Attribute reduction based on background knowledge and its application in classification of astronomical spectra data

To improve the efficiency of the attribute reduction, we present an attribute reduction algorithm based on background knowledge and information entropy by making use of background knowledge from research fields. Under the condition of known background knowledge, the algorithm can not only greatly improve the efficiency of attribute reduction, but also avoid the defection of information entropy partial to attribute with much value. The experimental result verifies that the algorithm is effective. In the end, the algorithm produces better results when applied in the classification of the star spectra data.

一种新的处理模糊和不确定性的数学工具简介

粗糙集合理论是一种新的处理模糊和不确定性的数学工具，这种方法可能是人工智能的重要基础。本文，我们介绍了粗糙集合的基本概念，集合的近似相等和近似包含关系，以及粗糙集合理论的主要优点和一种精确性衡量方法。最后，介绍了目前粗糙集合理论的应用和主要的研究方向等。