欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
多关系分类是数据挖掘领域中的研究和应用热点。已有多关系朴素贝叶斯分类算法将所有与目标表相连的表都考虑在内,包括语义关系很弱的表。为此,本文提出一种新的分类算法—Graph-NB。它通过对表进行剪裁,达到优化语义关系图,从而一定程度上消除无关表对分类影响的目的。该算法实现了深度优先与广度优先两种遍历策略。实验结果表明,语义关系图的优化可以提高分类准确度和运行效率,相比于其他算法,该算法运行时间短,分类准确度高。
同期刊论文项目
同项目期刊论文
Effectiveness of the International 3G Standardisation Process and Implications for China’s 3G Policy
Optimal Solution Structure for Multi-period Production Planning with Returned Products Remanufacturi
Single-Period Multi-Product Assemble-to-Order Systems with Common Components and Uncertain Demand Pa
What Lead to the Post-Implementation Success of the ERP? An Empirical Study of the Chinese Retail In
Properties and Pre-Processing Strategies to Enhance the Discovery of Functional Dependencies with De
An e-commerce performance assessment model: Its development and an initial test on e-commerce applic
Do IT Managers Learn How to Control Spending on New Information Technology? A Study of IT Budget Gro
位置：