Informatica

The analysis of the method for multiple criteria optimization problems applying a computer network has been presented in the paper. The essence of the proposed method is the distribution of the concrete optimization problem into the network rather than the parallelization of some optimization method. The aim of the authors is to design and investigate the interactive strategies to solve complex multiple criteria problems by applying a computer network. The optimized objective function is the weight sum of the criteria. The multiple criteria problem is iterated by selecting interactively different weight coefficients of the criteria. Therefore, the process is organized by designating the computers as the master (that coordinates the process of other computers) and the slaves (that execute different tasks). In the beginning of the process the researcher allocates a certain number of optimization problems to the network. The objective function optimization problems differ only in weight coefficients of the criteria. As soon as the task of a slave has been executed, the result is sent to the master. Every computer of the network behaves in analogous way. Whenever the researcher receives an immediate result from one of the computers, he gives a decision taking into consideration the latter and all the previous results, i.e., he selects new weight coefficients for the criteria and assigns a new task to the network. Likewise the multiple criteria problem is solved until the result is acceptable for the researcher. The application of the proposed method is illustrated on the basis of the problem for the selection of the optimal nutritive value. Message Passing Interface (MPI) software has been used. The trials have been carried out with the network of computers under the operation system Windows NT.

The problem of parameter clustering on the basis of their correlation matrix is considered. The convergence in probability of parameter clustering based on the simulated annealing is investigated theoretically.

The aim of investigation was to seek new ways for the analysis of extremal problems. A method of visual analysis of a set of objective function values is proposed. It allows us to find a direction where the variation of function is maximal. The method ensures a high quality of analysis when the number of used values of the objective function is small, and a possibility of identifying a specific character of the objective function. The results of analysis are used in search of a new coordinate system of the extremal problem and in a graphical representation of the observed data. The analysis will lead us to a better optimization strategy.

The problem is to discover knowledge in the correlation matrix of parameters (variables) about their groups. Results that deal with deterministic approaches of parameter clustering on the basis of their correlation matrix are reviewed and extended. The conclusions on both theoretical and experimental investigations of various deterministic strategies in solving the problem of extremal parameter grouping are presented. The possibility of finding the optimal number of clusters is considered. The transformation of a general clustering problem into the clustering on the sphere and the relation between clustering of parameters on the basis of their correlation matrix and clustering of vectors (objects, cases) of an n-dimensional unit sphere are analysed.

We consider a possibility of automating the analysis of a computer program realizing the objective function of an extremal problem, and of distributing the calculation of the function value into parallel processes on the basis of results of the analysis. The first problem is to recognize the constituent parts of the function. The next one is to determine their computing times. The third problem is to distribute the calculation of these parts among independent processes. A special language similar to PASCAL has been used to describe the objective function. A new scheduling algorithm, seeking to minimize the maximal finishing time of processing units, was proposed and investigated. Experiments are performed using a computer network.

A multiextremal problem on the synthesis of external circuit of a tunable subnanosecond pulse TRAPATT-generator was investigated using algorithms of local optimization and cluster analysis.

A multiple criteria decision support system has been developed and implemented on the personal computer. Three interactive methods of increasing complexity are realized. The main applications of the system were in the scope of decisions on the best energy development strategy for Lithuania.

The model of the HIV/AIDS infection spread is proposed and investigated. The paper deals with some specific features of the disease spread at the initial stage, i.e., when the infection extent is small enough. We propose a model characterizing any risk group by three differential equations. These equations describe the dynamics of active susceptible, active infected, and passive infected individuals. The evaluation of parameters from demographical and medical data is discussed. The package for the investigation of infection is presented, and possibilities to control the infection are shown. Two general directions of control may be distinguished: the HIV/AIDS blood tests and the publicity and availability of protective means. The investigations showed under what conditions the HIV/AIDS infection may be stopped.

The paper deals with the minimization algorithms which enable us to economize the computing time during the coordinated calculation of the values of an objective function on the nodes of a rectangular lattice by storing and using quantities that are common for several nodes. The algorithm of a uniform search with clustering, the variable metric algorithm and the polytope algorithm are modified.

In this paper we deal with the problem of extremal parameter grouping. The problem formulation, the algorithms of parameter grouping and the fields of implementation are presented. The deterministic algorithms of extremal parameter grouping often find the local maximum of the functional, characterizing the quality of a partition. The problem has been formulated as a problem of combinatorial optimization and attempted to be solved using the simulated annealing strategy. The algorithms, realizing such a strategy and devoted to the solving of the problem concerned, are proposed and investigated.