PCA和相融性度量在聚类算法中的应用

提出一种基于主分量分析和相融性度量的快速聚类方法。通过构造主分量空间将高维数据投影到两个主成分上进行特征提取,每一个主分量都是原始变量的线性组合,主分量之间互为正交关系,在剔除冗余信息的同时,实现高维数据降维,得到二维坐标,以此作为聚类分析的输入;提出相融性度量的定义,用相融性度量描述一个样本与训练集相融合的程度,设计一种基于相融性度量的分类器。以该方法为基础设计的光谱自动分类系统可实现快速、准确地分类。

Application of PCA and Coherence Measure in Clustering Algorithm

An efficient and quick method based on 2-D Principal Component Analysis (PCA) and coherence measure is introduced. The coordinates are achieved by projecting the high dimensional data to the 2-D space after the principle component space is built and feature extraction is finished at one time. Every principle component is the linear combination of the original variables and is irrelevant to each other. A novel coherence measure is introduced and designed for effectively measuring the coherence of a new specimen of unknown type with the training samples. The spectrum can be classified quickly and exactly by the classifier.