arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1004.4718cs.DB
收藏

一种大规模事务数据库聚类的数据清洗方法

A Data Cleansing Method for Clustering Large-scale Transaction Databases

Woong-Kee Loh, Yang-Sae Moon, Jun-Gyu Kang

摘要:

在本文中,我们强调需要进行数据清洗时,聚类大规模的事务数据库,并提出了一种新的数据清洗方法,提高聚类质量和性能。我们通过一系列的实验来评估我们的数据清洗方法。结果,聚类质量和性能分别显著提高了165%和330%。

英文摘要:

In this paper, we emphasize the need for data cleansing when clustering large-scale transaction databases and propose a new data cleansing method that improves clustering quality and performance. We evaluate our data cleansing method through a series of experiments. As a result, the clustering quality and performance were significantly improved by up to 165% and 330%, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑