Optimization of controlled damages on the recognition in the master education
Author(s): Bibyk M. V., Dovbysh A. S.
Affilation(s): Sumy State University, 2 Rymskogo-Korsakova St., 40007, Sumy, Ukraine
*Corresponding Author’s Address: [email protected]
Issue: Volume 4; Issue 1 (2017)
Dates:
Paper received: April 5, 2017
The final version of the paper received: May 6, 2017
Paper accepted online: May 10, 2017
Citation:
Bibyk M. V. Optimization of controlled damages on the recognition in the master education / M. V. Bibyk, A. S. Dovbysh // Journal of Engineering Sciences. — Sumy : Sumy State University, 2017. — Volume 4, Issue 1. — P. H1-H6.
DOI: 10.21272/jes.2017.4(1).h1
Research Area: Computer Engineering
Abstract: Information considered extreme learning algorithm is able to study decision support system as part of the automated control system combined heat and power unit with optimized control tolerance s recognition. Within the framework of information fusion algorithm optimization studies DSS ACS for signs of recognition expedient design based on categorical model, which is a reflection of sets involved in machine learning and generalization represents a directed graph, where edges are the respective operators transform sets. Algorithm extreme training information DSS is approaching iterative procedure CFE global maximum information to its limit value by optimizing the parameters of DSS. The dependence of the functional efficiency of machine learning DSS’s on the control tolerances on the recognition attributes is established. This value is not high enough CFE DSS training necessitates optimization of other parameters of the study, which affect its functional efficiency. Optimization of control tolerances on recognition features allowed to increase more than twice the value of the informational CFE machine learning DSS.
