Based attribute reduction

The objective of the thesis: Proposes filter-wrapper algorithms for fuzzy rough set based attribute reduction in decision tables to reduce the cardinality of reduct and increase significantly the classification accuracy.

28p extraenglish 24-05-2021 12 3   Download

The first is the hybrid filterwrapper algorithm proposal for finding the reduction set of the decision table using advanced fuzzy distance measurements and other measurements basing on fuzzy rough set to minimize2 the number of attributes of reduction set. Reduce and improve the accuracy of the classification model.

26p capheviahe27 23-02-2021 32 4   Download

. Attribute reduction is one of the most important issues in rough set theory. There have been many scientific papers that suppose algorithms on attribute reduction. However, these algorithms are all heuristic which find the best attribute reduction based on a kind of heuristic information. In this paper, we present a new algorithm for finding all attribute reductions of a decision and we show that the time complexity of the algorithm is exponential in the number of attributes. We also show that this complexity is polynomial in many special cases.

7p binhminhmuatrenngondoithonggio 09-06-2017 60 2   Download