An Improved Variable Precision Rough Sets Weighting Model for Healthy Housing

Abstract

Classical rough sets method makes knowledge absence in the key domain and affects the comprehensiveness of the index system after simplification, so an improved variable precision rough sets weighting model is proposed on the basis of variable precision rough sets theory. In the model, attributes are divided into first-class core attributes and second-class attributes, and core attributes are still calculated by the importance of the attributes in rough sets theory. The importance of second-class attribute is μ times of the core attributes’ minimum importance degree. Then normalize the importance degrees and convert them to weights. In the evaluation of the health of sound living environment, the model we proposed has lower error rates compared to other methods and the evaluation results demonstrate to be valid.