首页|New Machine Learning Study Findings Have Been Reported by Investigators at South west Jiaotong University (Machine Learningdriven Feature Importance Appraisal o f Seismic Parameters On Tunnel Damage and Seismic Fragility Prediction)
New Machine Learning Study Findings Have Been Reported by Investigators at South west Jiaotong University (Machine Learningdriven Feature Importance Appraisal o f Seismic Parameters On Tunnel Damage and Seismic Fragility Prediction)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-Research findings on Machine Learning are discussed in a new report. According tonews reporting out of Sichuan, Peopl e's Republic of China, by NewsRx editors, research stated, "Thisstudy proposes a machine learning-driven approach for the analysis of the feature importance of seismicparameters on tunnel damage and seismic fragility prediction. The Incre mental Dynamic Analysis (IDA)method serves as the fundamental database for vuln erability analysis."Financial supporters for this research include Postdoctoral Fellowship Program o f China PostdoctoralScience Foundation, National Natural Science Foundation of China (NSFC), Fundamental Research Fundsfor the Central Universities.Our news journalists obtained a quote from the research from Southwest Jiaotong University, "Strengthand deformation yield criteria are chosen to comprehensive ly assess the impact of different seismic parameterson the vulnerability of tun nels to seismic events. Three machine learning algorithms, namelyExtreme Gradie nt Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM), areutilized to develop models for classifying and regressing tunnel damage under s eismic conditions. Followingparameter tuning, the models' performance in multi- classification, binary classification, and regression predictionis assessed, wi th XGBoost and RF models exhibiting outstanding performance. Feature importanceanalysis of seismic parameters in XGBoost and RF models for multi-classification , binary classification,and regression is performed using Shapley additive expl anations (SHAP). The correlation analysis betweenSHAP-based feature values and predictions reveals that Peak Ground Displacement (PGD) has the highestinfluenc e in the regression model. Utilizing the interaction dependencies among crucial features in theregression model, fragility curves for tunnels based on these ke y features are effectively derived."
SichuanPeople's Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningSouthwest Jiaotong University
NETL
NSTL
