摘要
研究多流形结构的复杂数据的聚类方法,在流形学的基础上提出种子生长模型。对一维和二维多流形结构数据的建模和分析,表明该模型能够有效地解决类似的混合子空间聚类问题。以工业测量中的实例为研究对象建立模型,实验结果达到工业测量的目的,验证该模型在实际应用中的可行性。
Studies the clustering method of multiple manifold structure complex data, and proposes the seeds growth model on the basis of the manifold learning. One-dimensional and two-dimensional multiple manifold structure data modeling and their analysis, shows that the model can effectively solve the similar mixed subspace clustering problem. Takes the living example in Industrial measurement as the object of the study for modeling, the result achieves the purpose of industrial measurement, and verifies the feasibility of the model in practical application.
关键词
多流形数据
种子生长模型
评判指标
子空间聚类
Multiple Manifold Data
Seeds Growth Model
Judge Standard
Subspace Clustering
