摘要
提出一种面向大规模数据的特征趋势推理算法。首先,采用Hash函数抽取大规模数据样本,使用Pam聚类算法和并行K-means聚类算法对大规模数据样本进行聚类,获取最佳聚类结果后,提取大规模数据聚类的动态特征;其次,采用基于特征趋势规则的推理算法,构建大规模数据特征的趋势规则推理模型,并通过累计趋势规则方法设计趋势规则算法,推理大规模数据特征趋势,解决了推理结果误差较大的问题。实验结果表明,该算法对大规模数据特征趋势推理的准确率均值为98.10%,推理速度增长率为50%,推理耗时最大均值仅为114.25s,能快速准确地完成数据特征趋势推理。
The author proposed a characteristic trend reasoning algorithm for large-scale data.Firstly,Hash function was used to extract large-scale data samples,Pam clustering algorithm and parallel K-means clustering algorithm were used to cluster large-scale data samples.After obtaining the best clustering results,the dynamic characteristics of large data clustering were extracted.Secondly,a reasoning algorithm based on characteristic trend rules was used to construct a trend rule reasoning model for large-scale data characteristics,and a trend rule algorithm was designed by the method of cumulative trend rule,which could infer the trends of large-scale data characteristics,and solved the problem of large errors of reasoning results.The experimental results show that the average accuracy of the proposed algorithm for large-scale data characteristic trend reasoning is 98.10%,the growth rate of reasoning speed is 50%,and the maximum average reasoning time-consuming is only114.25 s,which can quickly and accurately complete data characteristic trend reasoning.
作者
吴春琼
WU Chunqiong(School of Information Science and Engineering,Xiamen University,Xiamen 361005,Fujian Province,China;School of Business,Yango University,Fuzhou 350015,China)
出处
《吉林大学学报（理学版）》
CAS
北大核心
2020年第2期364-370,共7页
Journal of Jilin University:Science Edition
基金
福建省社会科学基金(批准号:FJ2016B157)
福建省社科A类科研项目(批准号:JA12499S).
关键词
大规模数据
特征
趋势
推理
动态特征
累计趋势规则
large-scale data
characteristics
trend
reasoning
dynamic characteristics
cumulative trend rule
