This paper presents a model-free adaptive iterative learning control(ILC)scheme called a proportional-type ILC scheme for non-linear systems.The obvious characteristic of the proposed ILC scheme is that we can easily ...This paper presents a model-free adaptive iterative learning control(ILC)scheme called a proportional-type ILC scheme for non-linear systems.The obvious characteristic of the proposed ILC scheme is that we can easily finish the ILC task just utilising the Lipschitz constant of the system.In the proposed ILC scheme,the time-vary learning gain can be produced merely by input and output(I/O)measurements.Moreover,the convergence conclusion can be expressed by the ranges of the pseudo-partial derivative and the learning gain.In actual operation,a reasonable and useful convergence condition by a constant is also provided for selection.At last,the effectiveness of the proposed ILC scheme is shown by simulations.展开更多
Recurrent events data and gap times between recurrent events are frequently encountered in many clinical and observational studies,and often more than one type of recurrent events is of interest.In this paper,we consi...Recurrent events data and gap times between recurrent events are frequently encountered in many clinical and observational studies,and often more than one type of recurrent events is of interest.In this paper,we consider a proportional hazards model for multiple type recurrent gap times data to assess the effect of covaxiates on the censored event processes of interest.An estimating equation approach is used to obtain the estimators of regression coefficients and baseline cumulative hazard functions.We examine asymptotic properties of the proposed estimators.Finite sample properties of these estimators are demonstrated by simulations.展开更多
文摘This paper presents a model-free adaptive iterative learning control(ILC)scheme called a proportional-type ILC scheme for non-linear systems.The obvious characteristic of the proposed ILC scheme is that we can easily finish the ILC task just utilising the Lipschitz constant of the system.In the proposed ILC scheme,the time-vary learning gain can be produced merely by input and output(I/O)measurements.Moreover,the convergence conclusion can be expressed by the ranges of the pseudo-partial derivative and the learning gain.In actual operation,a reasonable and useful convergence condition by a constant is also provided for selection.At last,the effectiveness of the proposed ILC scheme is shown by simulations.
基金supported in part by Natural Science Foundation of Hubei(08BA164)Major Research Program of Hubei Provincial Department of Education(09B2001)+2 种基金supported in part by National Natural Science Foundation of China(1117112)Doctoral Fund of Ministry of Education of China(20090076110001)National Statistical Science Research Major Program of China(2011LZ051)
文摘Recurrent events data and gap times between recurrent events are frequently encountered in many clinical and observational studies,and often more than one type of recurrent events is of interest.In this paper,we consider a proportional hazards model for multiple type recurrent gap times data to assess the effect of covaxiates on the censored event processes of interest.An estimating equation approach is used to obtain the estimators of regression coefficients and baseline cumulative hazard functions.We examine asymptotic properties of the proposed estimators.Finite sample properties of these estimators are demonstrated by simulations.
