Feature Selection and Weighting Method Based on Similarity Rough Set for CBR

摘要: Case-based Reasoning systems retrieving cases is an n-ary task. Most researches resolve this problem with a similarity function based on KNN rules or some derivatives. But the result of method sensitive to those irrelevant noisy features. Standard rough set has been used in feature reduct and selection various domains. indispensable discreti- zation ruins objectivity usually post appro- ximation weighting costs lots computing capacity. This paper proposes theory. It avoids discretizing continuous attributes keeps quality datasets. Based indiscernibility relation, reducts weighs at same time. easy realize can generate accurate results.