一个新的多分类器组合模型

分类在数据挖掘中扮演着很重要的角色,然而单个分类器有很多缺点,包括适用范围十分有限和分类准确度不高等。把多个单分类器的分类结果融合起来是克服这些缺点的有效途径,因此存在很高的研究价值。组合多分类器的一个核心内容是融合规则,现存的融合规则有积规则、和规则、中值规则与投票规则等,但这些规则性能还不够稳定。提出了一个新的基于神经网络的融合规则,并依此建立一个新的多分类器组合模型,实验表明它能提高分类准确度和稳定性。

New model of combining multiple classifiers

Classification is a very important part in the domain of data mining,however,single classifiers have many defects,such as very finite applicability and low accuracy.Combining multiple classifiers can overcome the defects.The existent combination rule,which is the pivotal conception during the process of combination,including product rule,sum rule,median rule,voting rule and so on,but these are not steady enough.In this paper,the authors develop a new model of combining multiple classifiers based on nerve net,and it is proved that it can improve not only the accuracy of classification but also its applicability.