基于可变精度粗集模型的增量式归纳学习

Incremental learning based on Variable Precision Rough Set Model

知识获取是知识信息处理系统的关键问题之一,特别是计算机与网络技术的飞跃发展使得各个领域的信息量急剧增加,90年代以来,人们把目光转向了一个新的研究领域—知识发现(KnowledgeDiscovery),或数据库知识发现(Knowledge Discov-ery from Databases,KDD)。今天,基于Web的分布式知识发现更为KDD展示了广阔的应用前景。

Symbolic inductive learning methods such as induction of decision trees and rule induction methods are used in knowledge discovery from databases (KDD). However, most approaches cannot classify problems involving uncertain or imprecise information. In this paper, we discuss variable precision rough set model based approach to induce rules that aim at classification problems incrementally.