CAJ | 학술논문

近年来非负矩阵分解被广泛用于肿瘤基因表达数据聚类分析，本文总结了目前已有的非负矩阵分解方法。由于相关熵是对处理噪声和噪点具有很好的稳定性的一种相似性度量方法，本文将最大相关熵非负矩阵分解方法用在5个标准肿瘤基因表达数据集聚类上，取得了较好的聚类效果。最后，总结了目前用于评价非负矩阵分解基因表达数据聚类效果的方法。
근년래비부구진분해피엄범용우종류기인표체수거취류분석，본문총결료목전이유적비부구진분해방법。유우상관적시대처리조성화조점구유흔호적은정성적일충상사성도량방법，본문장최대상관적비부구진분해방법용재5개표준종류기인표체수거집취류상，취득료교호적취류효과。최후，총결료목전용우평개비부구진분해기인표체수거취류효과적방법。
Non-negative matrix factorization (NMF) has been shown to be a powerful tool for clustering gene expression data, which are widely used to classify cancers. We summarized several methods of NMF and similarity between the product of the two matrices and the original matrix. Correntropy was recently shown to be an effective similarity measurement due to its stability to outliers or noise. So we introduce a maximum correntropy criterion (MCC)-based NMF method (NMF-MCC). Extensive experiments on five cancer benchmark sets demonstrate that the introduced method is significantly more accurate than the state-of-the-art methods in cancer clustering. At last, we introduced several performance metrics of clustering.