云计算环境下非连续数据路径挖掘优化分析  

Optimization Analysis of Discontinuous Data Path Mining in Cloud Computing Environment

作　　者：谢辅雯[1] XIE Fu - wen(Jiangxi Normal University Science and Technology College, Ganzhou Jiangxi 341000, China)

机构地区：[1]赣南师范大学科技学院,江西赣州341000

出　　处：《计算机仿真》2018年第6期432-435,共4页Computer Simulation

基　　金：江西省教育厅科学技术研究项目(151574)

摘　　要：为提高非连续数据的利用率,需要对非连续数据路径进行挖掘。当前基于本体论的非连续数据路径挖掘方法,通过领域知识与数据库的无缝连接完成数据路径的挖掘,过程中重复数据的清洗效果较差,挖掘所用能耗较高,无法实现高质量的数据路径挖掘。提出依据模糊支持向量机,对非连续数据路径进行挖掘,通过统一标准格式,对数据排序的关键字中比较繁杂的表现形式,进行规格化地处理,将数据的格式进行统一;对排序关键字内的单词实施排序操作,增强非连续数据库内,数据排序结果单一性,以达到减少挖掘所用能耗的目的。通过候选的支持向量机减小数据训练数量,利用模糊隶属度法,对支持向量机建立模糊支持向量机起到的作用进行增强。采用POS法完成训练决策函数时获得的支持向量机集合的寻优操作,采并选出使挖掘误差为最小的向量子集对决策函数进行训练,以得到非连续数据路径挖掘最优结果。仿真表明,上述方法可对重复数据进行高效清洗,实现了高精度地数据路径挖掘,减少了数据挖掘所用能耗。In order to improve the utilization of discontinuous data, this article puts forward a method to mine discontinuous data path based on the fuzzy support vector machine. Through the uniform standard format, the more complex form in kcywords of data sorting was normalized, and then the format of data was unified. Moreover, words in sortkey were sorted to enhance the unity of data sorting result in discontinuous database, so as to reduce the energy consumption of mining. Through the candidate support vector machine, the number of data training was reduced. In addition, fuzzy membership method was used to enhance the role that support vector machine established fuzzy support vector machine. Meanwhile, POS method was used to complete the optimization operation of support vector machine set obtained when training decision function. Finally, the vector subset that made mining error minimum was selected to train decision function. Thus, optimal result of discontinuous data path mining was obtained. Simulation results prove that the proposed method can efficiently clean repeating data. Thus, the data path mining with high precision is achieved and the energy consumption of data mining is reduced.

关 键 词：云计算 非连续 数据路径 挖掘 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]