基于自适应权值的多分类器融合方法

Adaptive Weighting Based Fusion Method of Multi-Classifiers

提出了一种类似于聚类分析的融合方法 ,它通过分析样本在特征空间的分布 ,来估计分类器分类结果的可靠性 ,并根据各个样本的具体情况自适应地为各分类器赋予权值 ,从数据融合的层次上来说 ,这是一种介于特征级和决策级的融合方法 .

Combining information from multiple classifiers can improve the performance of pattern recognition systems. However, the traditional methods always assign fixed weights to the classifiers according to their classification performances without considering the sample itself. A clusterirng analogy fusion method is proposed in this paper, which estimates the reliability of each classifier by analyzing the distribution of samples, and adaptively assigns weights to classifiers based on the reliability estimation. This method can be seen as a method lying between feature level and decision level.