Vol 50, No 3 (2016)

A possible approach to constructing models for managing innovation projects in production–economics systems of enterprises and providing them with information support is described. The conceptual foundations for constructing models for innovation projects are presented, as well as the technique of transition from conceptual modeling to managing such projects. The obtained model and the set of parameters for project evaluation may be unique and depend on the specific features of the project, the preferences of the decision maker, and the production-economics system in which the project is carried out.

This paper presents a software complex for the computer-aided modeling of a term system. The project is implemented as an expert system that consists of a research team, a terminological knowledge base, a developer interface (the Semograf information system), and a user interface (TSBuilder and TSReader). Computer-aided design of a term system was achieved using data-mining methods, namely, decision-making trees and a modification of Rosenblatt’s perceptron.

This paper considers macro factors that determine the level of information support of the science and production domain. The trends of progress in the most advanced areas of Russia’s informatics are analyzed. The methodology and model of information-support management in all the phases of the research–development–production (R–D–P) cycle are considered. It is shown that the development of a design solution based on this model makes it possible to reduce the time lag and provide essentially improved information support in all the phases of the R–D–P cycle. Several proposals are formulated about overcoming the inertial trends in the development of the national information system.

We investigate an algorithm to find a point of an affine subspace in the positive orthant such that it is the closest one to the original point with respect to the Kullback–Leibler distance. This problem is solved by means of the classical Darroch–Ratcliff algorithm (see [1]), while we use ideas of the information geometry founded by Chentsov (see [2]) and Csiszar (see [3]). The main theorem of the present work proves the convergence of that algorithm (the method of the proof is different from previous ones). The proposed algorithm can be applied, e.g., to find the maximum likelihood estimates in an exponential family (see the last section of the paper).