Abstract: This paper presents an algorithm for discretization based on rough set and particle swarm optimization.It mainly inducts a modified PSO（MPSO） and improves the ability to break away from the local optimum.Simultaneously，the algorithm obtains a satisfactory discretization result.Authors do many tests for different data sets and the experimental results prove that the algorithm has better validity for discretization of continuous attributes.

摘要： 提出了一种结合粗糙集和粒子群的连续属性离散化算法，采用了MPSO算法的思想，提高了粒子群摆脱局部极值的能力，得到了较好的离散化效果。对不同的数据集进行了多次测试，结果表明该算法在对数据离散化时有较好的性能。