INFORMATION-EXTREME ALGORITHM FOR SYSTEM DIAGNOSTICS EMOTIONAL AND MENTAL PERSON’S STATE LEARNING
Науковий журнал «Радіоелектроніка, інформатика, управління»
Переглянути архів Інформація| Поле | Співвідношення | |
| ##plugins.schemas.marc.fields.042.name## |
dc |
|
| ##plugins.schemas.marc.fields.245.name## |
INFORMATION-EXTREME ALGORITHM FOR SYSTEM DIAGNOSTICS EMOTIONAL AND MENTAL PERSON’S STATE LEARNING |
|
| ##plugins.schemas.marc.fields.720.name## |
Dovbysh, A. S.; Sumy State University, Ukraine Shelehov, І. V.; Sumy State University, Ukraine Prylepa, D. V.; Sumy State University, Ukraine |
|
| ##plugins.schemas.marc.fields.653.name## |
information-extreme intelligent technology, computer diagnostic system, psychodiagnostics, learning, the criterion of the functional efficiency. |
|
| ##plugins.schemas.marc.fields.520.name## |
<p>A method of the emotional and mental person’s state recognition using facial image is considered. The fragments with eye and nose areas of the image are prompted for additional information obtaining. A forming of the input mathematical description of pattern recognition system by analyzing the left hemisphere and right hemisphere images of the human face is proposed. The preliminary process of forming training matrix by image brightness for a stable emotional and mental person’s state uses the whole images as well as corresponding fragments. Machine learning in the framework of information-extreme intellectual technologies is based on maximizing the information capacity of the recognition system. A criterion for the functional efficiency of machine learning uses a modified information measure Kullback as a functional of the accuracy characteristics of the two alternative solutions. An information-extreme algorithm for optimization geometrical parameters of recovering in radial basis of the feature space during the learning process hyperspherical<br />containers of recognition classes is developed by the categorical model of mapping involved in the learning process sets. Physical modeling results proved that the fragments of facial image are quite informative for the emotional and mental person’s state recognition.</p> |
|
| ##plugins.schemas.marc.fields.260.name## |
Zaporizhzhya National Technical University 2015-01-27 10:16:30 |
|
| ##plugins.schemas.marc.fields.856.name## |
application/pdf http://ric.zntu.edu.ua/article/view/37174 |
|
| ##plugins.schemas.marc.fields.786.name## |
Radio Electronics, Computer Science, Control; No 2 (2014): Radio Electronics, Computer Science, Control |
|
| ##plugins.schemas.marc.fields.546.name## |
uk |
|
| ##plugins.schemas.marc.fields.540.name## |
Copyright (c) 2015 A. S. Dovbysh, І. V. Shelehov, D. V. Prylepa |
|