With the advent of the data era, medical image data plays an increasingly important role in diagnosing and treating diseases. This study combined deep learning, ensemble learning, and mathematical theory to construct ...
详细信息
ISBN:
(纸本)9798400716607
With the advent of the data era, medical image data plays an increasingly important role in diagnosing and treating diseases. This study combined deep learning, ensemble learning, and mathematical theory to construct a stacking algorithm model based on the Naive Bayes method to achieve more accurate classification of medical images. In the stacking algorithm, the results of the primary classifier are treated equally, and the performance of the primary classifier is ignored. The poor performance of the primary classifier will affect the final classification result. To solve this problem, a stacking algorithm based on the Naive Bayes method is proposed in this paper. Firstly, the performance of the primary classifier is evaluated, and the output of the primary classifier is selected reasonably through the evaluation results. Secondly, the VGGNet, InceptionNet, and ResNet convolutional networks were used as primary classifiers to construct a complete stacking algorithm based on the Naive Bayes method. Next, the algorithm was tested and validated using COVID-19 and NoCOVID-19 lung CT image data. Finally, it is compared with a single primary classifier and the traditional stacking algorithm. The experimental results show that the stacking algorithm based on the Naive Bayes method is suitable for the binary classification task of medical images and has better classification results than a single primary classifier and the traditional stacking algorithm.
Accurate modeling for highly non-linear coupling of a damaged ship with liquid sloshing in waves is still of considerable interest within the computational fluid dynamics(CFD)and AI *** paper describes a data-driven S...
详细信息
Accurate modeling for highly non-linear coupling of a damaged ship with liquid sloshing in waves is still of considerable interest within the computational fluid dynamics(CFD)and AI *** paper describes a data-driven stacking algorithm for fast prediction of roll motion response amplitudes in beam waves by constructing a hydrodynamics model of a damaged ship based on the dynamic overlapping grid CFD *** general idea is to optimize various parameters varying with four types of classical base models like multi-layer perception,support vector regression,random forest,and hist gradient boosting *** offers several attractive properties in terms of accuracy and efficiency by choosing the standard DTMB 5415 model with double damaged compartments for *** is clearly demonstrated that the predicted response amplitude operator(RAO)in the regular beam waves agrees well with the experimental data available,which verifies the accuracy of the established damaged ship hydrodynamics *** high-quality CFD samples,therefore,implementation of the designed stacking algorithm with its optimal combination can predict the damaged ship roll motion amplitudes effectively and accurately(e.g.,the coefficient of determination 0.9926,the average absolute error 0.0955 and CPU 3s),by comparison of four types of typical base models and their various ***,the established stacking algorithm provides one potential that can break through problems involving the time-consuming and low efficiency for large-scale lengthy CFD simulations.
PurposeWhile the Chinese securities market is booming, the phenomenon of listed companies falling into financial distress is also emerging, which affects the operation and development of enterprises and also jeopardiz...
详细信息
PurposeWhile the Chinese securities market is booming, the phenomenon of listed companies falling into financial distress is also emerging, which affects the operation and development of enterprises and also jeopardizes the interests of investors. Therefore, it is important to understand how to accurately and reasonably predict the financial distress of ***/methodology/approachIn the present study, ensemble feature selection (EFS) and improved stacking were used for financial distress prediction (FDP). Mutual information, analysis of variance (ANOVA), random forest (RF), genetic algorithms, and recursive feature elimination (RFE) were chosen for EFS to select features. Since there may be missing information when feeding the results of the base learner directly into the meta-learner, the features with high importance were fed into the meta-learner together. A screening layer was added to select the meta-learner with better performance. Finally, Optima hyperparameters were used for parameter tuning by the *** empirical study was conducted with a sample of A-share listed companies in China. The F1-score of the model constructed using the features screened by EFS reached 84.55%, representing an improvement of 4.37% compared to the original features. To verify the effectiveness of improved stacking, benchmark model comparison experiments were conducted. Compared to the original stacking model, the accuracy of the improved stacking model was improved by 0.44%, and the F1-score was improved by 0.51%. In addition, the improved stacking model had the highest area under the curve (AUC) value (0.905) among all the compared ***/valueCompared to previous models, the proposed FDP model has better performance, thus bridging the research gap of feature selection. The present study provides new ideas for stacking improvement research and a reference for subsequent research in this field.
The objective of this study is to anticipate the repayment behaviors of financially vulnerable debtors in Korea using a prediction model employing a stacking algorithm. To accomplish this goal, this study is conducted...
详细信息
The objective of this study is to anticipate the repayment behaviors of financially vulnerable debtors in Korea using a prediction model employing a stacking algorithm. To accomplish this goal, this study is conducted on 1,171,204 debtors with delinquent loans acquired by KAMCO since 2018. Following this analysis, the meta-model successfully predicted 87.7% of vulnerable debtors' repayment decisions, thus validating its efficacy in discerning debtors with high repayment potential. In addition, it is confirmed that a stacking algorithm can be utilized to construct a prediction model that can be universally applied across a wider range, resulting in a substantial increase in accuracy. This study is significant as it empirically predicts the repayment likelihood of vulnerable debtors in Korea through the utilization of data regarding large-scale non-performing loans. Moreover, the findings of this analysis suggest that financial institutions can enhance their proficiency in loan management by screening and overseeing debtors based on their repayment potential.
Soil moisture (SM) profoundly influences crop growth, yield, soil temperature regulation, and ecological balance maintenance and plays a pivotal role in water resources management and regulation. The focal objective o...
详细信息
Soil moisture (SM) profoundly influences crop growth, yield, soil temperature regulation, and ecological balance maintenance and plays a pivotal role in water resources management and regulation. The focal objective of this investigation is to identify feature parameters closely associated with soil moisture through the implementation of feature selection methods on multi-source remote sensing data. Specifically, three feature selection methods, namely SHApley Additive exPlanations (SHAP), information gain (Info-gain), and Info_gain boolean AND SHAP were validated in this study. The multi-source remote sensing data collected from Sentinel-1, Landsat-8, and Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Model (ASTGTM DEM) enabled the derivation of 25 characteristic parameters through sound computational approaches. Subsequently, a stacking algorithm integrating multiple machine-learning (ML) algorithms based on adaptive learning was engineered to accomplish soil moisture prediction. The attained prediction outcomes were then juxtaposed against those of single models, including Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost). Notably, the adoption of feature factors selected by the Info_gain algorithm in combination with the adaptive stacking (Ada-stacking) algorithm yielded the most optimal soil moisture prediction results. Specifically, the Mean Absolute Error (MAE) was determined to be 1.86 Vol. %, the Root Mean Square Error (RMSE) amounted to 2.68 Vol. %, and the R-squared (R2) reached 0.95. The multifactor integrated model that harnessed optical remote sensing data, radar backscatter coefficients, and topographic data exhibited remarkable accuracy in soil surface moisture retrieval, thus providing valuable insights for soil moisture inversion studies in the designate
The effective extraction of water-leaving reflectance using atmospheric correction (AC) algorithms is essential for accurately retrieving ocean color parameters. However, existing AC approaches designed for specific w...
详细信息
The effective extraction of water-leaving reflectance using atmospheric correction (AC) algorithms is essential for accurately retrieving ocean color parameters. However, existing AC approaches designed for specific water types often struggle with the varying optical properties of open and coastal waters. This study proposes an efficient multi-layer stacking method for AC (MSM AC) that is suitable for both clear and turbid waters. The implementation and validation of the method were conducted using Himawari-8 imagery. To address the lack of training data, 10,000 Rayleigh-corrected reflectance samples were synthesized for six Himawari-8 bands, using simulated water-leaving, which cover different optically complex water properties through a radiative transfer, and aerosol reflectance data under different geometrical conditions. Following the principle of heterogeneous integration, various meta-learners were preselected for model training, and the preliminary model was finetuned using in situ data. A weighted integration strategy was then employed to develop an MSM AC tailored to Himawari-8 image data. For comparative analysis, a near-infrared-shortwave infrared AC method and a general machine learning AC method were also implemented. Model evaluation and validation were performed using a test subset of simulated data and in-situ datasets. Validation results indicate that the MSM AC exhibits strong performance in the validation bands (470 nm, 510 nm, and 640 nm) on the in-situ dataset, with R2 values of 0.64, 0.91, and 0.82 and root-mean-square logarithmic deviation (RMSLD) values of 0.007 sr-1 , 0.004 sr-1 , and 0.005 sr-1 , respectively. Additionally, water bodies with varying optical complexities were simulated by restructuring the ocean color component content in the simulated data. The correction performances of MSM and comparative algorithms were evaluated using the median absolute error (MedAE) between the predicted and simulated water-leaving reflectance data.
Ultra-high voltage(UHV)transmission lines are an important part of China’s power grid and are often surrounded by a complex electromagnetic *** ground total electric field is considered a main electromagnetic environ...
详细信息
Ultra-high voltage(UHV)transmission lines are an important part of China’s power grid and are often surrounded by a complex electromagnetic *** ground total electric field is considered a main electromagnetic environment indicator of UHV transmission lines and is currently employed for reliable long-term operation of the power ***,the accurate prediction of the ground total electric field remains a technical *** this work,we collected the total electric field data from the Ningdong-Zhejiang±800 kV UHVDC transmission project,as of the Ling Shao line,and perform an outlier analysis of the total electric field *** show that the Local Outlier Factor(LOF)elimination algorithm has a small average difference and overcomes the performance of Density-Based Spatial Clustering of Applications with Noise(DBSCAN)and Isolated Forest elimination ***,the stacking algorithm has been found to have superior prediction accuracy than a variety of similar prediction algorithms,including the traditional finite *** low prediction error of the stacking algorithm highlights the superior ability to accurately forecast the ground total electric field of UHVDC transmission lines.
This paper aims to build an employee attrition classification model based on the stacking *** algorithm is applied to address the issue of data imbalance and the Randomforest feature importance ranking method is used ...
详细信息
This paper aims to build an employee attrition classification model based on the stacking *** algorithm is applied to address the issue of data imbalance and the Randomforest feature importance ranking method is used to resolve the overfitting problem after data cleaning and ***,different algorithms are used to establish classification models as control experiments,and R-squared indicators are used to ***,the stacking algorithm is used to establish the final classification *** model has practical and significant implications for both human resource management and employee attrition analysis.
The data-driven method is used widely to estimate the state of health (SOH) of the battery, but the selection of data features and the data training methods affect the estimation results greatly. With the stacking alg...
详细信息
The data-driven method is used widely to estimate the state of health (SOH) of the battery, but the selection of data features and the data training methods affect the estimation results greatly. With the stacking algorithm, this paper proposes a multi-feature fusion model to estimate battery SOH by fusing different feature parameters and combining support vector regression (SVR) and long short-term memory network (LSTM). The feature param-eters were extracted only from the current change curve of the constant voltage charging stage. The support vector regression based on grid search (GS-SVR) was selected as the primary-learner, and the primary SVR models were constructed through 5-fold cross-validation for different feature parameters. The LSTM was selected as the secondary-learner. With the stacking algorithm, LSTM was used to fuse multiple primary SVR models to form an ensemble learner model to improve the performance of multi-feature fusion. The battery aging test data set and NASA battery test data set were used to evaluate the effectiveness. The results verified the validity and superiority of the proposed method. Compared with the existing estimation methods, root mean square error is reduced by at least 0.11, and mean absolute percentage error is reduced by at least 0.12%.
Online learning is becoming a common learning method in the field of education. The correct classification of online learners plays a vital role in solving the key issues such as low pass rates and high dropout rates....
详细信息
Online learning is becoming a common learning method in the field of education. The correct classification of online learners plays a vital role in solving the key issues such as low pass rates and high dropout rates. In this paper, we propose a improved ensemble algorithm for classifying learners, which integrates feature selection and the improved stacking algorithm (stacking-PMLR). One feature selection algorithm is Mean Decrease Impurity algorithm based on Random Forest. It is used to investigate the learning behavior factors which contribute to class of learner. It is also used to select the most frequent features and to reduce the dimensions.. Analyzing learners' behavior features by the feature selection algorithm, we know that a number of chapters, interaction days, interactions times and video viewed times are the most important factors. Learners' behavior features from feature selection are used as the attribute input of stacking-PMLR for classifying learners. After that, we use the multilevel improved ensemble algorithmstacking-PMLR to classify learners. We improve the stacking algorithms in terms of its hierarchical structure, data features representation, combination strategy and classification algorithm according to its own characteristics. We use the improved stacking algorithm to construct the classification model. In addition, fifteen real world different type datasets in UCI machine learning repository are applied. The experimental results show that the improved stacking algorithm has better performance in accuracy, precision and F-1. It also shows the feasibility of the stacking-PMLR. Finally, we use feature selection and the stacking-PMLR algorithm to classify the public dataset of the edX online learning platform. The experimental results show that the performance of stacking-PMLR is better. It shows the practical value of the stacking-PMLR in online learning prediction.
暂无评论