Slag viscosity plays a crucial role in the smelting process.A slag viscosity prediction model was developed by integrating hyperparameter optimization algorithms,machine learning,and SHapley Additive exPlanations(SHAP...Slag viscosity plays a crucial role in the smelting process.A slag viscosity prediction model was developed by integrating hyperparameter optimization algorithms,machine learning,and SHapley Additive exPlanations(SHAP)analysis.The developed slag viscosity prediction models were evaluated using multiple statistical metrics,leading to the identification of the optimal model—Bayesian optimization-based categorical boosting(BO-CatBoost).And this model was further compared with existing models,including NPL model,FactSage+Roscoe-Einstein(RE)equation,artificial neural network model+RE equation,Riboud model+RE equation,and Zhang model.The results indicate that the slag viscosity prediction model based on BO-CatBoost outperforms all other models,achieving a coefficient of determination of 0.9897,a root mean square error of 1.0619,a mean absolute error of 0.6133,and a hit ratio of 95.1%.The global interpretability analysis of SHAP analysis was used to reveal the importance degree of different features on slag viscosity.The local interpretability analysis of SHAP analysis was used to obtain the quantitative influence of different features on slag viscosity in specific samples.The high-accuracy and interpretable slag viscosity prediction model developed is beneficial to the intelligent design of slag composition.展开更多
Ensuring independent mobility for older adults has become a public health and social concern in China owing to its rapidly aging population.To explore independent mobility trends among older adults and the impact of s...Ensuring independent mobility for older adults has become a public health and social concern in China owing to its rapidly aging population.To explore independent mobility trends among older adults and the impact of sociodemo-graphic characteristics in recent years,this study used data from the Chinese Longitudinal Healthy Longevity Survey from 2012 to 2018,combined with binomial logit regression and CatBoost-Shapley additive explanation(SHAP)method to analyze the relationship between independent mobility and sociodemographic characteristics under bus and walking-oriented environments.Study findings indicated that age and gender significantly affected the independent mobility of older adults.Policymaking should prioritize the needs of older adults,focusing on age and gender differ-ences.Additionally,living expense adequacy significantly influenced independent mobility.Policies should substan-tially support economically disadvantaged older adults,en-suring their basic needs are met through subsidies and other measures.Moreover,the study found a notable impact of widowhood on independent mobility,suggesting enhanced social care and mental health support for widowed older adults,especially those who are long-lived.The outcomes of this study provided evidence for policymakers,which are beneficial for developing elderly-friendly travel policies to ensure and enhance the quality of life and independent mo-bility of older adults.展开更多
The methods of network attacks have become increasingly sophisticated,rendering traditional cybersecurity defense mechanisms insufficient to address novel and complex threats effectively.In recent years,artificial int...The methods of network attacks have become increasingly sophisticated,rendering traditional cybersecurity defense mechanisms insufficient to address novel and complex threats effectively.In recent years,artificial intelligence has achieved significant progress in the field of network security.However,many challenges and issues remain,particularly regarding the interpretability of deep learning and ensemble learning algorithms.To address the challenge of enhancing the interpretability of network attack prediction models,this paper proposes a method that combines Light Gradient Boosting Machine(LGBM)and SHapley Additive exPlanations(SHAP).LGBM is employed to model anomalous fluctuations in various network indicators,enabling the rapid and accurate identification and prediction of potential network attack types,thereby facilitating the implementation of timely defense measures,the model achieved an accuracy of 0.977,precision of 0.985,recall of 0.975,and an F1 score of 0.979,demonstrating better performance compared to other models in the domain of network attack prediction.SHAP is utilized to analyze the black-box decision-making process of the model,providing interpretability by quantifying the contribution of each feature to the prediction results and elucidating the relationships between features.The experimental results demonstrate that the network attack predictionmodel based on LGBM exhibits superior accuracy and outstanding predictive capabilities.Moreover,the SHAP-based interpretability analysis significantly improves the model’s transparency and interpretability.展开更多
Deep learning models have become a core technological tool in the field of medical image analysis.However,these models often suffer from a lack of transparency in their decision-making processes,leading to challenges ...Deep learning models have become a core technological tool in the field of medical image analysis.However,these models often suffer from a lack of transparency in their decision-making processes,leading to challenges related to trust and interpret ability in clinical applications.To address this issue,explainable artificial intelligence(XAI)techniques have been applied to medical image analysis.While showing promising potential,XAI also brings significant ethical risks in practice—most notably,the problem of spurious explanations.Such explanations may rise further concerns regarding patient privacy,data security,and the attribution of decisionmaking authority in medical contexts.This paper analyzes the application of XAI methods—particularly saliency aps—in medical image interpretation,identifies the underlying causes of spurious explanations,and proposes possible mitigation strategies.The aim is to contribute to the responsible and sustainable integration of explainable AI into clinical practice.展开更多
Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the sett...Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the settlement caused by tunneling.However,well-performing ML models are usually less interpretable.Irrelevant input features decrease the performance and interpretability of an ML model.Nonetheless,feature selection,a critical step in the ML pipeline,is usually ignored in most studies that focused on predicting tunneling-induced settlement.This study applies four techniques,i.e.Pearson correlation method,sequential forward selection(SFS),sequential backward selection(SBS)and Boruta algorithm,to investigate the effect of feature selection on the model’s performance when predicting the tunneling-induced maximum surface settlement(S_(max)).The data set used in this study was compiled from two metro tunnel projects excavated in Hangzhou,China using earth pressure balance(EPB)shields and consists of 14 input features and a single output(i.e.S_(max)).The ML model that is trained on features selected from the Boruta algorithm demonstrates the best performance in both the training and testing phases.The relevant features chosen from the Boruta algorithm further indicate that tunneling-induced settlement is affected by parameters related to tunnel geometry,geological conditions and shield operation.The recently proposed Shapley additive explanations(SHAP)method explores how the input features contribute to the output of a complex ML model.It is observed that the larger settlements are induced during shield tunneling in silty clay.Moreover,the SHAP analysis reveals that the low magnitudes of face pressure at the top of the shield increase the model’s output。展开更多
基金funded by the National Natural Science Foundation of China(No.52374321)the National Key Research and Development Program of China(No.2024YFB3713602)the Youth Science and Technology Innovation Fund of Jianlong Group-University of Science and Technology Beijing(No.20231235).
文摘Slag viscosity plays a crucial role in the smelting process.A slag viscosity prediction model was developed by integrating hyperparameter optimization algorithms,machine learning,and SHapley Additive exPlanations(SHAP)analysis.The developed slag viscosity prediction models were evaluated using multiple statistical metrics,leading to the identification of the optimal model—Bayesian optimization-based categorical boosting(BO-CatBoost).And this model was further compared with existing models,including NPL model,FactSage+Roscoe-Einstein(RE)equation,artificial neural network model+RE equation,Riboud model+RE equation,and Zhang model.The results indicate that the slag viscosity prediction model based on BO-CatBoost outperforms all other models,achieving a coefficient of determination of 0.9897,a root mean square error of 1.0619,a mean absolute error of 0.6133,and a hit ratio of 95.1%.The global interpretability analysis of SHAP analysis was used to reveal the importance degree of different features on slag viscosity.The local interpretability analysis of SHAP analysis was used to obtain the quantitative influence of different features on slag viscosity in specific samples.The high-accuracy and interpretable slag viscosity prediction model developed is beneficial to the intelligent design of slag composition.
基金The National Natural Science Foundation of China (No. 52272367)the Natural Science Foundation of Jiangsu Province (No. BK20231324)。
文摘Ensuring independent mobility for older adults has become a public health and social concern in China owing to its rapidly aging population.To explore independent mobility trends among older adults and the impact of sociodemo-graphic characteristics in recent years,this study used data from the Chinese Longitudinal Healthy Longevity Survey from 2012 to 2018,combined with binomial logit regression and CatBoost-Shapley additive explanation(SHAP)method to analyze the relationship between independent mobility and sociodemographic characteristics under bus and walking-oriented environments.Study findings indicated that age and gender significantly affected the independent mobility of older adults.Policymaking should prioritize the needs of older adults,focusing on age and gender differ-ences.Additionally,living expense adequacy significantly influenced independent mobility.Policies should substan-tially support economically disadvantaged older adults,en-suring their basic needs are met through subsidies and other measures.Moreover,the study found a notable impact of widowhood on independent mobility,suggesting enhanced social care and mental health support for widowed older adults,especially those who are long-lived.The outcomes of this study provided evidence for policymakers,which are beneficial for developing elderly-friendly travel policies to ensure and enhance the quality of life and independent mo-bility of older adults.
基金supported by the National Natural Science Foundation of China Project(No.62302540)please visit their website at https://www.nsfc.gov.cn/(accessed on 18 June 2024).
文摘The methods of network attacks have become increasingly sophisticated,rendering traditional cybersecurity defense mechanisms insufficient to address novel and complex threats effectively.In recent years,artificial intelligence has achieved significant progress in the field of network security.However,many challenges and issues remain,particularly regarding the interpretability of deep learning and ensemble learning algorithms.To address the challenge of enhancing the interpretability of network attack prediction models,this paper proposes a method that combines Light Gradient Boosting Machine(LGBM)and SHapley Additive exPlanations(SHAP).LGBM is employed to model anomalous fluctuations in various network indicators,enabling the rapid and accurate identification and prediction of potential network attack types,thereby facilitating the implementation of timely defense measures,the model achieved an accuracy of 0.977,precision of 0.985,recall of 0.975,and an F1 score of 0.979,demonstrating better performance compared to other models in the domain of network attack prediction.SHAP is utilized to analyze the black-box decision-making process of the model,providing interpretability by quantifying the contribution of each feature to the prediction results and elucidating the relationships between features.The experimental results demonstrate that the network attack predictionmodel based on LGBM exhibits superior accuracy and outstanding predictive capabilities.Moreover,the SHAP-based interpretability analysis significantly improves the model’s transparency and interpretability.
文摘Deep learning models have become a core technological tool in the field of medical image analysis.However,these models often suffer from a lack of transparency in their decision-making processes,leading to challenges related to trust and interpret ability in clinical applications.To address this issue,explainable artificial intelligence(XAI)techniques have been applied to medical image analysis.While showing promising potential,XAI also brings significant ethical risks in practice—most notably,the problem of spurious explanations.Such explanations may rise further concerns regarding patient privacy,data security,and the attribution of decisionmaking authority in medical contexts.This paper analyzes the application of XAI methods—particularly saliency aps—in medical image interpretation,identifies the underlying causes of spurious explanations,and proposes possible mitigation strategies.The aim is to contribute to the responsible and sustainable integration of explainable AI into clinical practice.
基金support provided by The Science and Technology Development Fund,Macao SAR,China(File Nos.0057/2020/AGJ and SKL-IOTSC-2021-2023)Science and Technology Program of Guangdong Province,China(Grant No.2021A0505080009).
文摘Accurate prediction of shield tunneling-induced settlement is a complex problem that requires consideration of many influential parameters.Recent studies reveal that machine learning(ML)algorithms can predict the settlement caused by tunneling.However,well-performing ML models are usually less interpretable.Irrelevant input features decrease the performance and interpretability of an ML model.Nonetheless,feature selection,a critical step in the ML pipeline,is usually ignored in most studies that focused on predicting tunneling-induced settlement.This study applies four techniques,i.e.Pearson correlation method,sequential forward selection(SFS),sequential backward selection(SBS)and Boruta algorithm,to investigate the effect of feature selection on the model’s performance when predicting the tunneling-induced maximum surface settlement(S_(max)).The data set used in this study was compiled from two metro tunnel projects excavated in Hangzhou,China using earth pressure balance(EPB)shields and consists of 14 input features and a single output(i.e.S_(max)).The ML model that is trained on features selected from the Boruta algorithm demonstrates the best performance in both the training and testing phases.The relevant features chosen from the Boruta algorithm further indicate that tunneling-induced settlement is affected by parameters related to tunnel geometry,geological conditions and shield operation.The recently proposed Shapley additive explanations(SHAP)method explores how the input features contribute to the output of a complex ML model.It is observed that the larger settlements are induced during shield tunneling in silty clay.Moreover,the SHAP analysis reveals that the low magnitudes of face pressure at the top of the shield increase the model’s output。
