The concept and method of determining the relation between data using relational equations with multi-operations composition

Abstract

Discovering knowledge from data has become one of the most critical problems in computer science in the last decades. Many methods and solutions to this issue have been created. It is not only the collection and analysis of data that is becoming an indispensable part of our lives but also the continuous process of improving detection methods for discovering knowledge from data. In the presented work, we modify the study of the relationship between attributes and specific ones, which are fuzzy relational equations. E. Sanchez, one of the pioneers of work on fuzzy relational equations, started research on using this method to study the relationship between input and output data, indicating it as a tool for analysing medical data. Since the 1970s, these equations have been studied with different types of compositions. The author of this work deals with this subject, examining the assumptions regarding the operations that can be used in max - relations’ composition in fuzzy relation equations A o x = b to have the solution set. In this work, we use a new way of compositing relations. It enables the use of various types of decision-attribute dependencies. We note that various dependencies may exist between individual data attributes and the decision. Undoubtedly, it is another stage of work on relational equations and provides new opportunities to discover the relationships between input and output data.