基于区分能力大小的启发式约简算法及其应用

提出了一种能处理噪音的有效约简算法，该算法基于粗集理论认为知识是区分事物的能力的观点，对知识进行量化，证明了量化的合理性，并以量化后的区分能力作为启发式信息，指导约简，提高了约简效率。另外，利用这种启发式信息，提出了一种解决噪音问题的方法。最后，将该算法应用到人机接口中，用于手关节自由度的约简，这对手势识别与合成是很有意义的工作。

Reduction Algorithm Based on Discernibility and Its Applications

Rough set is an important method in data mining, reduction is a core issue among rough set theory. However, there are two kinds problem in application of reduction: computation efficiency and processing data noises and default setting. Recently, many researchers have conducted on these problems, but haven't good approaches considering two problems at the same time. This paper proposes an efficient reduction algorithm, can properly process data noises. The algorithm based on an viewpoint that knowledge is an ability of classing thing, quantify knowledge and prove quantify reasonableness, quantified capacity differentiate as heuristic information guiding reduce computation have improved reducing efficiency. Additionally, using the heuristic information, this paper proposes a solving data noise problem method. As a practice case, this algorithm is applies in human computer interface, at the first time, rough set theory is applies in hand joint freedom degree reducing, this is a significant work toward hand gesture recognition and synthesis research.