基于LDA-FCM方法的Web服务发现聚类性能分析
    点此下载全文
引用本文:冉冉?覮,徐立波,曲睿婷,夏雨.基于LDA-FCM方法的Web服务发现聚类性能分析[J].计算技术与自动化,2020,(3):166-171
摘要点击次数: 274
全文下载次数: 0
作者单位
冉冉?覮,徐立波,曲睿婷,夏雨 (国网辽宁省电力有限公司 信息通信分公司辽宁 沈阳110006) 
中文摘要:为提高Web服务发现能力,需要进行Web数据的优化聚类处理,提出了基于LDA-FCM方法的Web服务发现聚类方法。利用LDA模型进行Web服务发现资源数据的重组和自适应调度,以提取Web服务发现的数据资源特征。依据数据特征确定其相似度,在FCM算法中,通过相似度计算隶属度,从而确定聚类中心,多次迭代后,实现Web服务发现聚类。实验结果表明,所提方法复杂度较低,具有较好的聚类精度,聚类执行时间较少,其查全率与查准率均较高。
中文关键词:LDA模型  Web服务  聚类  模糊C均值算法  隶属度  数据相似度  服务发现
 
Performance Analysis of Web Service Discovery clustering Based on LDA-FCM Method
Abstract:In order to improve the ability of Web service discovery,it is necessary to optimize the clustering of Web data,and a clustering method of Web service discovery based on LDA-FCM method is proposed. The LDA model is used for the reorganization and adaptive scheduling of Web service discovery resource data in order to extract the data resource characteristics of Web service discovery. According to the data characteristics,the similarity is determined. In the FCM algorithm,the membership degree is calculated by similarity,so as to determine the clustering center. After many iterations,the Web service discovery clustering is realized. The experimental results show that the proposed method has low complexity,good clustering accuracy and less clustering execution time. The recall rate and precision rate are high.
keywords:Latent Dirichlet Allocation model  Web service  clustering  fuzzy C-means algorithm  degree of membership  data similarity  service discovery
查看全文   查看/发表评论   下载pdf阅读器