A Data Cleansing Method for Clustering Large-Scale Transaction Databases

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

• （社）電子情報通信学会の論文
• 2010-11-01

著者

• Moon Yang-sae

  Department Of Computer Science Kangwon National University

• Loh Woong-kee

  Department Of Multimedia Sungkyul University

• KANG Jun-Gyu

  Department of Industrial & Management Engineering, Sungkyul University

• Kang Jun-gyu

  Department Of Industrial & Management Engineering Sungkyul University

関連論文

• Efficient Storage and Querying of Horizontal Tables Using a PIVOT Operation in Commercial Relational DBMSs
• Fourier Magnitude-Based Privacy-Preserving Clustering on Time-Series Data
• Hybrid Lower-Dimensional Transformation for Similar Sequence Matching
• Fast Normalization-Transformed Subsequence Matching in Time-Series Databases(Data Mining)
• A Data Cleansing Method for Clustering Large-Scale Transaction Databases
• Linear Detrending Subsequence Matching in Time-Series Databases
• A Fast Divide-and-Conquer Algorithm for Indexing Human Genome Sequences
• A Storage-Efficient Suffix Tree Construction Algorithm for Human Genome Sequences

スポンサーリンク