摘要:

The estimation of ARMA (autoregressive-moving-average) models and of Kalman-Bucy filter models of stationary time-series in cases of complete parameter and Covariance ignorance can be obtained from first identifying a corresponding pure AR (autoregressive) model of finite order. Since the correct AR model is, in general, of infinite order, a bias is introduced in an otherwise consistent estimation procedure. Upper bounds of this bias are presently estimated in terms of a bound on the error in the corresponding innovations process. This bound is shown to converge to zero with increasing the order of the AR model or for the correct order if this order is finite. The above upper bound is thus also shown to yield a criterion for evaluating the finite order to approximate infinite AR models.

ISSN:0020-7721    

DOI:10.1080/00207727508941789

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

In this paper, a preliminary study is made of the dynamic optimization problem for a river with many polluters using a recently developed model of a section of the river Cam near Cambridge in England. Because of the high dimensionality of the system it is computationally prohibitive to obtain optimal solutions. However, the system has a fairly simple structure which could be utilized to alleviate the computational burden. A simple hierarchical structure is proposed for the river pollution control and the strategy is demonstrated on a digital simulation. For the practical implementation of the strategy, it is necessary, however, to have available the state vector of the system. In practice, only certain corrupted measurements of the outputs are available. It is therefore necessary to construct a state estimator. Like the optimal controller, the optimal estimator also requires prohibitive amounts of computation. However, a hierarchical strategy similar to the control strategy could be used to alleviate the computational burden. Such an estimator is also demonstrated on a digital simulation of the river.

ISSN:0020-7721    

DOI:10.1080/00207727508941790

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

A new clustering technique, based on the concept of immediato neighbourhood, with a novel capability to self-learn the number of clusters expected in the unsupervized environment, has been developed. The method compares favourably with other clustering schemes based on distance measures, both in terms of conceptual innovations and computational economy. Test implementation of the scheme usingC-l flight line training sample data in a simulated unsupervized mode has brought out the efficacy of the technique. The technique can easily be implemented as a front end to established pattern classification systems with supervized learning capabilities to derive unified learning systems capable of operating in both supervized and unsupervized environments. This makes the technique an attractive proposition in the context of remotely sensed earth resources data analysis wherein it is essential to have such a unified learning system capability.

ISSN:0020-7721    

DOI:10.1080/00207727508941791

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Singular perturbation methods are used to provide a basis for the analysis of the asymptotic controllability of multivariable linear systems containing small ‘ parasitic ’ elements, and for the design of feedback controllers which will effect asymptotic eigenvalue assignment in such systems.

ISSN:0020-7721    

DOI:10.1080/00207727508941792

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

This paper discusses the importance of technological forecasting as a planning and decision making tool. The basic Delphi methodology is briefly described and its variations summarized. Outline of an experiment conducted with Delphi in a classroom environment is given and its results discussed.

ISSN:0020-7721    

DOI:10.1080/00207727508941793

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

The classical predator-prey model of Lotku, and Rescigno and Richardson are combined to derive a mathematical model for the case of two trophic levels. The simplest level involves only ordinary differential equations discussed by Lotka and Volterra. The more general level is hereditary equations where the whole history of process comes into play.

ISSN:0020-7721    

DOI:10.1080/00207727508941794

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Transport situation in a model city is interpreted as anN-person game and shown to possess a feature of the Prisoner's dilemma. The total transit time is larger. when each player selects optimal strategy without any restriction ; smaller, when penalties (tolls) are imposed on the non-cooperative strategies. The optimal structure of tolls for the presented model is calculated by the method of statistical mechanics.

ISSN:0020-7721    

DOI:10.1080/00207727508941795

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

Equilibrium points provide a method of solution to non-zero sum non-cooperative games. In this work, after initially considering solution concepts associated with such games, a variant of the method of fictitious play has been used for determining equilibrium points. This method is simple and easy to implement computationally. Two-player, three-player and higher order examples illustrate the effectiveness of the method. Stability of solution is achieved rather rapidly in most examples, except for a set of non-convergent examples reported by Shapley (1964). liven in these eases stabilization of the solution is sometimes possible by modifying the algorithm. Solutions to team games where team members do not coordinate their strategies but try to play the game on an individual basis are obtained by fictitious play and compared to the team equilibrium points.

ISSN:0020-7721    

DOI:10.1080/00207727508941796

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

This paper presents an approximate method to calculate the expected lost sales for a reorder level system of inventory control in which both the demand per unit time and the lead time are gamma distributed with integer modulus. Laplace transforms are used to determine the first four moments of the probability density function (p.d.f.) of demand over lead time. A gamma fit approximation of this p.d.f. is obtained and shown to be quite accurate for a large number of cases. This approximation allows the calculation of expected lost sales to be a simple task.

ISSN:0020-7721    

DOI:10.1080/00207727508941797

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor

摘要:

In this paper the modal control approach is employed to improve the transient response of a power system, by shifting the dominant eigenvalues of the uncontrolled system farther towards the left in the complex plane. Both complete as well as incomplete state variable feedback are considered. A sector criterion is used for the new locations of the eigenvalues. Comparison of the results obtained by modal control approach with the frequently used approach using optimal linear state regulator formulation is made.

ISSN:0020-7721    

DOI:10.1080/00207727508941798

出版商:Taylor & Francis Group    

年代:1975

数据来源: Taylor