Classification by fuzzy decision trees inducted based on Cumulative Mutual Information
Jan Rabčan, Patrik Rusnak, С. А. Субботин · 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET) · 2018
One of the important tasks of decision support systems is a recognition (classification) of new instances based on previous knowledge. Nowadays exists many methods and approaches for the classification. One of the often used classification methods in practical application is based on Decision Trees (DT) or Fuzzy Decision Trees (FDT). The induction of DT and FDT in different applied areas is a relevant problem in Data Mining. In this paper, an algorithm for the FDT induction based on Cumulative Mutual Information Estimate is considered. This algorithm is used and evaluated by the defect detection of blades of gas turbine aircraft engines.