Based on the complex correlation between the geochemical element distribution patterns at the surface and the types of bedrock and the powerful capabilities in capturing subtle of machine learning algorithms,four mach...Based on the complex correlation between the geochemical element distribution patterns at the surface and the types of bedrock and the powerful capabilities in capturing subtle of machine learning algorithms,four machine learning algorithms,namely,decision tree(DT),random forest(RF),XGBoost(XGB),and LightGBM(LGBM),were implemented for the lithostratigraphic classification and lithostratigraphic prediction of a quaternary coverage area based on stream sediment geochemical sampling data in the Chahanwusu River of Dulan County,Qinghai Province,China.The local Moran’s I to represent the features of spatial autocorrelations,and terrain factors to represent the features of surface geological processes,were calculated as additional features.The accuracy,precision,recall,and F1 scores were chosen as the evaluation indices and Voronoi diagrams were applied for visualization.The results indicate that XGB and LGBM models both performed well.They not only obtained relatively satisfactory classification performance but also predicted lithostratigraphic types of the Quaternary coverage area that are essentially consistent with their neighborhoods which have the known types.It is feasible to classify the lithostratigraphic types through the concentrations of geochemical elements in the sediments,and the XGB and LGBM algorithms are recommended for lithostratigraphic classification.展开更多
In this paper, we propose a software component under Windows that generates pseudo random numbers using RDS （Refined Descriptive Sampling） as required by the simulation. RDS is regarded as the best sampling method a...In this paper, we propose a software component under Windows that generates pseudo random numbers using RDS （Refined Descriptive Sampling） as required by the simulation. RDS is regarded as the best sampling method as shown in the literature. In order to validate the proposed component, its implementation is proposed on approximating integrals. The simulation results from RDS using ＂RDSRnd＂ generator were compared to those obtained using the generator ＂Rnd＂ included in the Pascal programming language under Windows. The best results are given by the proposed software component.展开更多
Robust stability for a class of sampled-data systems whose underlying continuous-time systems were subjected to additive structured perturbations was considered. The proposed upper bounds of the induced perturbations ...Robust stability for a class of sampled-data systems whose underlying continuous-time systems were subjected to additive structured perturbations was considered. The proposed upper bounds of the induced perturbations in discrete-time model were similar to those obtained in reference. A stable digital optimal state feedback controller whose design was based on the solution of Riccati equation was given. By considering stability based on the second method of Lyapunov, the robust stability bounds for discrete-time model was obtained. Combining the above findings, one sufficient condition of robust stability and a new region of robust stability on the underlying continuous-time system were obtained. Example was given to illustrate the proposed results. It was shown that the sampling period was a crucial design parameter.展开更多
基金Projects(41772348,42072326)supported by the National Natural Science Foundation of ChinaProject(2017YFC0601503)supported by the National Key Research and Development Program,China。
文摘Based on the complex correlation between the geochemical element distribution patterns at the surface and the types of bedrock and the powerful capabilities in capturing subtle of machine learning algorithms,four machine learning algorithms,namely,decision tree(DT),random forest(RF),XGBoost(XGB),and LightGBM(LGBM),were implemented for the lithostratigraphic classification and lithostratigraphic prediction of a quaternary coverage area based on stream sediment geochemical sampling data in the Chahanwusu River of Dulan County,Qinghai Province,China.The local Moran’s I to represent the features of spatial autocorrelations,and terrain factors to represent the features of surface geological processes,were calculated as additional features.The accuracy,precision,recall,and F1 scores were chosen as the evaluation indices and Voronoi diagrams were applied for visualization.The results indicate that XGB and LGBM models both performed well.They not only obtained relatively satisfactory classification performance but also predicted lithostratigraphic types of the Quaternary coverage area that are essentially consistent with their neighborhoods which have the known types.It is feasible to classify the lithostratigraphic types through the concentrations of geochemical elements in the sediments,and the XGB and LGBM algorithms are recommended for lithostratigraphic classification.
文摘In this paper, we propose a software component under Windows that generates pseudo random numbers using RDS （Refined Descriptive Sampling） as required by the simulation. RDS is regarded as the best sampling method as shown in the literature. In order to validate the proposed component, its implementation is proposed on approximating integrals. The simulation results from RDS using ＂RDSRnd＂ generator were compared to those obtained using the generator ＂Rnd＂ included in the Pascal programming language under Windows. The best results are given by the proposed software component.
基金Sponsored by the Special Research Foundation for the Doctor's Speciality of University(Grant No.20060214004) and the Key Scientific Research Founda-tion of Education Ministry(Grant No.206041) and the Key Scientific Research Foundation of Harbin Science Bureau(Grant No.2005AA1CG037).
文摘Robust stability for a class of sampled-data systems whose underlying continuous-time systems were subjected to additive structured perturbations was considered. The proposed upper bounds of the induced perturbations in discrete-time model were similar to those obtained in reference. A stable digital optimal state feedback controller whose design was based on the solution of Riccati equation was given. By considering stability based on the second method of Lyapunov, the robust stability bounds for discrete-time model was obtained. Combining the above findings, one sufficient condition of robust stability and a new region of robust stability on the underlying continuous-time system were obtained. Example was given to illustrate the proposed results. It was shown that the sampling period was a crucial design parameter.
