Search

An inventory stacking decision assigns positions to items which are stacked vertically, such as containers in container terminals and steel plates in steel plants. The performance of stacking decisions is greatly affected by the arrival and departure information on items. We study an inventory stacking problem with partial information based on industrial observation in a steel plant. On the inbound side, we investigate three levels of information on future arriving items and their effect on performance. On the outbound side, we study the impact of the retrieval sequence, which is often random. We develop models incorporating different availabilities of information and determine stacking strategies. The study shows that the stacking strategy and stacking performance depend highly on information quality and space utilisation. Especially, when the space utilisation is high, low-quality information deteriorates the performance and such information should be ignored. This contradicts the general belief that more information should bring better performance. The study further proposes a time window allocation approach to reduce the uncertainty in retrieval, and it is effective in improving stacking performance. [ABSTRACT FROM AUTHOR]

Large numbers of vulnerable road users were killed in truck crashes. In this study, ensemble machine learning models are constructed to predict the injury severity of the vulnerable road user (VRU) to truck (VRU-T) crashes. The study is based on the five years (2017–2021) of VRU-T crash data in the Shandong Province from the Center for Accident Research in Zibo. The injury severity of VRUs is estimated using machine learning ensemble models- Stacking, Voting, Random Forest, and eXtreme Gradient Boosting (XGBoost). Compared to the other three models, the Stacking has excellent predictive performance on the pedestrian and non-motorized datasets. Then, SHapley Additive exPlanations and Partial Dependence Plot box are introduced to analyze risk factors qualitatively and quantitatively. The innovative findings of this study are as follows: (1) as VRUs age, they are more likely to be seriously injured in truck crashes; (2) middle-aged truck drivers and truck drivers with medium driving experience increase the probability of VRUs being severe and fatally injured in truck crashes; (3) crashes involving heavy trucks, under signalized crossing, or on the national and provincial road and urban road have a positive effect on the crash severity for cyclists, and E-Bike riders. [ABSTRACT FROM AUTHOR]

Predicting survival outcomes in critical accidents has been a focal point in machine learning research. This study addresses several limitations of existing methods, including insufficient management of data imbalance, lack of emphasis on hyperparameter tuning, and proneness to overfitting. Many existing models struggle to generalize effectively on imbalanced datasets or depend on default hyperparameter settings, resulting in biased predictions. By integrating Principal Component Analysis (PCA), hyperparameter optimization, and resampling methods, as well as combining Edited Nearest Neighbors (ENN) with the Synthetic Minority Oversampling Technique (SMOTE), the model significantly improves predictive accuracy and model generalization. An ensemble model combining seven machine learning algorithms—Logistic Regression, Support Vector Machine, KNN, Random Forest, XGBoost, LightGBM, and CatBoost—was applied to predict survival outcomes. Stochastic Weighted Averaging (SWA) was applied to mitigate overfitting and enhance generalization. The accuracy increased from 91.97% to 94.89% after SWA was applied in this specific scenario. The combination of PCA-based dimensionality reduction, hyperparameter tuning, and resampling techniques (ENN + SMOTE) ensured the model handled data imbalance and optimized predictive accuracy. The final model demonstrated excellent performance, with Area Under the Curve (AUC) and Average Precision (AP) values both reaching 0.98, indicating high accuracy and precision. These improvements were validated using the Titanic dataset in a binary classification problem of predicting passenger survival. The results emphasize that ensemble learning, enhanced by SWA, offers a powerful framework for handling imbalanced and complex datasets, providing significant advancements in predictive modeling accuracy. This study provides insights into how machine learning techniques can be effectively combined to solve classification challenges in real-world scenarios. [ABSTRACT FROM AUTHOR]

Computational models enable accurate, timely prediction of landslides based on the monitoring data on-site as the development of artificial intelligence technology. The most existing prediction methods focus on finding a single prediction algorithm with excellent performance or an integrated and efficient hyperparameter optimization algorithm with a highly accurate regression prediction algorithm. In order to break through the limitation of generalization of prediction models, this paper proposes an ensemble model that combines deep learning algorithms, with a stacking framework optimized with the sliding window method. Multiple deep learning algorithms are set as the first layer of the stacking framework, which is optimized with the sliding window method to avoid confusion in the time order of datasets based on time series analysis. The Shengjibao landslide in the Three Gorges Reservoir is used as a case study. First, the cumulative displacement is decomposed into a trend and a periodic term using a moving average method. A single-factor and a multi-factor superposition model based on multiple deep learning algorithms are used to predict the trend and periodic term of the displacement, respectively. Finally, the predicted values of the trend and periodic terms are added to obtain the total predicted landslide displacement. For monitoring point ZK2-3, the values of RMSE and MAPE of the total displacement prediction with the stacking model are 15.93 mm and 0.54%, and the values of RMSE and MAPE of the best-performing individual deep learning model are 20.00 mm and 0.64%. The results show that the stacking model outperforms other models by combining the advantages of each individual deep learning algorithm. This study provides a framework for integrating landslide displacement prediction models. It can serve as a reference for the geological disaster prediction and the establishment of an early warning system in the Three Gorges Reservoir Area. [ABSTRACT FROM AUTHOR]

Background: Relation extraction (RE) plays a crucial role in biomedical research as it is essential for uncovering complex semantic relationships between entities in textual data. Given the significance of RE in biomedical informatics and the increasing volume of literature, there is an urgent need for advanced computational models capable of accurately and efficiently extracting these relationships on a large scale. Results: This paper proposes a novel approach, SARE, combining ensemble learning Stacking and attention mechanisms to enhance the performance of biomedical relation extraction. By leveraging multiple pre-trained models, SARE demonstrates improved adaptability and robustness across diverse domains. The attention mechanisms enable the model to capture and utilize key information in the text more accurately. SARE achieved performance improvements of 4.8, 8.7, and 0.8 percentage points on the PPI, DDI, and ChemProt datasets, respectively, compared to the original BERT variant and the domain-specific PubMedBERT model. Conclusions: SARE offers a promising solution for improving the accuracy and efficiency of relation extraction tasks in biomedical research, facilitating advancements in biomedical informatics. The results suggest that combining ensemble learning with attention mechanisms is effective for extracting complex relationships from biomedical texts. Our code and data are publicly available at: https://github.com/GS233/Biomedical. [ABSTRACT FROM AUTHOR]

The wrinkles are pervasive in ultrathin two‐dimensional (2D) materials, but the regulation of wrinkles is rarely explored systematically. Here, we employed a series of carboxylic acids (from formic acid to octanoic acid) to control the wrinkles of Zr‐BTB (BTB=1, 3, 5‐(4‐carboxylphenyl)‐benzene) metal–organic framework (MOF) nanosheet. The wrinkles at the micrometer scale were observed with transmission electron microscopy. Furthermore, high‐angle annular dark‐field (HAADF) images showed lattice distortion in many nanoscale regions, which was precisely matched to the nano‐wrinkles. With the changes of hydrophilicity/hydrophobicity, MOF‐MOF and MOF‐solvent interactions were possibly synergistically regulated and wrinkles with different sizes were obtained, which was supported by HAADF, molecular dynamics, and density functional theory calculation. Different wrinkle sizes resulted in different pore sizes between the Zr‐BTB nanosheet interlayers, providing highly‐oriented thin films and the successive optimization of kinetic diffusion pathways, proved by grazing‐incidence wide‐angle X‐ray scattering and nitrogen adsorption. The most suitable wrinkle pore from Zr‐BTB‐C4 exhibited highly efficient chromatographic separation of the substituted benzene isomers. Our work provides a rational route for the modulation of nanoscale wrinkles and their stacked pores of MOF nanosheets and improves the separation abilities of MOFs. [ABSTRACT FROM AUTHOR]

With the development of financial technology, the traditional experience-based and single-network credit default prediction model can no longer meet the current needs. This manuscript proposes a credit default prediction model based on TabNeT-Stacking. First, use the PyTorch deep learning framework to construct an improved TabNet structure. The multi-population genetic algorithm is used to optimize the Attention Transformer automatic feature selection module. The particle swarm algorithm is used to optimize the hyperparameter selection and achieve automatic parameter search. Finally, Stacking ensemble learning is used, and the improved TabNet is used to extract features. XGBoost (eXtreme Gradient Boosting), LightGBM (Light Gradient Boosting Machine), CatBoost (Category Boosting), KNN (K-NearestNeighbor), and SVM (Support Vector Machine) are selected as the first-layer base learners, and XGBoost is used as the second-layer meta-learner. The experimental results show that compared with original models, the credit default prediction model proposed in this manuscript outperforms the comparison models in terms of accuracy, precision, recall, F1 score, and AUC (Area Under the Curve) of credit default prediction results. [ABSTRACT FROM AUTHOR]

Linear regression cannot fully reveal the complex non-linear relationships among influencing factors and scarce samples in the flowering period. In this study, ensemble learning was proposed to predict the flowering periods of rapeseed. The generation of virtual samples was also incorporated. The rapeseed in full bloom and meteorological data was utilized in Longyou County, Quzhou City, Zhejiang Province, China from 1998 to 2023. The original samples were expanded using Gaussian Mixture Model-based Virtual Sample Generation and Cubic Spline Interpolation. Two new datasets were obtained, each of which contained 985 samples. The models were established using eight machine learning methods: Random Forest (RF), Kernel Ridge Regression (KRR), Ridge Regression (RR), Least Absolute Shrinkage and Selection Operator (Lasso), Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Gradient Boosting Decision Tree (GBDT). Hyperparameter optimization was conducted using a Bayesian optimizer. Finally, a prediction model was established for the rapeseed flowering period using stacking ensemble learning. The vast majority of models demonstrated superior performance on the Cubic interpolation dataset, compared with the original and GMM-VSG dataset. Specifically, the RF model was achieved in an RMSE of 0.679 d, an MAE of 0.351 d, and an R² of 0.990, indicating significant improvements, compared with the original dataset with an RMSE of 6.286 d, an MAE of 5.028 d, and an R² of 0.201, as well as the GMM-VSG dataset with an RMSE of 2.680 d, an MAE of 1.588 d, and an R² of 0.881. Additionally, the SVR model also performed better on the Cubic dataset, with an RMSE of 0.849 d, an MAE of 0.333 d, and an R² of 0.984, indicating a better performance than before. LightGBM as an ensemble learning was performed the best on the Cubic dataset, with the lowest RMSE of 0.613 d MAE of 0.336 d, and the highest R² of 0.992. The strong feature learning and noise resistance were verified to capture the complex relationships within the dataset. In contrast, there was no significant improvement of Lasso and RR models on the Cubic dataset. For instance, Lasso exhibited an RMSE of 3.879 d and an MAE of 3.054 d on the Cubic dataset. There was a relative decrease in the error, compared with the original RMSE of 6.329 d and MAE of 5.567 d. There was a substantial gap relative to other models. Five models were developed using the Stacking ensemble learning approach: SRX_L, All_L, SLL_L, SRL_L, and SRK_L. Among them, the SRX_L model performed the best across various metrics. The highest R² value of 0.999 7 was achieved with the lowest RMSE and MAE values among all models, at 0.1227 d and 0.1056 d, respectively. There was a general consistency in the actual and predicted flowering trends, in terms of the fitting flowering period. The high predictive accuracy was also obtained over most years, particularly in 2001, 2011, and 2014. Among them, the prediction closely matched the actual data with minimal discrepancies, sometimes less than 0.01 or even approaching zero. However, there were some years with the larger differences, such as 1999 and 2023. Particularly, the year 1999 experienced the largest discrepancy, where the error was 0.442 1 d. The maximum actual flowering period occurred in 2005, reaching 92 days, with an error between the predicted and actual values of 0.041 6 d. The minimum actual flowering period was observed in 2020, at 63 days, with an error between the predicted and actual values of 0.132 5 d. Therefore, the model can be expected to highly accurately predict the extreme values. The virtual sample generation can also be suitable for small datasets. The predictive accuracy and generalizability of the improved model were significantly enhanced to reduce the costs and challenges of data collection. Compared with single machine learning, Stacking ensemble learning can substantially improve the predictive performance. Stacking ensemble learning is well-suited to complex tasks with nonlinear relationships, such as the flowering periods of rapeseed. [ABSTRACT FROM AUTHOR]

To address the subjectivity of traditional factor attribute grading methods and the weak predictive capabilities of single-model classifications, this study focused on Yulong County; the Contribution Degree Clustering Method (CDCM) utilizes the Certainty Factor (CF) as the contribution index to partition continuous factor attribute intervals. Additionally, the Sparrow Search Optimization Algorithm (SSA) is employed for hyperparameter tuning. The CF is incorporated into Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), and Random Forest (RF) models to form the CF-SSA-SVM, CF-SSA-BPNN, and CF-SSA-RF coupling models, respectively. These basic coupling models are further integrated using the Stacking algorithm to create the CF-SSA-Stacking integrated coupling model for constructing a landslide susceptibility assessment system. The results indicate that the CF-SSA-Stacking integrated coupling model achieves the highest accuracy, F1 score, Kappa coefficient, and AUC value, with values of 0.89375, 0.89172, 0.787500, and 0.9522, respectively. These metrics are significantly superior to those of the three basic coupling models, demonstrating better generalization capability and reliability. This suggests that the model can identify more historical landslide occurrences using fewer grid areas classified as extremely-high- or high-susceptibility zones. It is suitable as an effective regional landslide susceptibility assessment method for practical disaster prevention and mitigation applications. Further studies could explore the model's performance across varying geological settings or with different datasets, providing a roadmap for future research and development in landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]

This paper presents a regional 3D geological modeling method based on the stacking ensemble technique to overcome the challenges of sparse borehole data in large-scale linear underground projects. The proposed method transforms the 3D geological modeling problem into a stratigraphic property classification problem within a subsurface space grid cell framework. Borehole data is pre-processed and trained using stacking method with five different machine learning algorithms. The resulting modelled regional cells are then classified, forming a regional 3D grid geological model. A case study for an area of 324 km2 along Xuzhou metro lines is presented to demonstrate the effectiveness of the proposed model. The study shows an overall prediction accuracy of 85.4%. However, the accuracy for key stratigraphy layers influencing the construction risk, such as karst carve strata, is only 4.3% due to the limited borehole data. To address this issue, an oversampling technique based on the synthetic minority oversampling technique (SMOTE) algorithm is proposed. This technique effectively increases the number of sparse stratigraphic samples and significantly improves the prediction accuracy for karst caves to 65.4%. Additionally, this study analyzes the impact of sampling distance on model accuracy. It is found that a lower sampling interval results in higher prediction accuracy, but also increases computational resources and time costs. Therefore, in this study, an optimal sampling distance of 1 m is chosen to balance prediction accuracy and computation cost. Furthermore, the number of geological strata is found to have a negative effect on prediction accuracy. To mitigate this, it is recommended to merge less significant stratigraphy layers, reducing computation time. For key strata layers, such as karst caves, which have a significant impact on construction risk, further onsite sampling or oversampling using the SMOTE technique is recommended. [ABSTRACT FROM AUTHOR]

To explore how to control the estrogen level in vivo by regulating the activity of the estrogen receptor in the development of breast cancer drugs, multiple-featured evaluation methods were first applied to screen the molecular descriptors of compounds according to the information of antagonist ERα provided in this study. Combining the methods of Extreme Gradient Boost (XGBoost), Light Gradient Boosting Machine (LightGBM) and Random Forest (RF), a stacking-integrated regression model for quantitatively predicting the ERα (estrogen receptors alpha) activity of breast cancer candidate drug was constructed, which considered the compounds acting on the target and their biological activity data, a series of molecular structure descriptors as the independent variables, and the biological activity values as the dependent variables. Then, three classification methods of XGBoost, LightGBM, and Gradient Boosting Decision Tree (GBDT) were selected and the voting strategy was applied to build five ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) classification prediction models. Finally, two schemes based on genetic algorithm (GA) were used to optimize the model and provide predictions for optimizing the biological activity and ADMET properties of ERα antagonists simultaneously. Results showed that the model prediction has strong practical significance, which can guide the structural optimization of existing active compounds and improve the activity of anti-breast cancer candidate drugs. [ABSTRACT FROM AUTHOR]

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Facial expression recognition is a topic of significant interest in affective computing. However, prior datasets and studies have primarily focused on recognizing facial expressions in controlled environments, limiting their generalizability to realistic context. Thus, despite recent advancements, recognizing facial expressions accurately in wild scenarios remains a challenging task. In this work, we propose an ensemble model based on multi-task meta-learner that utilizes a pool of CNN classifiers while dynamically selecting and fusing the optimal ensemble in order to recognize facial expressions more effectively in the wild. The suggested scheme leverages the output probabilities of base learners as meta-features, and integrates multi-label classification into dynamic ensemble selection. As best as we know, this is the first investigation of multi-task learning at the meta-learning level in the context of facial expression recognition. In particular, we introduce an effective meta-learner that combines the strengths of stacking and dynamic ensemble selection. The proposed approach has been evaluated exhaustively on several challenging datasets; including RAF-DB, FER2013, and FERPlus; and the obtained results demonstrate that the ensemble CNN outperforms individual CNN models consistently, while achieving high performance across all datasets. We further demonstrate the generalizability of the proposed approach by performing cross-dataset evaluation. [ABSTRACT FROM AUTHOR]

The southeastern coastal regions of China are characterized by typical hilly terrain with abundant rainfall throughout the year, leading to frequent geological hazards. To investigate the measurement accuracy of surface deformation and the effectiveness of error correction methods using the small baselines subset–interferometry synthetic aperture radar (SBAS-InSAR) method in identifying potential geological hazards in such areas, this study processes and analyzes 129 SAR images covering Ninghai County, China. By processing coherence coefficients using the Stacking technique, errors introduced by low-coherence images during phase unwrapping are mitigated. Subsequently, interferograms with high coherence are selected for time-series deformation analysis based on the statistical parameters of coherence coefficients. The results indicate that, after mitigating errors from low-coherence images, applying the SBAS-InSAR method to only high-coherence SAR datasets provides reliable surface deformation results. Additionally, when combined with field geological survey data, this method successfully identified landslide boundaries and potential landslides not accurately detected in previous geological surveys. This study demonstrates that using the SBAS-InSAR method and selecting high-coherence SAR images based on interferogram coherence statistical parameters significantly improves measurement accuracy and effectively identifies potential geological hazards. [ABSTRACT FROM AUTHOR]

Introduction: Methylmalonic acidemia (MMA) is a disorder of autosomal recessive inheritance, with an estimated prevalence of 1:50,000. First-tier clinical diagnostic tests often return many false positives [five false positive (FP): one true positive (TP)]. In this work, our goal was to refine a classification model that can minimize the number of false positives, currently an unmet need in the upstream diagnostics of MMA. Methods: We developed machine learning multivariable screening models for MMA with utility as a secondary-tier tool for false positives reduction. We utilized mass spectrometry-based features consisting of 11 amino acids and 31 carnitines derived from dried blood samples of neonatal patients, followed by additional ratio feature construction. Feature selection strategies (selection by filter, recursive feature elimination, and learned vector quantization) were used to determine the input set for evaluating the performance of 14 classification models to identify a candidate model set for an ensemble model development. Results: Our work identified computational models that explore metabolic analytes to reduce the number of false positives without compromising sensitivity. The best results [area under the receiver operating characteristic curve (AUROC) of 97%, sensitivity of 92%, and specificity of 95%] were obtained utilizing an ensemble of the algorithms random forest, C5.0, sparse linear discriminant analysis, and autoencoder deep neural network stacked with the algorithm stochastic gradient boosting as the supervisor. The model achieved a good performance trade-off for a screening application with 6% false-positive rate (FPR) at 95% sensitivity, 35% FPR at 99% sensitivity, and 39% FPR at 100% sensitivity. Conclusions: The classification results and approach of this research can be utilized by clinicians globally, to improve the overall discovery of MMA in pediatric patients. The improved method, when adjusted to 100% precision, can be used to further inform the diagnostic process journey of MMA and help reduce the burden for patients and their families. [ABSTRACT FROM AUTHOR]

Soil salinization is an essential risk factor for agricultural development and food security, and obtaining regional soil salinity information more reliably remains a priority problem to be solved. To improve the accuracy of soil salinity inversion, this study focuses on the Manas River Basin oasis area, the largest oasis farming area in Xinjiang, as the study area and proposes a new soil salinity inversion model based on stacked integrated learning algorithms. Firstly, we selected four machine learning regression models, namely, random forest (RF), back propagation neural network, support vector regression, and convolutional neural network, for performance evaluation. Based on the model performance, we selected the more effective RF and BPNN as the basic regression models and further constructed a stacking integrated learning model. This stacking integration learning model improved the prediction accuracy by training a secondary model to fuse the prediction results of these two basic models as new features. We compared and analyzed the stacking integrated learning model with four single machine learning regression models. Findings indicated that the stacking integrated learning regression model fitted better and had good stability; on the test set, the stacking integrated learning regression model showed a relative increase of 8.2% in R2, a relative decrease of 14.0% in RMSE, and a relative increase of 6.5% in RPD when compared to the RF model, which was the single most effective machine learning regression model, and the stacking model was able to achieve soil salinity inversion more accurately. The soil salinity in the oasis areas of the Manas River Basin tended to decrease from north to south from 2016 to 2020 from a spatial point of view, and it was reduced in April from a temporal point of view. The percentage of pixels with a high soil salinity content of 2.75–2.80 g kg−1 in the study area had decreased by 19.6% in April 2020 compared to April 2016. The innovatively constructed stacking integrated learning regression model improved the accuracy of soil salinity estimation on the basis of the superior results obtained in the training of the single optimal machine learning regression model. As a consequence, this model can provide technological backup for fast monitoring and inversion of soil salinity as well as prevention and containment of salinization. [ABSTRACT FROM AUTHOR]

Botryosphaeria laricina (larch shoot blight) was first identified in 1973 in Jilin Province, China. The disease spread rapidly and caused considerable damage because its pathogenesis was unknown at the time and there were no effective controls or quarantine methods. At present, it shows a spreading trend, but most research can only conduct physiological analyses within a relatively short period, combining individual influencing factors. Nevertheless, methods such as neural network models, ensemble learning algorithms, and Markov models are used in pest and disease prediction and forecasting. However, there may be fitting issues or inherent limitations associated with these methods. This study obtained B. laricina data at the county level from 2003 to 2021. The dataset was augmented using the SMOTE algorithm, and then algorithms such as XGBoost were used to select the significant features from a combined set of 12 features. A new stacking fusion model has been proposed to predict the status of B. laricina. The model is based on random forest, gradient boosted decision tree, CatBoost and logistic regression algorithms. The accuracy, recall, specificity, precision, F1 value and AUC of the model reached 90.9%, 91.6%, 90.4%, 88.8%, 90.2% and 96.2%. The results provide evidence of the strong performance and stability of the model. B. laricina is mainly found in the northeast and this study indicates that it is spreading northwest. Reasonable means should be used promptly to prevent further damage and spread. [ABSTRACT FROM AUTHOR]

In recent years, COVID-19 and skin cancer have become two prevalent illnesses with severe consequences if untreated. This research represents a significant step toward leveraging machine learning (ML) and ensemble techniques to improve the accuracy and efficiency of medical image diagnosis for critical diseases such as COVID-19 (grayscale images) and skin cancer (RGB images). In this paper, a stacked ensemble learning approach is proposed to enhance the precision and effectiveness of diagnosis of both COVID-19 and skin cancer. The proposed method combines pretrained models of convolutional neural networks (CNNs) including ResNet101, DenseNet121, and VGG16 for feature extraction of grayscale (COVID-19) and RGB (skin cancer) images. The performance of the model is evaluated using both individual CNNs and a combination of feature vectors generated from ResNet101, DenseNet121, and VGG16 architectures. The feature vectors obtained through transfer learning are then fed into base-learner models consisting of five different ML algorithms. In the final step, the predictions from the base-learner models, the ensemble validation dataset, and the feature vectors extracted from neural networks are assembled and applied as input for the meta-learner model to obtain final predictions. The performance metrics of the stacked ensemble model show high accuracy for COVID-19 diagnosis and intermediate accuracy for skin cancer. [ABSTRACT FROM AUTHOR]

Appendicitis is a condition wherein the appendix becomes inflamed, and it can be difficult to diagnose accurately. The type of appendicitis can also be hard to determine, leading to misdiagnosis and difficulty in managing the condition. To avoid complications and reduce mortality, early diagnosis and treatment are crucial. While Alvarado's clinical scoring system is not sufficient, ultrasound and computed tomography (CT) imaging are effective but have downsides such as operator-dependency and radiation exposure. This study proposes the use of machine learning methods and a locally collected reliable dataset to enhance the identification of acute appendicitis while detecting the differences between complicated and non-complicated appendicitis. Machine learning can help reduce diagnostic errors and improve treatment decisions. This study conducted four different experiments using various ML algorithms, including K-nearest neighbors (KNN), DT, bagging, and stacking. The experimental results showed that the stacking model had the highest training accuracy, test set accuracy, precision, and F1 score, which were 97.51%, 92.63%, 95.29%, and 92.04%, respectively. Feature importance and explainable AI (XAI) identified neutrophils, WBC_Count, Total_LOS, P_O_LOS, and Symptoms_Days as the principal features that significantly affected the performance of the model. Based on the outcomes and feedback from medical health professionals, the scheme is promising in terms of its effectiveness in diagnosing of acute appendicitis. [ABSTRACT FROM AUTHOR]

Alzheimer's Disease, a progressive brain disorder that impairs memory, thinking, and behavior, has started to benefit from advancements in deep learning. However, the application of deep learning in medicine faces the challenge of limited data resources for training models. Transfer learning offers a solution by leveraging pre-trained models from similar tasks, reducing the data and computational requirements to achieve high performance. Additionally, data augmentation techniques, such as rotation and scaling, help increase the dataset size. In this study, we worked with magnetic resonance imaging (MRI) datasets and applied various pre-processing and augmentation techniques including include intensity normalization, affine registration, skull stripping, entropy-based slicing, flipping, zooming, shifting, and rotating to clean and expand the dataset. We applied transfer learning to high-performing pre-trained models—ResNet-50, DenseNet-201, Xception, EfficientNetB0, and Inception V3, originally trained on ImageNet. We fine-tuned these models using the feature extraction technique on augmented data. Furthermore, we implemented ensemble learning techniques, such as stacking and boosting, to enhance the final prediction performance. The novel methodology we applied achieved high precision (95%), recall (94%), F1 score (95%), and accuracy (95%) for Alzheimer's disease detection. Overall, this study establishes a robust framework for applying machine learning to diagnose Alzheimer's using MRI scans. The combination of transfer learning, via pre-trained neural networks fine-tuned on a processed and augmented dataset, with ensemble learning, has proven highly effective, marking a significant advancement in medical diagnostics. [ABSTRACT FROM AUTHOR]

IoT networks are made up of devices that have few computer resources, like less battery life, less processing power, less memory, and most importantly, minimum security, defense mechanisms, and infrastructure to protect them. As the number of IoT devices are growing fast, we can't ignore the impact of large-scale DDoS attacks that come from IoT devices. Artificial intelligence, including Deep Learning and machine learning (ML), is critical in the categorization and detection of DDoS attacks in the Internet of Things. We hope to contribute to current research by enhancing the efficiency with which Intrusion Detection Systems (IDS) identify DDoS attacks. This research paper focuses on exploring the effectiveness of tree-based classifiers and ensemble classifiers. The ensemble approaches used are voting and Stacking with a particular focus on Step Forward Feature Selection and average feature importance methods by performing evaluation to improve the classification of DDoS attacks, Decision Tree (DT), Extra Tree (ET), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) were selected as the best tree classifiers. Hyper-parameter tuning was performed to improve the performance of the classifiers. The proposed models are trained on Bot-IoT, CICIoT2023, and DS2OS datasets. The tree-based classifiers with ensemble of Stacking and voting demonstrated their capability to effectively detect and classify DDoS attacks. The result obtained from the proposed approach showcase an impressive accuracy rate of over 99%. [ABSTRACT FROM AUTHOR]

The increasing severity of climate change, including global warming, makes it crucial to act quickly to adapt and reduce its impact. To address the complex issues of climate change, we need to understand how it affects different continents. Traditional methods of predicting climate change often fail due to the inherent complexities and nonlinearities of climate systems. Thus, to overcome these limitations, this study proposes a machine learning-based stacking model. Initially, the state of art models was trained while the results are unsatisfactory, the grid search optimization was employed to improve the results. However, the results produced were in a mediocre state. Thus, a stacking based, Stack-ClimaBoost model was proposed. This model optimizes the integration of Random Forest (RF), CatBoost (CB), and Light Gradient Boosting Machine (LGBM) using grid search optimization. The Stack-ClimaBoost model outperforms previous state-of-the-art models obtaining a low MAPE 0.765, an RMSE of 2.254, and an R2 value of 0.9003. In addition, for each of the seven continents Stack-ClimaBoost model performed better with a low MAPE (1.8653-5. 8280), an RMSE (1.2-4.57), with a higher R² value of (0.65-0.94). With its adaptable solutions, the proposed Stack-ClimaBoost Regressor model could excel in environmental research and climate modeling on multiple continents. Enhancing precision facilitates more dependable prognostications of temperature patterns, thereby supporting proactive strategizing and decision-making aimed at alleviating the consequences of climate change. [ABSTRACT FROM AUTHOR]

Abstract Background Relation extraction (RE) plays a crucial role in biomedical research as it is essential for uncovering complex semantic relationships between entities in textual data. Given the significance of RE in biomedical informatics and the increasing volume of literature, there is an urgent need for advanced computational models capable of accurately and efficiently extracting these relationships on a large scale. Results This paper proposes a novel approach, SARE, combining ensemble learning Stacking and attention mechanisms to enhance the performance of biomedical relation extraction. By leveraging multiple pre-trained models, SARE demonstrates improved adaptability and robustness across diverse domains. The attention mechanisms enable the model to capture and utilize key information in the text more accurately. SARE achieved performance improvements of 4.8, 8.7, and 0.8 percentage points on the PPI, DDI, and ChemProt datasets, respectively, compared to the original BERT variant and the domain-specific PubMedBERT model. Conclusions SARE offers a promising solution for improving the accuracy and efficiency of relation extraction tasks in biomedical research, facilitating advancements in biomedical informatics. The results suggest that combining ensemble learning with attention mechanisms is effective for extracting complex relationships from biomedical texts. Our code and data are publicly available at: https://github.com/GS233/Biomedical .

Time series analysis has been widely employed in various domains, including finance, healthcare, meteorology, and economics. This approach is crucial in extracting patterns, discerning trends, and forecasting future data points. Traditional approaches for time series analysis often struggle to capture the complex relationships and dependencies present in real-world time series data. Recently, deep learning has shown remarkable performance on many time series analysis tasks. Numerous deep-learning architectures have been proposed to cater the diversity of time-series datasets across different domains. Although advanced deep learning models have considerable computational capabilities, they may fail to detect complex correlations that exist within certain datasets. The performance of particular deep learning models could be impacted by factors such as data noise, model design, and hyperparameter setups. Modern time series data, with its challenges and non-linearities, requires even more refined techniques. In this context, ensemble deep learning techniques have emerged as a promising solution. By combining multiple models, ensemble learning addresses the limitations of individual models, enhancing prediction accuracy and robustness. Despite significant advancements made in this domain, our literature review reveals a critical gap. The study aims to bridge this gap by providing a pioneering investigation into the application of ensemble techniques to time series analysis. We systematically categorize existing ensemble methods used in diverse domains and conduct a comprehensive literature review to understand the current state of ensemble deep learning in time series analysis. Our research explores the complexities of the three main ensemble techniques—bagging, boosting, and stacking—and extends to include adaptive and hybrid ensemble methods, which are increasingly relevant for time series forecasting. We provide a conceptual framework and pseudocode for practical implementation, allowing for a thorough examination of these established and emerging techniques. Additionally, our review discusses the evaluation metrics commonly used in ensemble learning for time series analysis, including statistical tests that assess the significance of the improvements offered by ensemble methods. Moreover, we analyze and examine the primary challenges, unresolved issues, and possible directions for future research in this rapidly evolving field. This study is a significant and original contribution to the domain, setting the foundation for future research and progress in combining ensemble deep learning with time series analysis. [ABSTRACT FROM AUTHOR]

Although some machine learning methods have been widely applied to customer churn prediction across various fields, few studies have focused on customer churn in card and board mobile games. Moreover, the massive volume of game log data presents new challenges for customer churn prediction. To address this, this paper proposes a customized high-performance solution based on the big data technology, Spark. Initially, Spark is utilized to preprocess the game log data and compute features; subsequently, the neighborhood cleaning rule (NCL) method is employed to handle the issue of class imbalance; finally, an ensemble learning model based on the stacking method is constructed. We validated our approach on a large-scale real dataset (260 GB). The results show that the method proposed in this paper performs optimally, achieving an accuracy of 96.33%, and the entire solution takes only 11 min to execute, meeting the practical requirements for prediction accuracy and data processing capability. [ABSTRACT FROM AUTHOR]

Aim: Species distribution models (SDMs) are powerful tools for assessing suitable habitats across large areas and at fine spatial resolution. Yet, the usefulness of SDMs for mapping species' realised distributions is often limited since data biases or missing information on dispersal barriers or biotic interactions hinder them from accurately delineating species' range limits. One way to overcome this limitation is to integrate SDMs with expert range maps, which provide coarse‐scale information on the extent of species' ranges and thereby range limits that are complementary to information offered by SDMs. Innovation: Here, we propose a new approach for integrating expert range maps in SDMs based on an ensemble method called stacked generalisation. Specifically, our approach relies on training a meta‐learner regression model using predictions from one or more SDM algorithms alongside the distance of training points to expert‐defined ranges as predictor variables. We demonstrate our approach with an occurrence dataset for 49 bat species covering four biodiversity hotspots in the Eastern Mediterranean, Western Asia and Central Asia. Main Conclusions: Our approach offers a flexible method to integrate expert range maps with any combination of SDM modelling algorithms, thus facilitating the use of algorithm ensembles. In addition, it provides a novel, data‐driven way to account for uncertainty in expert‐defined ranges not requiring prior knowledge about their accuracy, which is often lacking. Integrating expert range maps into SDMs for bats resulted in more realistic predictions of distribution patterns that showed narrower niche breadths and smaller range overlaps between species compared to traditional SDMs. Our approach holds promise to improve assessments of species distributions, while our work highlights the overlooked potential of stacked generalisation as an ensemble method in species distribution modelling. [ABSTRACT FROM AUTHOR]

The Controlled-Source Electromagnetic (CSEM) method is one of the electromagnetic methods utilized in geophysical exploration. This method provides a subsurface image through the resistivity anomalies of materials encountered by electromagnetic waves. The research area is located near a major city, resulting in high electromagnetic noise. Electromagnetic noise can be categorized into two types of the noise namely periodic noise and sporadic noise. Eliminating noise is a crucial objective to enhance data quality, as it can introduce uncertainty into interpretations. Three noise removal techniques are employed: pre-stack to filter the harmonic noise, stacking to remove the sporadic noise, and post-stack for smoothing. The CSEM data used consists of signals in the time domain with a 10-second period and a 50% duty cycle. The results of applying these noise removal techniques indicate that all three methods are highly effective in noise reduction. The pre-stack technique can remove periodic noise, while sporadic noise is addressed by the stacking technique, and signal smoothing can be achieved using the poststack technique.

Abstract Enormous amounts of data are generated in the form of feedback or comments from online platforms such as social media, e-commerce, education, and programming. This feedback and comments hold significant value for making important strategic decisions; therefore, effectively analyzing them poses a major challenge. This research addresses the imperative need for an efficient comment classification model. To fill this research gap, we propose a robust ensemble machine learning (ML) model called CommentClass (RF+AdaBoost+SVM+Soft-Voting), specifically designed for the comment classification task. First, we developed eight (08) pipelines using various combinations of ML algorithms. Next, the fundamental ensemble techniques such as stacking, blending, hard-voting, soft-voting, and averaging are incorporated into these pipelines to improve comment classification performance. These ensemble models are able to discern the latent characteristics of diverse text comments, classifying them to achieve superior accuracy. The proposed CommentClass ensemble model achieved an impressive accuracy and F1-score of approximately 98% for comment classification on the YouTube dataset. This result represents an improvement in accuracy by approximately +3% compared to prior research on the same dataset. Moreover, the proposed CommentClass model obtained higher F1-scores of 90.26%, 87.04%, and 75.74%, on the Spambase, IMDB, and Twitter datasets, respectively, compared to other sophisticated models. Furthermore, the proposed CommentClass model exhibited significant accuracy on the SMS dataset and two distinct synthetic datasets.

Abstract In the current century, heart-related sickness is one of the important causes of death for all humans. An estimated 17.5 million deaths occur due to heart disease worldwide. It is observed that more than 75% of peoples with average income level mostly suffer from heart diseases and its complications. So, there is need for predicting heart infection and its related complications. Data mining is the method of converting raw data into useful information. These tools allow given data to predict future trends. Data mining concepts were mainly adapted in heart disease data sets to interpret the intricate inferences out of it. In the modern world, many research are carried in health care engineering with the use of mining and prediction techniques. This investigation aims to identify significant features in heart disease dataset and to apply ensembling techniques for improving exactness of prediction. Prediction models are developed using different ensembling techniques like stacking and voting. For the experimental purpose, the Z-Alizadeh Sani dataset is used, which is available in the UCI machine learning data repository. Stacking and voting techniques are applied to the dataset. Stacking with substantial characteristics has the maximum accuracy of 86.79% in the Z-Alizadeh dataset. Test outcome proves that the prediction model implemented with the features selected using firefly algorithm and stacking-based classification model has the highest accuracy prediction than other technique. Furthermore, this study delineates a comparative analysis with prior works, showcasing the superior capabilities of the firefly algorithm in optimizing feature selection processes, which is crucial for advancing the accuracy of heart disease predictions.

Nowadays, fiber stacks are extensively used in the aircraft and structural component manufacturing industries. It is mainly due to their excellent mechanical and physiochemical performances. The different stacking sequences of fiber materials expand the structural properties due to high-strength carbon fiber and low-cost glass fiber. The fragile and anisotropic conduct of Carbon (Cf) and Glass (Gf) laminates generates different types of complex machining issues. This article focuses on the Drilling test of Carbon/glass fiber hybrid composites using different stacking sequences. The effect of varying stacking orders is explored in this study to identify a feasible composite. The control of varying constraints, namely, spindle speed (N), feed rate (f ), and stacking sequence (SS) of carbon (Cf) and glass fiber (Gf) reinforcement, is performed to achieve the optimal parametric condition. The finding reveals that sample A (C4G4) stacking sequence provides an acceptable value for thrust force 59.05 N and delamination 1.0001 for high drilling efficiency. The stacking technique of carbon/glass layers can be endorsed to the manufacturing sector for cost-effective composite development and a defect-free machining environment.

The use of speech-based recognition technologies in human–computer interactions is increasing daily. Age and gender recognition, one of these technologies, is a popular research topic used directly or indirectly in many applications. In this research, a new age and gender recognition approach based on the ensemble of different machine learning algorithms is proposed. In the study, five different classifiers, namely KNN, SVM, LR, RF, and E-TREE, are used as base-level classifiers and the majority voting and stacking methods are used to create the ensemble models. First, using MFCC features, five base-level classifiers are created and the performance of each model is evaluated. Then, starting from the one with the highest performance, these classifiers are combined and ensemble models are created. In the study, eight different ensemble models are created and the performances of each are examined separately. The experiments conducted with the Turkish subsection of the Mozilla Common Voice dataset show that the ensemble models increase the recognition accuracy, and the highest accuracy of 97.41% is achieved with the ensemble model created by stacking five classifiers (SVM, E-TREE, RF, KNN, and LR). According to this result, the proposed ensemble model achieves superior accuracy compared to similar studies in recognizing age and gender from speech signals. [ABSTRACT FROM AUTHOR]

Background: Carotid atherosclerosis (CAS) is a significant risk factor for cardiocerebrovascular events. The objective of this study is to employ stacking ensemble machine learning techniques to enhance the prediction of CAS occurrence, incorporating a wide range of predictors, including endocrinerelated markers. Methods: Based on data from a routine health check-up cohort, five individual prediction models for CAS were established based on logistic regression (LR), random forest (RF), support vector machine (SVM), extreme gradient boosting (XGBoost) and gradient boosting decision tree (GBDT) methods. Then, a stacking ensemble algorithm was used to integrate the base models to improve the prediction ability and address overfitting problems. Finally, the SHAP value method was applied for an in-depth analysis of variable importance at both the overall and individual levels, with a focus on elucidating the impact of endocrinerelated variables. Results: A total of 441 of the 1669 subjects in the cohort were finally diagnosed with CAS. Seventeen variables were selected as predictors. The ensemble model outperformed the individual models, with AUCs of 0.893 in the testing set and 0.861 in the validation set. The ensemble model has the optimal accuracy, precision, recall and F1 score in the validation set, with considerable performance in the testing set. Carotid stenosis and age emerged as the most significant predictors, alongside notable contributions from endocrinerelated factors. Conclusion: The ensemble model shows enhanced accuracy and generalizability in predicting CAS risk, underscoring its utility in identifying individuals at high risk. This approach integrates a comprehensive analysis of predictors, including endocrine markers, affirming the critical role of endocrine dysfunctions in CAS development. It represents a promising tool in identifying high-risk individuals for the prevention of CAS and cardio-cerebrovascular diseases. [ABSTRACT FROM AUTHOR]

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning. [ABSTRACT FROM AUTHOR]

In the United States, several land use and land cover (LULC) data sets are available based on satellite data, but these data sets often fail to accurately represent features on the ground. Alternatively, detailed mapping of heterogeneous landscapes for informed decision-making is possible using high spatial resolution orthoimagery from the National Agricultural Imagery Program (NAIP). However, large-area mapping at this resolution remains challenging due to radiometric differences among scenes, landscape heterogeneity, and computational limitations. Various machine learning (ML) techniques have shown promise in improving LULC maps. The primary purposes of this study were to evaluate bagging (Random Forest, RF), boosting (Gradient Boosting Machines [GBM] and extreme gradient boosting [XGB]), and stacking ensemble ML models. We used these techniques on a time series of Sentinel 2A data and NAIP orthoimagery to create a LULC map of a portion of Irion and Tom Green counties in Texas (USA). We created several spectral indices, structural variables, and geometry-based variables, reducing the dimensionality of features generated on Sentinel and NAIP data. We then compared accuracy based on random cross-validation without accounting for spatial autocorrelation and target-oriented cross-validation accounting for spatial structures of the training data set. Comparison of random and target-oriented cross-validation results showed that autocorrelation in the training data offered overestimation ranging from 2% to 3.5%. The XGB-boosted stacking ensemble on-base learners (RF, XGB, and GBM) improved model performance over individual base learners. We show that meta-learners are just as sensitive to overfitting as base models, as these algorithms are not designed to account for spatial information. Finally, we show that the fusion of Sentinel 2A data with NAIP data improves land use/land cover classification using geographic object-based image analysis. [ABSTRACT FROM AUTHOR]

Soil moisture is an important component of the hydrologic cycle and ecosystem functioning, and it has a significant impact on agricultural production, climate change and natural disasters. Despite the availability of machine-learning techniques for estimating soil moisture from high-resolution remote-sensing imagery, including synthetic aperture radar (SAR) data and optical remote sensing, comprehensive comparative studies of these techniques remain limited. This paper addresses this gap by systematically comparing the performance of four tree-based ensemble-learning models (random forest (RF), extreme gradient boosting (XGBoost), light gradient-boosting machine (LightGBM), and category boosting (CatBoost)) and three deep-learning models (deep neural network (DNN), convolutional neural network (CNN), and gated recurrent unit (GRU)) in terms of soil moisture estimation. Additionally, we introduce and evaluate the effectiveness of four different stacking methods for model fusion, an approach that is relatively novel in this context. Moreover, Sentinel-1 C-band dual-polarization SAR and Sentinel-2 multispectral data, as well as NASADEM and geographical code and temporal code features, are used as input variables to retrieve the soil moisture in the ShanDian River Basin in China. Our findings reveal that the tree-based ensemble-learning models outperform the deep-learning models, with LightGBM being the best individual model, while the stacking approach can further enhance the accuracy and robustness of soil moisture estimation. Moreover, the stacking all boosting classes ensemble-learning model (SABM), which integrates only boosting-type models, demonstrates superior accuracy and robustness in soil moisture estimation. The SHAP value analysis reveals that ensemble learning can utilize more complex features than deep learning. This study provides an effective method for retrieving soil moisture using machine-learning and high-resolution remote-sensing data, demonstrating the application value of SAR data and high-resolution optical remote-sensing data in soil moisture monitoring. [ABSTRACT FROM AUTHOR]

Polymer composites are becoming more popular as a feasible alternative to conventional engineering materials due to superior physio-mechanical qualities, corrosion resistance, moisture resistance, damage tolerance, and tailored properties. The epoxy matrix molecular structure significantly affects mechanical performance because of its high crosslink structure, density, and stiffness. This paper deals with the evaluation of mechanical and thermal characteristics of carbon (C) and glass fiber (G) stacked composites modified by multiwall carbon nanotube (MWCNT). The conventional hand-layup method (HLM) was employed to fabricate nanocomposite samples in different MWCNT wt% (0, 0.45, 0.90,1.35). Tensile and Flexural testing examined the mechanical behavior of the developed composite. Thermogravimetric analysis and dynamic mechanical analysis compute the thermal and viscoelastic behavior of the nanocomposite specimens. Scanning electron microscopy describes the failure mechanisms on the damaged surfaces of the nanocomposite samples. The MWCNT supplements in the stacked composite make it more efficient than pristine samples and augment the mechanical characteristics of structural components. The MWCNT-modified stacked samples show improved tensile and flexural behavior than the stacked samples for the desired application. This work reveals that adding MWCNTs as the third phase reinforcement into the stacked (C–G–C) nanocomposites could improve the mechanical and thermal characteristics. [ABSTRACT FROM AUTHOR]

Road Traffic Injuries are one of the world's leading cause of death, with greatest burden falling on nations with lower and moderate incomes. They are consistently ranked in top 10 leading causes of mortality worldwide for persons of all ages. The biggest advantage of classifying victim degree of injuries in road accidents can pave a way for safer roads and reduced accident rates. This article employs California based SWITRS dataset to propose a novel approach namely Stacked DCL-X model for classifying ' ' v i c t i m _ d e g r e e _ o f _ i n j u r y ′ ′ . It classifies injuries that might take place due to collisions occurring between vehicles and near by pedestrians, obstacles etc. on roads. To verify the superiority of our proposed model, several Machine Learning algorithm-based classification models are stacked together to classify ' ' v i c t i m _ d e g r e e _ o f _ i n j u r y ′ ′ . A total of 1 27 000 accidents are considered from SWITRS dataset when determining the ' ' v i c t i m _ d e g r e e _ o f _ i n j u r y ′ ′ . Machine Learning classifiers implemented in this article includes XGBoost, CatBoost, LightGBM, Decision Tree, Random Forest, Gradient Boosting and Stacked DCL-X. In addition, the algorithm used at feature selection step is Harris Hawk Optimization algorithm, a Nature Inspired Algorithm to select the best features. Prediction results shows that the proposed Stacked DCL-X model provides good stability, fewer hyper-parameters, and highest accuracy under different levels of training data volume. The values of Accuracy, Mean Square Error, and ROC-Auc in Stacked DCL-X model are 87.52, 0.5677 and 97.43, respectively. Moreover, confusion matrix and evaluation metrics of the proposed model provides better results than state-of-the-art classifiers. Statistical analysis has also been performed using Friedman's rank test on different datasets to ensure the superiority of our proposed Stacked DCL-X model. The findings of this study would be helpful in classifying the ' ' v i c t i m _ d e g r e e _ o f _ i n j u r y ′ ′ . These findings are highly significant in smart city projects to effectively establish timely proactive strategies and improve road traffic safety. [ABSTRACT FROM AUTHOR]

A high proportion of new energy has become a prominent feature of modern power systems. Due to the intermittency, volatility, and strong randomness in wind power generation, an accurate and reliable method for the prediction of wind power is required. This paper proposes a modified stacking ensemble learning method for short-term wind power predictions to reduce error and improve the generalization performance of traditional single networks in tackling the randomness of wind power. Firstly, the base learners including tree-based models and neural networks are improved based on the Bagging and Boosting algorithms, and a method for determining internal parameters and iterations is provided. Secondly, the linear integration and stacking integration models are combined to obtain deterministic prediction results. Since the modified stacking meta learner can change the weight, it will enhance the strengths of the base learners and optimize the integration of the model prediction to fit the second layer prediction, compared to traditional linear integration models. Finally, a numerical experiment showed that the modified stacking ensemble model had a decrease in MAPE from about 8.3% to 7.5% (an absolute decrease of 0.8%) compared to a single learner for the 15 min look-ahead tests. Changing variables such as the season and predicting the look-ahead time showed satisfactory improvement effects under all the evaluation criteria, and the superiority of the modified stacking ensemble learning method proposed in this paper regarding short-term wind power prediction performance was validated. [ABSTRACT FROM AUTHOR]

Recently, π–π stacked antiaromatic π‐systems have received considerable attention because they can exhibit stacked‐ring aromaticity due to substantial intermolecular orbital interactions. Here, we report three antiaromatic norcorrole dimers that self‐assemble to form supramolecular architectures through chiral self‐sorting. A 2,2'‐linked norcorrole dimer with 3,5‐di‐tert‐butylphenyl groups forms a π‐stacked dimer both in solid and solution states via homochiral self‐sorting. Its association constant in solution is (3.6±1.7)×105 M−1 at 20 °C. In the solid state, 3,3'‐linked norcorrole dimers with 3,5‐di‐tert‐butylphenyl and phenyl groups afford macrocyclic and helical supramolecular assemblies via heterochiral and homochiral self‐sorting, respectively. Notably, the subtle modification in the substituent resulted in a complete change in the structure of the aggregates and the chiral self‐sorting mode. The present findings demonstrate that structural manipulation in antiaromatic monomer units leads to the formation of various supramolecular assemblies on the basis of the attractive interactions between antiaromatic π‐systems. [ABSTRACT FROM AUTHOR]

Stacking engineering is a popular method to tune the performance of two dimensional materials for advanced applications. In this work, Jansu MoSSe and WSSe monolayers are constructed as a van der Waals (vdWs) heterostructure by different stacking configurations. Using first-principle calculations, all the relaxed stacking configurations of the MoSSe/WSSe heterostructure present semiconductor properties while the direct type-II band structure can be obtained. Importantly, the Z-scheme charge transfer mode also can be addressed by band alignment, which shows the MoSSe/WSSe heterostructure is an efficient potential photocatalyst for water splitting. In addition, the built-in electric field of the MoSSe/WSSe vdWs heterostructure can be enhanced by the S-Se interface due to further asymmetric structures, which also results in considerable charge transfer comparing with the MoSSe/WSSe vdWs heterostructure built by the S-S interface. Furthermore, the excellent optical performances of the MoSSe/WSSe heterostructure with different stacking configurations are obtained. Our results provide a theoretical guidance for the design and control of the two-dimensional heterostructure as photocatalysts through structural stacking. [ABSTRACT FROM AUTHOR]

Cadmium chalcogenide nanoplatelets (NPLs) are not only known due to their unique optical properties but also because of their ability to self‐assemble into stacks with new collective properties. Only recently, a stacking process in an aqueous medium has been demonstrated, which opens up possible applications and methods such as gelation. Nanoparticle‐based aerogels gain a lot of attention due to their high relative surface areas and porosity and thus, high potential for catalytic applications. Herein, the positive properties of aerogels to the NPL‐stack system by cryoaerogelation of destabilized NPL dispersions are introduced. After the addition of an antisolvent to initiate the stacking, the dispersion is flash‐frozen with liquid nitrogen and freeze‐dried. By this method, porous cryoaerogel networks result in high surface areas and retained stacking of the NPLs. The formed stack‐gels are investigated by electron microscopy and physisorption measurements. Optical and photoelectrochemical measurements verify the charge carrier transport within the stack‐gel network. [ABSTRACT FROM AUTHOR]

We design four Artificial Neural Network (ANN) models, namely a Multilayer Perceptron (MLP), a Convolutional Neural Network (CNN), an Extreme Learning Machine network (ELM) and an ensemble model based on stacking (STACKED) to forecast the ionospheric vertical Total Electron Content (vTEC) from 1 to 24 hours in advance on a single station at mid latitude. The time series used, spanning from January 2006 to December 2018, includes vTEC, provided by the Global Navigation Satellite System (GNSS) receiver at Tsukuba (TSKB), Japan (36.06 o N, 140.05 o E) and suitable external drivers selected among several helio-geophysical parameters. The selection of appropriate external drivers is made by rating their relevance on the vTEC at forecasting timescales (from 1 to 24 hours). The process, based on eleven machine learning models, highlights that the most important external drivers are: the 10.7 cm Solar Flux (F10.7), the magnitude B T of the Interplanetary Magnetic Field (IMF), and the Auroral Electrojet (AE) index. The forecasting performance of the four models (MLP, CNN, ELM, STACKED) is then analysed. The analysis relies on three statistical metrics to compare actual and forecasted vTEC: the coefficient of determination ( R 2 ), the Mean Absolute Error (MAE), and the Root Mean Squared Error (RMSE). Additionally, descriptive statistics are presented using box and whisker plots. The four ANN models show a quite satisfactory capability to forecast vTEC when applied to the test dataset which represents 10% of the available data from 2006 to 2018. Furthermore, by conducting a Wilcoxon signed rank test, it is shown that statistically significant improvements are achieved by the STACKED model with regard to MLP, CNN and ELM. On average, by analysing the forecasted (from 1 to 24 hours in advance) vs the actual vTEC, the STACKED model achieves R 2 = 0.816 , RMSE = 0.426 TECu, and MAE = 0.296 TECu (1 TECunit = 10 16 electrons/ m 2 ) whilst MLP, CNN and ELM show respectively R 2 = 0.808 , 0.812 , 0.803 , RMSE = 0.436 TECu, 0.431 TECu, 0.441 TECu and MAE = 0.304 TECu, 0.299 TECu, 0.312 TECu. [ABSTRACT FROM AUTHOR]

There has recently been increasing attention paid to sulphur dioxide (SO2) pollution owing to its hazardous effect on both human health and atmospheric environment. To handle this problem, the wet flue gas desulphurization (FGD) system has found wide applications in SO2 emitting industries. Accurate prediction of SO2 emissions in treated flue gas serves the purpose of providing timely operating guidance for the FGD system. However, the wet FGD process is characterized by highly nonlinear dynamics and non-stationarity, which poses significant difficulties and limitations for traditional modeling methods. To address above issues, in this article, an integrated model is proposed to perform SO2 emission forecasting for an FGD process. Our integrated model comprises a multiplicity of techniques, including complete ensemble empirical mode decomposition (EMD) with adaptive noise CEEMDAN stacking ensemble learning (SEL) and permutation-based entropy (PEN). The CEEMDAN serves as decomposing SO2 emission signal, then the complexity of each decomposed sub-series is analyzed by PEN and ones with similar scores are combined, finally a stacking-based ensemble learning model which incorporates different types of member models are developed for modeling purposes. The proposed method was validated and evaluated by measurements of a real FGD system in a 600MW coal-fired unit, and experimental results illustrate the superiority of our method. [ABSTRACT FROM AUTHOR]

A model framework for the prediction of defects in strip steel is proposed with the objective of enhancing the accuracy of defect detection. Initially, the data are balanced through the utilisation of the Improved Synthetic Minority Oversampling Technique (ISmote), which is based on clustering techniques. Subsequently, further enhancements are made to the inertia weights and learning factors of the immune particle swarm optimisation (IPSO), with additional optimisations in speed updates and population diversity. These enhancements are designed to address the issue of premature convergence at the early stages of the process and local optima at the later stages. Finally, a prediction model is then constructed based on stacking, with its hyperparameters optimised through the improved immune particle swarm optimisation (IIPSO). The results of the experimental trials demonstrate that the IIPSO-ISmote-Stacking model framework exhibits superior prediction performance when compared to other models. The Macro_Precision, Macro_Recall, and Macro_F1 values for this framework are 93.3%, 93.6%, and 92.2%, respectively. [ABSTRACT FROM AUTHOR]

The research in the field of mobile assisted language learning has a long history. It basically follows the route from theory to application practice, but there are few process studies on learners' individual language skills learning behavior based on mobile platform data. This research takes vocabulary learning as the starting point, and constructs a mobile user English learning pattern recognition model with improved Stacking integration algorithm. The purpose of this study is to identify different learning modes by analyzing the learning behavior and learning data of mobile users, and to provide personalized learning suggestions for users. The evaluation goal of this study is the accuracy and robustness of the mobile users' English learning pattern recognition model, and the accuracy is the classification accuracy of the model for different learning patterns. Robustness is the stability and consistency of the model in different situations. In order to evaluate the integrated English learning mode of mobile users, the study first divides the collected learning data set into training set and test set. In this step, the method used in the study is cross-validation, which aims to reduce the difference of evaluation results caused by different data sets. For the relevant features in mobile users' learning data, the features extracted by the research include learning behavior and learning progress, which can accurately reflect the learning mode. Then, the integrated learning method is used to train the model, and the best parameter combination is selected through the training set. Finally, the study uses the test set to evaluate the trained model, and calculates the accuracy and recall index of the model on the test set. Through this evaluation method, the evaluation results of the integrated learning pattern recognition model in terms of accuracy and robustness are obtained, and reference is provided for the improvement of the model. The model proposed in this study is suitable for a large number of user data. Because the learning behavior of users is influenced by personal habits, there are limitations in obtaining enough high-quality data, so the labeling of data is subjective. It is still a challenge to select the most representative features of user learning behavior extracted from the model. The feature selection method can lead to different results, and the process requires a lot of human intervention. The experiment conducted mining and analysis on user learning behavior data of a domestic English vocabulary learning APP. Compared with the confusion matrix of the traditional Stacking model, the improved Stacking model has a stronger ability to distinguish user learning patterns. According to the formula, the accuracy of the improved Stacking model is 91.29%; The accuracy of traditional Stacking model is 90.71%. The ROC curve of the improved Stacking model is smoother than the three single models. Its AUC value is 0.85, which is the same as that of XGBoost. The function is also improved compared with the traditional Stacking model, Logistic Regression (LR) and Random Forest (RF) model. Therefore, the Stacking integrated model owns the best forecast performance and can accurately predict the long-term learning mode of users. In this study, the English learning patterns of mobile users are identified by the method of integrated learning, so that the prediction results of multiple basic learners can be integrated, and the complementarity between different learners can be effectively dealt with, thus improving the generalization ability of the model. This model aims at identifying the English learning patterns of mobile users, and can accurately identify the learning patterns of users by analyzing their learning behaviors on mobile devices. This is of great significance for personalized English learning recommendation. The English learning pattern recognition model for mobile users proposed in this study can identify users' learning patterns by analyzing their learning behaviors, thus providing personalized learning support and suggestions. In the process of digital manufacturing, they can learn from the idea of learning pattern recognition model and identify the patterns and laws in the production process by analyzing production data and process parameters, so as to optimize the production process and improve production efficiency. [ABSTRACT FROM AUTHOR]

Students' performance in higher education reflects their overall quality in higher education. By predicting the performance, students with greater learning problems can be screened out early and given appropriate guidance. To predict students' performance in English, the knowledge information of courses, examination papers, and historical examination records are used to build a feature project of students' examinations. Meanwhile, the features strongly correlated with their performance are filtered out. Then the next step of performance prediction is carried out. The results showed that a neural network long and short-term memory performance prediction model incorporating an attention mechanism was more effective than other models in predicting English performance in higher education. Further experiments found that the model reduced the error by 1.04% on the MAE metric, 0.53% on the RMSE metric, and increased its value by 4.12% on the R2 metric. Adding the new feature dataset led to better forecasting by the Att-LSTM model in all metrics. This indicated that the enhanced dataset temporality could improve the effectiveness of the Att-LSTM model in predicting English grades in higher education. The stacked integrated prediction model, by integrating multiple strong regressors, can avoid poor prediction and excessive overall bias due to one regressor and increase the soundness and prediction precision of the mode. [ABSTRACT FROM AUTHOR]