×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • Text fragment meaning search model

    The object of research is the consideration and analysis of such a field as information retrieval. Given the rapid growth in the number of electronic documents, the tasks of their clustering, classification and ordering become very relevant. The work also indicates the need for creating formal methods for the semantics of texts and their processing. In addition, a software product was created that implements such a functional of semantic analysis as context and contextual bundle. The scientific novelty is to teach the machine to disclose the physical meaning in the documentation of a technical nature, to optimize the search for the necessary data

    Keywords: semantics, contextual connective, reverse polish notation, clustering, context

  • Software for multivariate analysis of variance

    The object of research in this article has become a rather important topic of describing such a statistical method as analysis of variance. The fact is that many software products consider, basically, a case when the number of factors is not more than two. With the exception of such a powerful product as a SPSS Statistica. The same can be attributed to scientific works, where the method of analysis of variance with a large number of factors is very rarely considered and described (often, when it comes to multifactorial analysis of variance, two factors are also considered). Therefore, an analysis was made of the existing mathematical apparatus, a proprietary idea was proposed for the implementation of this statistical method, and was created a software product to demonstrate how its work.

    Keywords: variance analysis, general case, software implementation

  • Software for multifactor regression analysis in violation of the assumption of the normal law distribution of observations

    This article discusses the use of regression analysis in violation of the assumption of the normal distribution of observations. The analysis of the following work illustrated that the theoretical distribution of observations may differ significantly from practical research if normal law is rejected. To solve this problem, which is one of the central ones in statistical analysis, stable estimation methods were studied and applied. Based on the results obtained, a software product was developed that implements this statistical method.

    Keywords: Normal law distribution of observations, stable estimation methods, M-estimates, software implementation