基于FP-growth算法的高维混合属性数据挖掘方法 |
点此下载全文 |
引用本文:梁树杰.基于FP-growth算法的高维混合属性数据挖掘方法[J].计算技术与自动化,2024,(2):88-92 |
摘要点击次数: 109 |
全文下载次数: 0 |
|
|
中文摘要:常规高维混合属性数据挖掘方法多采用云平台技术,无法完整保留数据的结构相似性,使得数据挖掘效率较低。为此,提出了基于FP-growth算法的高维混合属性数据挖掘方法。为了改善数据质量,根据高维混合属性数据在数据库中的存储结构,采用了一种固定算法实现数据去噪,并依据数据类型计算分类型和数值型相似度,结合FP-growth算法对频繁项样本分支进行筛选生成项表头,保证数据结构相似性的完整性,通过搜索项表头输出有效关联规则,实现数据挖掘过程。实验结果表明,所提方法具有较高的挖掘效率。 |
中文关键词:数据挖掘 FP-growth算法 固定算法 高维混合属性 |
|
A High Dimensional Mixed Attribute Data Mining Method Based on FP-growth Algorithm |
|
|
Abstract:Conventional high-dimensional mixed attribute data mining methods mostly use cloud platform technology, which can not completely preserve the structural similarity of data, making the efficiency of data mining low. For this reason, a high dimensional mixed attribute data mining method based on FP-growth algorithm is proposed. In order to improve the data quality, according to the storage structure of high-dimensional mixed attribute data in the database, a fixed algorithm is adopted to de-noise the data, and the classification and numerical similarity are calculated according to the data type, and the FP-growth algorithm is combined to filter the frequent item sample branches to generate the item header to ensure the integrity of the data structure similarity, and the data mining process is realized by outputting effective association rules from the search item header. Experimental results show that the proposed method has high mining efficiency. |
keywords:data mining FP-growth algorithm fixed algorithm high-dimensional mixed attributes |
查看全文 查看/发表评论 下载pdf阅读器 |