基于同层节点集划分的模糊概念格并行构造算法  

PARALLEL CONSTRUCTION ALGORITHM FOR FUZZY CONCEPT LATTICE BASED ON PARTITIONING OF SAME-LAYER NODES SET

作　　者：孙佳[1] 柴玉梅[1] 

机构地区：[1]郑州大学信息工程学院,河南郑州450001

出　　处：《计算机应用与软件》2016年第7期261-265,286,共6页Computer Applications and Software

摘　　要：形式概念分析理论在诸多计算机领域得到广泛应用。模糊概念格的构造仍是其在应用过程中的一个主要问题。为提高模糊概念格的构造效率,对串行算法进行并行化改造,提出模糊概念格的并行构造算法。该算法对节点进行层次划分,给出了同层节点的定义,得出同层节点构造任务相互独立的重要性质,并引入映射函数简化搜索空间的遍历,提高搜索模糊概念格的效率,并行构造模糊概念格,达到了提高构造效率的目的。实验表明该算法在面对大规模的构造任务时,具有良好的性能。The theory of formal concept analysis( FCA) is extensively applied in various computer fields. Constructing fuzzy concept lattice is still a major issue in its application process. In order to improve the efficiency of fuzzy concept lattice construction,we presented a parallel construction algorithm for fuzzy concepts lattice by reforming the serial construction algorithm to the parallelised one. The proposed algorithm stratifies the nodes,by defining the concept of same-layer nodes,we derived the important nature of the same-layer nodes that their construction tasks are independent each other,and the introduction of mapping function simplifies the search space traversal,the efficiency of searching fuzzy concept lattice is thus improved. The parallel construction of fuzzy concept lattice achieves the goal of improving the construction efficiency. Experiments show that the algorithm has good performance when facing with the large scale construction tasks.

关 键 词：模糊概念格构造 模糊集 节点分层 并行算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]