 model, adapting its weights and layers to capture subtle facial expressions. Moreover, this study utilizes ensemble learning by integrating transfer learning from pretrained models, a strategic tuning approach, binary classifiers, and a meta-classifier. Our approach achieves superior performance in accurately identifying and classifying emotions within facial images. Experimental results for the meta-classifier demonstrate 100% accuracy on the test set. For further assessment, we also train our meta-classifier on a Cohn–Kanade (CK+) dataset, achieving 92% accuracy on the test set. These findings highlight the effectiveness and potential of employing transfer learning and stacking techniques with EfficientNet-B0 for FER tasks. Full article

Hyperspectral remote sensing plays a crucial role in guiding and supporting various mineral prospecting activities. Combined with artificial intelligence, hyperspectral remote sensing technology becomes a powerful and versatile tool for a wide range of mineral exploration activities. This study investigates the effectiveness of ensemble learning (EL) algorithms for lithological classification and mineral exploration using EnMAP hyperspectral imagery (HSI) in a semi-arid region. The Moroccan Anti-Atlas mountainous region is known for its complex geology, high mineral potential and rugged terrain, making it a challenging for mineral exploration. This research applies core and heterogeneous ensemble learning methods, i.e., boosting, stacking, voting, bagging, blending, and weighting to improve the accuracy and robustness of lithological classification and mapping in the Moroccan Anti-Atlas mountainous region. Several state-of-the-art models, including support vector machines (SVMs), random forests (RFs), k-nearest neighbors (k-NNs), multi-layer perceptrons (MLPs), extra trees (ETs) and extreme gradient boosting (XGBoost), were evaluated and used as individual and ensemble classifiers. The results show that the EL methods clearly outperform (single) base classifiers. The potential of EL methods to improve the accuracy of HSI-based classification is emphasized by an optimal blending model that achieves the highest overall accuracy (96.69%). The heterogeneous EL models exhibit better generalization ability than the baseline (single) ML models in lithological classification. The current study contributes to a more reliable assessment of resources in mountainous and semi-arid regions by providing accurate delineation of lithological units for mineral exploration objectives. Full article

The accurate prediction of carbon dioxide (CO₂) adsorption in metal–organic frameworks (MOFs) is critical for accelerating the discovery of high-performance materials for post-combustion carbon capture. Experimental screening of MOFs is often costly and time-consuming, creating a strong incentive to develop reliable data-driven models. Despite extensive research, most studies rely on standalone models or generic ensemble strategies that fall short in handling the complex, nonlinear relationships inherent in adsorption data. In this study, a novel ensemble learning framework is developed by integrating five distinct regression algorithms: Random Forest, XGBoost, LightGBM, Support Vector Regression, and Multi-Layer Perceptron. These algorithms are combined into four custom ensemble strategies: equal-weighted voting, performance-weighted voting, stacking, and manual blending. A dataset comprising 1212 experimentally validated MOF entries with input descriptors including BET surface area, pore volume, pressure, temperature, and metal center is used to train and evaluate the models. The stacking ensemble yields the highest performance, with an R² of 0.9833, an RMSE of 1.0016, and an MAE of 0.6630 on the test set. Model reliability is further confirmed through residual diagnostics, prediction intervals, and permutation importance, revealing pressure and temperature to be the most influential features. Ablation analysis highlights the complementary role of all base models, particularly Random Forest and LightGBM, in boosting ensemble performance. This study demonstrates that custom ensemble learning strategies not only improve predictive accuracy but also enhance model interpretability, offering a scalable and cost-effective tool for guiding experimental MOF design. Full article

In medical diagnostics, brain tumor classification remains essential, as accurate and efficient models aid medical professionals in early detection and treatment planning. Deep learning methodologies for brain tumor classification have gained popularity due to their potential to deliver prompt and precise diagnostic results. This article proposes a novel classification technique that integrates the Xception model with a hybrid attention mechanism and progressive image resizing to enhance performance. The methodology is built on a combination of preprocessing techniques, transfer learning architecture reconstruction, and dynamic fine-tuning strategies. To optimize key hyper-parameters, this study employed the Dynamic Chaotic Whale Optimization Algorithm. Additionally, we developed a novel learning rate scheduler that dynamically adjusts the learning rate based on image size at each training phase, improving training efficiency and model adaptability. Batch sizes and layer freezing methods were also adjusted according to image size. We constructed an ensemble approach by preserving models trained on different image sizes and merging their results using weighted averaging, bagging, boosting, stacking, blending, and voting techniques. Our proposed method was evaluated on benchmark datasets achieving remarkable accuracies of 99.67%, 99.09%, and 99.67% compared to the classical algorithms. Full article

In view of the bottleneck problems of serious spectral peak cross-interference, redundant data dimensions, and inefficient traditional dimensionality reduction methods in the infrared spectral analysis of mixed gases, this paper studies a joint dimensionality reduction strategy combining stacked self encoder (SAE) and partial least squares (PLS) and constructs an XGBoost regression model for quantitative detection. The experimental data are from the real infrared spectrum dataset of the National Institute of Standards and Technology (NIST) database, covering key industrial gases such as CO, CH₄, etc. Compared with the traditional principal component analysis (PCA), which relies on the variance contribution rate and leads to dimensional redundancy, and the calculation efficiency of dimension parameters that need to be cross-verified for PLS dimension reduction alone, the SAE-PLS joint strategy has two advantages: first, the optimal dimension reduction is automatically determined by SAE’s nonlinear compression mechanism, which effectively overcomes the limitations of linear methods in spectral nonlinear feature extraction; and second, the feature selection is carried out by combining the variable importance projection index of PLS. Compared with SAE, the compression efficiency is significantly improved. The XGBoost model was selected because of its adaptability to high-dimensional sparse data. Its regularization term and feature importance weighting mechanism can suppress the interference of spectral noise. The experimental results show that the mean square error (MSE) on the test set is reduced to 0.012% (71.4% lower than that of random forest), and the correlation coefficient (R²) is 0.987. By integrating deep feature optimization and ensemble learning, this method provides a new solution with high efficiency and high precision for industrial process gas monitoring. Full article

Financial time series in volatile markets often exhibit non-stationary behavior and signatures of stochastic chaos, challenging traditional forecasting methods based on stationarity assumptions. In this paper, we introduce a novel multi-expert forecasting system (MES) that leverages ensemble machine learning techniques—including bagging, boosting, and stacking—to enhance prediction accuracy and support robust risk management decisions. The proposed framework integrates diverse “weak learner” models, ranging from linear extrapolation and multidimensional regression to sentiment-based text analytics, into a unified decision-making architecture. Each expert is designed to capture distinct aspects of the underlying market dynamics, while the supervisory module aggregates their outputs using adaptive weighting schemes that account for evolving error characteristics. Empirical evaluations using high-frequency currency data, notably for the EUR/USD pair, demonstrate that the ensemble approach significantly improves forecast reliability, as evidenced by higher winning probabilities and better net trading results compared to individual forecasting models. These findings contribute both to the theoretical understanding of ensemble forecasting under chaotic market conditions and to its practical application in financial risk management, offering a reproducible methodology for managing uncertainty in highly dynamic environments. Full article

Groundwater depletion has emerged as a pressing global challenge, yet the low spatial resolution (0.25°) of Gravity Recovery and Climate Experiment (GRACE) satellite data limits its application in regional groundwater monitoring. In this study, based on 0.25° spatial resolution groundwater storage anomalies (GWSAs) data derived from GRACE satellite observations and GLDAS hydrological model outputs, supplemented with hydrological data, humanities data, and other geographic parameters, we constructed a Stacking-based ensemble machine learning model that achieved a 1 km spatial resolution of GWSAs distribution data across the contiguous United States (CONUS) from 2010 to 2020. The ensemble model integrates eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost) models using an Attention-Based Dynamic Weight Allocation (ADWA) approach, along with a ridge regression model. The results indicate that our ensemble model outperforms individual machine learning (ML) models, achieving a coefficient of determination (R²) of 0.929, root mean square error (RMSE) of 25.232 mm, mean absolute error (MAE) of 19.125 mm, and Nash–Sutcliffe efficiency (NSE) of 0.936, validated by 10-fold cross-validation. In situ measurements indicate that, compared with the original data, approximately 61.7% of the monitoring wells (266 out of 431) exhibit a higher correlation after downscaling, with the overall correlation coefficient increasing by about 18.7%, which suggests that the downscaled product exhibits an appreciable improvement in accuracy. The ensemble model proposed in this study, by integrating the advantages of various ML algorithms, is better able to address the complexity and uncertainty of groundwater storage variations, thus providing scientific support for the sustainable management of groundwater resources. Full article