Systems and Means of Informatics

2020, Volume 30, Issue 4, pp 4-13


  • M. P. Krivenko


When developing statistical methods for data analysis in relation to the problems of observation classification in the field of diagnostic medicine, sociology, word processing, and image recognition, it is necessary to conduct studies of the viability of the data models used, to experiment with data and algorithms for their processing. To do this, one has to turn to the capabilities of computer technology and create the appropriate software. The article discusses the experience of developing a version of software aimed at solving data classification problems. The composition of the modules is given, which ensures the construction and use of probabilistic data models, the estimation of their parameters, and the study of the effectiveness of the proposed decision-making procedures. It also provides examples of solving specific applied problems and briefly describes the software elements used. The conditions and possible ways of further development of the structure, composition, and content of statistical analysis procedures are characterized.

[+] References (2)

[+] About this article