谱聚类熵值排列通过求n 个二次规划问题，就可以求得相似度矩阵W，降低了谱聚类算法对参数的敏感性，使算法更稳定(Clustering Entropy Ranking By finding n quadratic programming problems, we can obtain the similarity matrix W, which reduces the sensitivity of the spectral clustering algorithm to the parameters