Knowledge Acquisition In Information Systems With Multi-scale Decisions Based On Evidence Theory

Granular computing has unique advantages in data mining and knowledge discovery.Granular computing is a major research direction in the field of AI today.Rough set theory has played a significant role in the research process of granular computing.With the development of the times,rough set theory has achieved considerable results in fields such as data mining,pattern recognition,and artificial intelligence.Evidence theory is another important tool to deal with uncertainty.Rough set and evidence theory are closely related.Evidence theory can be used to analyze knowledge acquisition in information systems.This dissertation presents the knowledge acquisition in information systems with multi-scale decisions based on evidence theory.The main content is as follows:First of all,To solve the problem of knowledge acquisition in information systems with multi-scale decision,optimal scale selection in information systems with multi-scale decision from the perspective of Dempster-Shafer theory of evidence is proposed.The concept of information systems with multi-scale decision is introduced.The notion of scale selections in information systems with multi-scale decision is defined.It is shown that the collection of all scale selections forms a lattice structure.Belief and plausibility functions in the Dempster-Shafer theory of evidence are employed to characterize optimal scale selections in information systems with multi-scale decision.Secondly,the optimal scale selection problem of information systems with multi-scale decisions is studied by using granularity trees and cuts.The concepts of granularity trees and cuts are introduced.Each attribute and decision has a granularity tree,and each granularity tree has many different local cuts,which represent the scale selection methods under a specific attribute.A local cut of different attributes and decision forms a global cut,resulting in a mixed scale decision table.The concept of cuts selections based on granularity trees and cuts in information systems with multi-scale decisions is presented.It is shown that the collection of all cuts selections forms a lattice structure.A comparative study between optimal cuts and optimal scale selections is performed and an algorithm is designed to verify the effectiveness of the method.Finally,the optimal cuts selection problem of information systems with multi-scale decisions is discussed from the perspective of Dempster-Shafer theory of evidence.Belief and plausibility functions in the Dempster-Shafer theory of evidence are employed to characterize optimal cuts selections in information systems with multi-scale decision.