Integrating Automatic Clustering and Weighted Grey Relational Technique for Missing Value Processing in Large Databases

• Main Authors: yung-sheng shen, 沈永勝
• Other Authors: chien-chiau yang
• Format: Others
• Language: zh-TW
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/63303151320310174256

碩士 === 國立臺灣科技大學 === 電子工程系 === 93 === Data mining has became a very popular research area recently. It is a process of extracting desirable knowledge from huge database, and offering enterprises the consultation while making policies. The quality of data analysis results will be affected if there exist missing values in the database, so how to deal carefully with the missing value problem is a quite important topic. So far, while dealing with classificatory data of missing value, the method of convention had been to ignore the missing value data. But this is usually not a wise move. In this paper, we continue with the advantage of using grey relational analysis to deal with missing value problem proposed in the past. We propose a new approach to handle missing values. The proposed approach integrates the automatic clustering algorithm and weighted grey relational analysis, then we can compute suitable values for the part of missing value. We hope to fulfill the needs of data preprocessing in KDD(Knowledge Discovery in Database) by this method, and improve the correctness of the follow-up use. We also implement this method and use some of large databases to justify the feasibility of the method we proposed.