自动化与信息工程
自動化與信息工程
자동화여신식공정
AUTOMATION & INFORMATION ENGINEERING
2013年
2期
6-9,32
,共5页
谱聚类%奇异解%特征向量%聚类个数
譜聚類%奇異解%特徵嚮量%聚類箇數
보취류%기이해%특정향량%취류개수
Spectral Clustering%Singular Solution%Eigenvector%Number of Clusters
对谱聚类的奇异解进行了研究。在谱聚类中,由对象相似度的定义,两种属性完全不同或截然相反的对象的类,其类内对象的相似度、类间对象的相似度和与其它类对象的相似度,会出现接近或相同的情况,从而有可能被聚为一类。研究发现,大多数情况下,出现谱聚类的奇异解的主要原因是聚类个数设置不合理和高斯核参数σ估计不准确。本文给出了利用特征值差值分析与特征值累积贡献率来确定聚类个数和估计高斯核参数σ的方法。实验表明,所给聚类个数选择和高斯核参数σ估计的方法有效,可以消除谱聚类结果中存在的奇异解。
對譜聚類的奇異解進行瞭研究。在譜聚類中,由對象相似度的定義,兩種屬性完全不同或截然相反的對象的類,其類內對象的相似度、類間對象的相似度和與其它類對象的相似度,會齣現接近或相同的情況,從而有可能被聚為一類。研究髮現,大多數情況下,齣現譜聚類的奇異解的主要原因是聚類箇數設置不閤理和高斯覈參數σ估計不準確。本文給齣瞭利用特徵值差值分析與特徵值纍積貢獻率來確定聚類箇數和估計高斯覈參數σ的方法。實驗錶明,所給聚類箇數選擇和高斯覈參數σ估計的方法有效,可以消除譜聚類結果中存在的奇異解。
대보취류적기이해진행료연구。재보취류중,유대상상사도적정의,량충속성완전불동혹절연상반적대상적류,기류내대상적상사도、류간대상적상사도화여기타류대상적상사도,회출현접근혹상동적정황,종이유가능피취위일류。연구발현,대다수정황하,출현보취류적기이해적주요원인시취류개수설치불합리화고사핵삼수σ고계불준학。본문급출료이용특정치차치분석여특정치루적공헌솔래학정취류개수화고계고사핵삼수σ적방법。실험표명,소급취류개수선택화고사핵삼수σ고계적방법유효,가이소제보취류결과중존재적기이해。
In spectral clustering, according to the definition of object similarity, two classes of objects whose properties are completely different or opposite, may be clustered into one class. It is because that the similarity of these objects within class, between different classes and with other classes, can be very close to each other. The study found that in most cases, the main reason of the emergence of singular solutions is the number of clusters is set unreasonable and the Gaussian kernel parameterσdoes not estimate accurately. The method given in this paper is trying to determine the number of clusters and estimate the Gaussian kernel parameterσ, using the difference between two consecutive eigenvalues and the cumulative contribution rate of the eigenvalues of the scaled adjacency matrix of spectral clustering algorithm. Experiments show that this method is effective, which the number of spectral clustering choice and Gaussian kernel parameterσestimated, it can eliminate the singularity exists in the spectral clustering.