Policies for knowledge refreshing in databases

Fang, Xiao

doi:10.1016/j.omega.2006.07.003

Policies for knowledge refreshing in databases

2009-02-01

5

PRE

AI

DOI：10.1016/j.omega.2006.07.003

原文链接

原文求助

摘要

En 中文

Knowledge discovery in databases (KDD) provides organizations necessary tools to sift through vast data stores to extract knowledge. This process supports and improves decision making in organizations. In this paper, we introduce and define the concept of knowledge refreshing, a critical step to ensure the quality and timeliness of knowledge discovered in a KDD process. This has been unfortunately overlooked by prior researchers. Specifically, we study knowledge refreshing from the perspective of when to refresh knowledge so that the total system cost over a time horizon is minimized. We propose a model for knowledge refreshing, and a dynamic programming methodology for developing optimal strategies. We demonstrate the effectiveness of the proposed methodology using data from a real world application. The proposed methodology provides decision makers guidance in running KDD effectively and efficiently. (C) 2006 Elsevier Ltd. All rights reserved.

Keyword:

decision support systems

dynamic programming

decision rnaking/process

artificial intelligence

Policies for knowledge refreshing in databases

摘要

AI总结

期刊

机构

引用论文