Using Incomplete Clustering Models for Big Data Analysis

The use of Big Data in the generation of solutions has become an important part of modern engineering and management processes. Big data is a collection of information that is too large or complex to be processed by traditional methods. This data can be structured or unstructured. Big data and Zwicky morphological analysis are powerful tools for generating and analyzing engineering solutions (ES). Also, the use of two approaches makes it possible to adapt the analysis process to the dynamic and complex conditions of modern technologies. Incomplete clustering is proposed, in which only a part of the solutions is grouped into clusters. In the context of synthesizing and analyzing multiple ES, incomplete clustering helps manage uncertainty and variety of possible solutions without forcing each solution to be tied to a specific group. Incomplete clustering is useful for dividing multiple engineering solutions into groups based on key characteristics. Also, the proposed approach, taking into account incomplete information, helps to more accurately account for risks and reduce the likelihood of making bad decisions.