Home > Table of Contents


Proceedings of 2009 International Symposium on Computer Science and Computational Technology (ISCSCT 2009)

Huangshan, China, December 26-28, 2009

Editors: Fei Yu, Guangxue Yue, Jian Shu, Yun Liu

AP Catalog Number: AP-PROC-CS-09CN005

ISBN: 978-952-5726-07-7 (Print), 978-952-5726-08-4 (CD-ROM)

Page(s): 335-338

Null Values Estimation Method Based on Predictions in Incomplete Information Systems

Yanji Jiang, Ze Jiang, and Fenggang Huang

Full text: PDF


Collaborative filtering rating mechanism to valuation method is introduced into this paper for the shortcoming of method in improved SIM-EM (Original-EM), it proposes an improved estimation method of a null value from the perspective of the prediction of similar objects. By calculating the sparse degree of rough sets can choose suitable estimation methods. According to the degree of similarity between objects, we can predict and fill the null value when the sparsity within a specified threshold. The improved algorithm is proposed in this paper to deal with sparse data on the extreme situation can get an excellent result, and the accuracy is better than the original method.

Index Terms

rough set theory; incomplete information system; null value; prediction

Copyright @ 2009 ACADEMY PUBLISHER All rights reserved