Seismic fault rupture can extend to the surface,and the resulting surface deformation can cause severe damage to civil engineering structures crossing the fault zones.Coseismic Surface Rupture Prediction Models(CSRPMs...Seismic fault rupture can extend to the surface,and the resulting surface deformation can cause severe damage to civil engineering structures crossing the fault zones.Coseismic Surface Rupture Prediction Models(CSRPMs)play a crucial role in the structural design of fault-crossing engineering and in the hazard analysis of fault-intensive areas.In this study,a new global coseismic surface rupture database was constructed by compiling 171 earthquake events(Mw:5.5-7.9)that caused surface rupture.In contrast to the fault classification in traditional empirical relationships,this study categorizes earthquake events as strike-slip,dip-slip,and oblique-slip.CSRPMs utilizing Bayesian ridge regression(BRR)were developed to estimate parameters such as surface rupture length,average displacement,and maximum displacement.Based on Bayesian theory,BRR combines the benefits of both ridge regression and Bayesian linear regression.This approach effectively addresses the issue of overfitting while ensuring the strong model robustness.The reliability of the CSRPMs was validated by residual analysis and comparison with post-earthquake observations from the 2023 Türkiye earthquake doublet.The BRR-CSRPMs with new fault classification criteria are more suitable for the probabilistic hazard analysis of complex fault systems and dislocation design of fault-crossing engineering.展开更多
The accuracy of the statistical learning model depends on the learning technique used which in turn depends on the dataset’s values.In most research studies,the existence of missing values(MVs)is a vital problem.In a...The accuracy of the statistical learning model depends on the learning technique used which in turn depends on the dataset’s values.In most research studies,the existence of missing values(MVs)is a vital problem.In addition,any dataset with MVs cannot be used for further analysis or with any data driven tool especially when the percentage of MVs are high.In this paper,the authors propose a novel algorithm for dealing with MVs depending on the feature selec-tion(FS)of similarity classifier with fuzzy entropy measure.The proposed algo-rithm imputes MVs in cumulative order.The candidate feature to be manipulated is selected using similarity classifier with Parkash’s fuzzy entropy measure.The predictive model to predict MVs within the candidate feature is the Bayesian Ridge Regression(BRR)technique.Furthermore,any imputed features will be incorporated within the BRR equation to impute the MVs in the next chosen incomplete feature.The proposed algorithm was compared against some practical state-of-the-art imputation methods by conducting an experiment on four medical datasets which were gathered from several databases repository with MVs gener-ated from the three missingness mechanisms.The evaluation metrics of mean abso-lute error(MAE),root mean square error(RMSE)and coefficient of determination(R2 score)were used to measure the performance.The results exhibited that perfor-mance vary depending on the size of the dataset,amount of MVs and the missing-ness mechanism type.Moreover,compared to other methods,the results showed that the proposed method gives better accuracy and less error in most cases.展开更多
基金Foundation of China under Grant Nos. U2139207 and 52378517the Natural Science Foundation of Hubei Province under Grant No. 2023AFB934
文摘Seismic fault rupture can extend to the surface,and the resulting surface deformation can cause severe damage to civil engineering structures crossing the fault zones.Coseismic Surface Rupture Prediction Models(CSRPMs)play a crucial role in the structural design of fault-crossing engineering and in the hazard analysis of fault-intensive areas.In this study,a new global coseismic surface rupture database was constructed by compiling 171 earthquake events(Mw:5.5-7.9)that caused surface rupture.In contrast to the fault classification in traditional empirical relationships,this study categorizes earthquake events as strike-slip,dip-slip,and oblique-slip.CSRPMs utilizing Bayesian ridge regression(BRR)were developed to estimate parameters such as surface rupture length,average displacement,and maximum displacement.Based on Bayesian theory,BRR combines the benefits of both ridge regression and Bayesian linear regression.This approach effectively addresses the issue of overfitting while ensuring the strong model robustness.The reliability of the CSRPMs was validated by residual analysis and comparison with post-earthquake observations from the 2023 Türkiye earthquake doublet.The BRR-CSRPMs with new fault classification criteria are more suitable for the probabilistic hazard analysis of complex fault systems and dislocation design of fault-crossing engineering.
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University(KAU)Jeddah,Saudi Arabia,under grant No.(PH:13-130-1442).
文摘The accuracy of the statistical learning model depends on the learning technique used which in turn depends on the dataset’s values.In most research studies,the existence of missing values(MVs)is a vital problem.In addition,any dataset with MVs cannot be used for further analysis or with any data driven tool especially when the percentage of MVs are high.In this paper,the authors propose a novel algorithm for dealing with MVs depending on the feature selec-tion(FS)of similarity classifier with fuzzy entropy measure.The proposed algo-rithm imputes MVs in cumulative order.The candidate feature to be manipulated is selected using similarity classifier with Parkash’s fuzzy entropy measure.The predictive model to predict MVs within the candidate feature is the Bayesian Ridge Regression(BRR)technique.Furthermore,any imputed features will be incorporated within the BRR equation to impute the MVs in the next chosen incomplete feature.The proposed algorithm was compared against some practical state-of-the-art imputation methods by conducting an experiment on four medical datasets which were gathered from several databases repository with MVs gener-ated from the three missingness mechanisms.The evaluation metrics of mean abso-lute error(MAE),root mean square error(RMSE)and coefficient of determination(R2 score)were used to measure the performance.The results exhibited that perfor-mance vary depending on the size of the dataset,amount of MVs and the missing-ness mechanism type.Moreover,compared to other methods,the results showed that the proposed method gives better accuracy and less error in most cases.
