Alexander Dokukin

Learn More
A new regression method based on convex correcting procedures over sets of predictors is developed. In contrast to previously developed approach based on minimization of generalized error, the proposed one utilies correcting procedures of maximal correlation with the target value. In the proposed approach a concept of a set of predictors irreducible against(More)
The article is devoted to thorough study of a new regression method performance. The proposed method based on convex correcting procedures over sets of predictors is subject to modifications and tested in comparison with the acknowledged regression utility. The modifications touch both resource consumption and quality aspects of the method and tests are(More)
Methods for the analysis of medical data and the results of their application to the treatment of a number of socially important diseases in important medical areas (cardiology, neurology, surgery, and oncology) are considered. The precedent approach is investigated. Practical methods of discrete analysis of training data, logical and statistical methods(More)
Special regimes and special control techniques are proposed and investigated for controlled pump-and-fan drives with DC brushless synchronous motor. Specific is zero EMF of an exciter with zero speed. Investigation confirms suitability of proposed regimes and control. Results are implemented in two turbo-compressor drives, 6.3 MW, 3000 rpm each.
In this work the new pattern recognition method based on the unification of algebraic and statistical approaches is described. The main point of the method is the voting procedure upon the statistically weighted regularities, which are linear separators in two-dimensional projections of feature space. The report contains brief description of the theoretical(More)
The paper is devoted to the description of hybrid pattern recognition method developed by research groups from Russia, Armenia and Spain. The method is based upon logical correction over the set of conventional neural networks. Output matrices of neural networks are processed according to the potentiality principle which allows increasing of recognition(More)
The problem of choosing an ensemble of binary subproblems for multiclass recognition problems is considered in the algebraic and logical approaches. The connection of the first and second level algorithm correctness and the applicability of logical deduction in a multilevel scheme are studied. Two modifications of the ECOC method are proposed that allow one(More)
  • 1