Background:Coronary heart disease(CHD)remains a prominent cause of mortality globally,necessitating early and accurate detection methods.Traditional diagnostic approaches can be invasive,costly,and time-consuming,nece...Background:Coronary heart disease(CHD)remains a prominent cause of mortality globally,necessitating early and accurate detection methods.Traditional diagnostic approaches can be invasive,costly,and time-consuming,necessitating the need for more efficient alternatives.This aimed to optimize the Light Gradient-Boosting Machine(LightGBM)algorithm to enhance its performance and accuracy in the early detection of CHD,providing a reliable,cost-effective,and non-invasive diagnostic tool.Methods:The Framingham Heart Study(FHS)dataset publicly available on Kaggle was used in this study.Multiple Imputations by Chained Equations(MICE)were applied separately to the training and testing sets to handle missing data.Borderline-SMOTE(Synthetic Minority Over-sampling Technique)was used on the training set to balance the dataset.The LightGBM algorithm was selected for its efficiency in classification tasks,and Bayesian Optimization with Tree-structured Parzen Estimator(TPE)was employed to fine-tune its hyperparameters.The optimized LightGBM model was trained and evaluated using metrics such as accuracy,precision,and AUC-ROC on the test set,with cross-validation to ensure robustness and generalizability.Findings:The optimized LightGBM model showed significant improvement in early CHD detection.The baseline LightGBM model with dropped missing values had an accuracy of 0.8333,sensitivity of 0.1081,precision of 0.3429,F1 score of 0.1644,and AUC of 0.6875.With MICE imputation,performance improved to an accuracy of 0.9399,sensitivity of 0.6693,precision of 0.9043,F1 score of 0.7692,and AUC of 0.9457.The combined approach of Borderline-SMOTE,MICE imputation,and TPE for LightGBM achieved an accuracy of 0.9882,sensitivity of 0.9370,precision of 0.9835,F1 score of 0.9597,and AUC of 0.9963,indicating a highly effective and robust model.Interpretation:The optimized model demonstrated outstanding performance in early CHD detection.The study’s strengths include its comprehensive approach to addressing missing data and class imbalance and the fine-tuning of hyperparameters through Bayesian Optimization.However,there is a need to test with other datasets for its generalizability to be well-established.This study provides a strong framework for early CHD detection,improving clinical practice by allowing for more precise and dependable diagnostics and effective interventions.展开更多
Reducing carbon emissions from the transport sector is essential for realizing the carbon neutrality goal in China.Despite substantial studies on the influence of urban form on transport cO_(2)emissions,most of them h...Reducing carbon emissions from the transport sector is essential for realizing the carbon neutrality goal in China.Despite substantial studies on the influence of urban form on transport cO_(2)emissions,most of them have treated the effects as a linear process,and few have studied their nonlinear relationships.This research focused on 274 Chinese cities in 2019 and applied the gradient-boosting decision tree(GBDT)model to investigate the nonlinear effects of four aspects of urban form,including compactness,complexity,scale,and fragmentation,on urban transport CO_(2)emissions.It was found that urban form contributed 20.48%to per capita transport CO_(2)emissions(PTCEs),which is less than the contribution of socioeconomic development but more than that of transport infrastructure.The contribution of urban form to total transport CO_(2)emissions(TCEs)was the lowest,at 14.3%.In particular,the effect of compactness on TCEs was negative within a threshold,while its effect on PTCEs showed an inverted U-shaped relationship.The effect of complexity on PTCEs was positive,and its effect on TCEs was nonlinear.The effect of scale on TCEs and PTCEs was positive within a threshold and negative beyond that threshold.The effect of fragmentation on TCEs was also nonlinear,while its effect on PTCEs was positively linear.These results show the complex effects of the urban form on transport CO_(2)emissions.Thus,strategies for optimizing urban form and reducing urban transport carbon emissions are recommended for the future.展开更多
Machine-learning(ML)models are novel and robust tools to establish structure-to-property connection on the basis of computationally expensive ab-initio datasets.For advanced technologies,predicting novel materials and...Machine-learning(ML)models are novel and robust tools to establish structure-to-property connection on the basis of computationally expensive ab-initio datasets.For advanced technologies,predicting novel materials and identifying their specification are critical issues.Two-dimensional(2D)materials are currently a rapidly growing class which show highly desirable properties for diverse advanced technologies.In this work,our objective is to search for desirable properties,such as the electronic band gap and total energy,among others,for which the accelerated prediction is highly appealing,prior to conducting accurate theoretical and experimental investigations.Among all available componential methods,gradient-boosted(GB)ML algorithms are known to provide highly accurate predictions and have shown great potential to predict material properties based on the importance of features.In this work,we applied the GB algorithm to a dataset of electronic and structural properties of 2D materials in order to predict the specification with high accuracy.Conducted statistical analysis of the selected features identifies design guidelines for the discovery of novel 2D materials with desired properties.展开更多
Modeling the application of train operation adjustment actions to recover from delays is of great importance to supporting the decision-making of dispatchers.In this study,the effects of two train operation adjustment...Modeling the application of train operation adjustment actions to recover from delays is of great importance to supporting the decision-making of dispatchers.In this study,the effects of two train operation adjustment actions on train delay recovery were explored using train operation records from scheduled and actual train timetables.First,the modeling data were sorted to extract the possible influencing factors under two typical train operation adjustment actions,namely the compression of the train dwell time at stations and the compression of the train running time in sections.Stepwise regression methods were then employed to determine the importance of the influencing factors corresponding to the train delay recovery time,namely the delay time,the scheduled supplement time,the running interval,the occurrence time,and the place where the delay occurred,under the two train operation adjustment actions.Finally,the gradient-boosted regression tree(GBRT)algorithm was applied to construct a delay recovery model to predict the delay recovery effects of the train operation adjustment actions.A comparison of the prediction results of the GBRT model with those of a random forest model confirmed the better performance of the GBRT prediction model.展开更多
文摘Background:Coronary heart disease(CHD)remains a prominent cause of mortality globally,necessitating early and accurate detection methods.Traditional diagnostic approaches can be invasive,costly,and time-consuming,necessitating the need for more efficient alternatives.This aimed to optimize the Light Gradient-Boosting Machine(LightGBM)algorithm to enhance its performance and accuracy in the early detection of CHD,providing a reliable,cost-effective,and non-invasive diagnostic tool.Methods:The Framingham Heart Study(FHS)dataset publicly available on Kaggle was used in this study.Multiple Imputations by Chained Equations(MICE)were applied separately to the training and testing sets to handle missing data.Borderline-SMOTE(Synthetic Minority Over-sampling Technique)was used on the training set to balance the dataset.The LightGBM algorithm was selected for its efficiency in classification tasks,and Bayesian Optimization with Tree-structured Parzen Estimator(TPE)was employed to fine-tune its hyperparameters.The optimized LightGBM model was trained and evaluated using metrics such as accuracy,precision,and AUC-ROC on the test set,with cross-validation to ensure robustness and generalizability.Findings:The optimized LightGBM model showed significant improvement in early CHD detection.The baseline LightGBM model with dropped missing values had an accuracy of 0.8333,sensitivity of 0.1081,precision of 0.3429,F1 score of 0.1644,and AUC of 0.6875.With MICE imputation,performance improved to an accuracy of 0.9399,sensitivity of 0.6693,precision of 0.9043,F1 score of 0.7692,and AUC of 0.9457.The combined approach of Borderline-SMOTE,MICE imputation,and TPE for LightGBM achieved an accuracy of 0.9882,sensitivity of 0.9370,precision of 0.9835,F1 score of 0.9597,and AUC of 0.9963,indicating a highly effective and robust model.Interpretation:The optimized model demonstrated outstanding performance in early CHD detection.The study’s strengths include its comprehensive approach to addressing missing data and class imbalance and the fine-tuning of hyperparameters through Bayesian Optimization.However,there is a need to test with other datasets for its generalizability to be well-established.This study provides a strong framework for early CHD detection,improving clinical practice by allowing for more precise and dependable diagnostics and effective interventions.
基金National Natural Science Foundation of China,No.42071227,No.42371214。
文摘Reducing carbon emissions from the transport sector is essential for realizing the carbon neutrality goal in China.Despite substantial studies on the influence of urban form on transport cO_(2)emissions,most of them have treated the effects as a linear process,and few have studied their nonlinear relationships.This research focused on 274 Chinese cities in 2019 and applied the gradient-boosting decision tree(GBDT)model to investigate the nonlinear effects of four aspects of urban form,including compactness,complexity,scale,and fragmentation,on urban transport CO_(2)emissions.It was found that urban form contributed 20.48%to per capita transport CO_(2)emissions(PTCEs),which is less than the contribution of socioeconomic development but more than that of transport infrastructure.The contribution of urban form to total transport CO_(2)emissions(TCEs)was the lowest,at 14.3%.In particular,the effect of compactness on TCEs was negative within a threshold,while its effect on PTCEs showed an inverted U-shaped relationship.The effect of complexity on PTCEs was positive,and its effect on TCEs was nonlinear.The effect of scale on TCEs and PTCEs was positive within a threshold and negative beyond that threshold.The effect of fragmentation on TCEs was also nonlinear,while its effect on PTCEs was positively linear.These results show the complex effects of the urban form on transport CO_(2)emissions.Thus,strategies for optimizing urban form and reducing urban transport carbon emissions are recommended for the future.
文摘Machine-learning(ML)models are novel and robust tools to establish structure-to-property connection on the basis of computationally expensive ab-initio datasets.For advanced technologies,predicting novel materials and identifying their specification are critical issues.Two-dimensional(2D)materials are currently a rapidly growing class which show highly desirable properties for diverse advanced technologies.In this work,our objective is to search for desirable properties,such as the electronic band gap and total energy,among others,for which the accelerated prediction is highly appealing,prior to conducting accurate theoretical and experimental investigations.Among all available componential methods,gradient-boosted(GB)ML algorithms are known to provide highly accurate predictions and have shown great potential to predict material properties based on the importance of features.In this work,we applied the GB algorithm to a dataset of electronic and structural properties of 2D materials in order to predict the specification with high accuracy.Conducted statistical analysis of the selected features identifies design guidelines for the discovery of novel 2D materials with desired properties.
基金the National Nature Science Foundation of China(Nos.71871188 and U1834209)the Science and Technology Department of Sichuan Province(No.2018JY0567)。
文摘Modeling the application of train operation adjustment actions to recover from delays is of great importance to supporting the decision-making of dispatchers.In this study,the effects of two train operation adjustment actions on train delay recovery were explored using train operation records from scheduled and actual train timetables.First,the modeling data were sorted to extract the possible influencing factors under two typical train operation adjustment actions,namely the compression of the train dwell time at stations and the compression of the train running time in sections.Stepwise regression methods were then employed to determine the importance of the influencing factors corresponding to the train delay recovery time,namely the delay time,the scheduled supplement time,the running interval,the occurrence time,and the place where the delay occurred,under the two train operation adjustment actions.Finally,the gradient-boosted regression tree(GBRT)algorithm was applied to construct a delay recovery model to predict the delay recovery effects of the train operation adjustment actions.A comparison of the prediction results of the GBRT model with those of a random forest model confirmed the better performance of the GBRT prediction model.
