【摘要】 传统的K-Modes算法采用简单匹配的方法来计算对象之间的距离,并没有充分考虑同一属性下的两个不同值之间的相似性。基于粗糙集中的上、下近似,提出了一种新的距离度量,并重新定义了类中心,对传统K-Modes算法进行了改进。与其他改进K-Modes算法进行了比较,实验结果表明,基于粗糙集的改进K-Modes算法有效地提高了聚类精度。更多还原

【Abstract】 Traditional K-Modes clustering algorithm uses a simple matching dissimilarity measure to compute the distance between two objects.However,the similarity between two values of the same attributes is not considered.A new distance measure based on upper and lower approximations in rough set theory was proposed,and a new description of cluster center was defined.Traditional K-Modes clustering algorithm was improved.By comparing with other improved K-Modes algorithms,experimental results illustrate that the improved K-Modes clustering algorithm based on rough sets increases the clustering accuracy.更多还原