基于SFLA和FCM的Web搜索结果聚类  

Web search results clustering method based on SFLA and FCM

作　　者：许方[1] 张桂珠[1] 

机构地区：[1]江南大学物联网工程学院,江苏无锡214122

出　　处：《计算机工程与应用》2013年第14期109-112,116,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60665001);江南大学自主科研计划(No.JUSRP30909)

摘　　要：针对模糊聚类算法中存在的对初始值敏感、易陷入局部最优等问题,提出了一种融合改进的混合蛙跳算法(SFLA)的模糊C均值算法(FCM)用于Web搜索结果的聚类。新算法中,使用SFLA的优化过程代替FCM的基于梯度下降的迭代过程。改进的SFLA通过混沌搜索优化初始解,变异操作生成新个体,并设计了一种新的搜索策略,有效地提高了算法寻优能力。实验结果表明,该算法提高了模糊聚类算法的搜索能力和聚类精度,在全局寻优能力方面具有优势。The traditional fuzzy clustering algorithm is sensitive to initial point and easy to fall into local optimum. In order to overcome these flaws, a novel Web search results clustering method based on Fuzzy C-Mean algorithm which combines the modi- fied Shuffled Frog Leaping Algorithm （SFLA） is presented. The new method uses SFLA to replace the iteration process of FCM based on the gradient descent. In this SFLA, a chaotic local search is introduced to improve the quality of the initial individual. In addition, mutation operating is joined to generate new individual. Simultaneously, a new searching strategy is presented to in- crease the optimization ability. The experimental results show the proposed method improves the search capability and the clus- tering performance of fuzzy clustering algorithm, and it has the advantages in the global search ability.

关 键 词：Web搜索结果聚类 混合蛙跳算法 模糊C均值 搜索策略 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]