BACKGROUND There is a lack of literature discussing the utilization of the stacking ensemble algorithm for predicting depression in patients with heart failure(HF).AIM To create a stacking model for predicting depress...BACKGROUND There is a lack of literature discussing the utilization of the stacking ensemble algorithm for predicting depression in patients with heart failure(HF).AIM To create a stacking model for predicting depression in patients with HF.METHODS This study analyzed data on 1084 HF patients from the National Health and Nutrition Examination Survey database spanning from 2005 to 2018.Through univariate analysis and the use of an artificial neural network algorithm,predictors significantly linked to depression were identified.These predictors were utilized to create a stacking model employing tree-based learners.The performances of both the individual models and the stacking model were assessed by using the test dataset.Furthermore,the SHapley additive exPlanations(SHAP)model was applied to interpret the stacking model.RESULTS The models included five predictors.Among these models,the stacking model demonstrated the highest performance,achieving an area under the curve of 0.77(95%CI:0.71-0.84),a sensitivity of 0.71,and a specificity of 0.68.The calibration curve supported the reliability of the models,and decision curve analysis confirmed their clinical value.The SHAP plot demonstrated that age had the most significant impact on the stacking model's output.CONCLUSION The stacking model demonstrated strong predictive performance.Clinicians can utilize this model to identify highrisk depression patients with HF,thus enabling early provision of psychological interventions.展开更多
The number of attacks is growing tremendously in tandem with the growth of internet technologies.As a result,protecting the private data from prying eyes has become a critical and tough undertaking.Many intrusion dete...The number of attacks is growing tremendously in tandem with the growth of internet technologies.As a result,protecting the private data from prying eyes has become a critical and tough undertaking.Many intrusion detection solutions have been offered by researchers in order to decrease the effect of these attacks.For attack detection,the prior system has created an SMSRPF(Stacking Model Significant Rule Power Factor)classifier.To provide creative instance detection,the SMSRPF combines the detection of trained classifiers such as DT(Decision Tree)and RF(Random Forest).Nevertheless,it does not generate any accuratefindings that are adequate.The suggested system has built an EWF(Ensemble Wrapper Filter)feature selection with SMSRPF classifier for attack detection so as to overcome this problem.The UNSW-NB15 dataset is used as an input in this proposed research project.Specifically,min–max normalization approach is used to pre-process the incoming data.The feature selection is then carried out using EWF.Based on the selected features,SMSRPF classifiers are utilized to detect the attacks.The SMSRPF is integrated with the trained classi-fiers such as DT and RF to create creative instance detection.After that,the testing data is classified using MCAR(Multi-Class Classification based on Association Rules).The SRPF judges the rules correctly even when the confidence and the lift measures fail.Regarding accuracy,precision,recall,f-measure,computation time,and error,the experimental findings suggest that the new system outperforms the prior systems.展开更多
为应对基于游戏的学习平台在知识追踪应用方面的不足,本研究利用Field Day Lab提供的教育游戏用户日志进行深入分析。采用方差法和Null Importance方法对数据集进行降维处理,并结合K折交叉验证与LightGBM算法,建立了一个高效的预测模型...为应对基于游戏的学习平台在知识追踪应用方面的不足,本研究利用Field Day Lab提供的教育游戏用户日志进行深入分析。采用方差法和Null Importance方法对数据集进行降维处理,并结合K折交叉验证与LightGBM算法,建立了一个高效的预测模型。此外,通过集成Logistic模型,构建起Stacking模型。研究表明,该模型在验证集上的Macro-F1值显著提升至0.699,同时也在测试集上显示出优异的泛化能力。本研究为教育游戏领域的知识追踪提供了创新方法,并为游戏开发与教育实践提供了宝贵参考,支持教育游戏的开发者为学生创造更有效的学习体验。展开更多
文摘BACKGROUND There is a lack of literature discussing the utilization of the stacking ensemble algorithm for predicting depression in patients with heart failure(HF).AIM To create a stacking model for predicting depression in patients with HF.METHODS This study analyzed data on 1084 HF patients from the National Health and Nutrition Examination Survey database spanning from 2005 to 2018.Through univariate analysis and the use of an artificial neural network algorithm,predictors significantly linked to depression were identified.These predictors were utilized to create a stacking model employing tree-based learners.The performances of both the individual models and the stacking model were assessed by using the test dataset.Furthermore,the SHapley additive exPlanations(SHAP)model was applied to interpret the stacking model.RESULTS The models included five predictors.Among these models,the stacking model demonstrated the highest performance,achieving an area under the curve of 0.77(95%CI:0.71-0.84),a sensitivity of 0.71,and a specificity of 0.68.The calibration curve supported the reliability of the models,and decision curve analysis confirmed their clinical value.The SHAP plot demonstrated that age had the most significant impact on the stacking model's output.CONCLUSION The stacking model demonstrated strong predictive performance.Clinicians can utilize this model to identify highrisk depression patients with HF,thus enabling early provision of psychological interventions.
文摘The number of attacks is growing tremendously in tandem with the growth of internet technologies.As a result,protecting the private data from prying eyes has become a critical and tough undertaking.Many intrusion detection solutions have been offered by researchers in order to decrease the effect of these attacks.For attack detection,the prior system has created an SMSRPF(Stacking Model Significant Rule Power Factor)classifier.To provide creative instance detection,the SMSRPF combines the detection of trained classifiers such as DT(Decision Tree)and RF(Random Forest).Nevertheless,it does not generate any accuratefindings that are adequate.The suggested system has built an EWF(Ensemble Wrapper Filter)feature selection with SMSRPF classifier for attack detection so as to overcome this problem.The UNSW-NB15 dataset is used as an input in this proposed research project.Specifically,min–max normalization approach is used to pre-process the incoming data.The feature selection is then carried out using EWF.Based on the selected features,SMSRPF classifiers are utilized to detect the attacks.The SMSRPF is integrated with the trained classi-fiers such as DT and RF to create creative instance detection.After that,the testing data is classified using MCAR(Multi-Class Classification based on Association Rules).The SRPF judges the rules correctly even when the confidence and the lift measures fail.Regarding accuracy,precision,recall,f-measure,computation time,and error,the experimental findings suggest that the new system outperforms the prior systems.
文摘为应对基于游戏的学习平台在知识追踪应用方面的不足,本研究利用Field Day Lab提供的教育游戏用户日志进行深入分析。采用方差法和Null Importance方法对数据集进行降维处理,并结合K折交叉验证与LightGBM算法,建立了一个高效的预测模型。此外,通过集成Logistic模型,构建起Stacking模型。研究表明,该模型在验证集上的Macro-F1值显著提升至0.699,同时也在测试集上显示出优异的泛化能力。本研究为教育游戏领域的知识追踪提供了创新方法,并为游戏开发与教育实践提供了宝贵参考,支持教育游戏的开发者为学生创造更有效的学习体验。
