摘要
大型云存储数据库中分布海量的非连续层次数据,该类数据具有较强的自耦合非线性特征,采用传统方法进行数据挖掘时,存在挖掘难度大的问题.为此,提出一种基于云计算的非连续层次数据挖掘算法.进行数据挖掘模型的总体分析,对非连续层次数据进行语义指向性特征提取和量化编码,在量化编码的基础上,采用模糊C均值聚类算法,完成语义本体特征指向性波束聚类,实现数据挖掘算法改进.实验结果表明,非连续层次数据挖掘改进算法,精度较高,性能较好,抗干扰能力较强,性能指标优于传统方法.
A large database of cloud storage has massive discontinuous level data, and the data has stronger coupling nonlinear characteristics. When using traditional method for data mining, mining difficult problems exist. Discontinuous hierarchical data mining algorithm based on cloud computing is put forward. Carrying on the overall analysis of the data mining model, semantic directivity character- istics of discontinuous level data are extracted and quantization coding is conducted, on the basis of quantitative coding, fuzzy C-means clustering algorithm is adopted, to complete semantic ontology di- rectional beam cluster, improving the data mining algorithm. The experiment results showed that the improved algorithm has high precision, good performance and strong anti-jamming capability, and its performance is superior to that of traditional methods.
出处
《西安工程大学学报》
CAS
2016年第4期498-503,共6页
Journal of Xi’an Polytechnic University
基金
广东省高职教育教学管理委员会教改课题(JGW2013026)
关键词
云计算
语义
数据挖掘
数据聚类
信息检索
cloud computing
semantic
data mining
data clustering
information retrieval
