An attribute reduction algorithm in a decision based on improved entropy

Nguyễn Long Giang, Vũ Đức Thi

Abstract


In rough set theory, many attribute reduction algorithms based on information entropy have been proposed. Although this algorithms reduce the time complexity, they do not obtain the minimal reduction in inconsistent decision tables. In this paper, we propose an improved entropy and we prove that the attribute reduction based on this entropy is equivalent to Pawlak's reduction in inconsistent decision tables. As a result, a complete heuristic algorithm was designed to find the attribute reduction based on improved entropy and its time complexity is O(|C|2 |U|), where |C| is the number of condition attributes, and |U| is the number of objects.


Full Text: PDF

Refbacks

  • There are currently no refbacks.


Journal of Computer Science and Cybernetics ISSN: 1813-9663

Published by Vietnam Academy of Science and Technology