| 摘要: |
| 针对稀疏子空间聚类和最小二乘回归子空间聚类求得的表示系数存在类内过于稀疏和类间过于稠密的问题，利用A2范数，提出一种基于欧氏距离的且具有组效应的加权低秩子空间聚类算法，该算法通过基于欧氏距离的加权方式，使得最终的表示系数在保证同一子空间数据点联系的同时，减小不同子空间数据点之间的联系.利用该表示系数建立相似矩阵J，将J应用到谱聚类得到聚类结果.实验结果表明，与当前流行的算法比较，该算法取得了较好的聚类效果. |
| 关键词: 低秩 子空间聚类 组效应 A2范数 加权方式 谱聚类 |
| DOI：10.13328/j.cnki.jos.005235 |
| 分类号: |
| 基金项目:国家自然科学基金（61373055，61672265）；江苏省教育厅科技成果产业化推进项目（JH10-28） |
|
| Weighted Low Rank Subspace Clustering Based on A2 Norm |
|
FU Wen-Jin, WU Xiao-Jun
|
|
School of Internet of things Engineering, Jiangnan University, Wuxi 214122, China
|
| Abstract: |
| In order to solve the problem of over-sparsity for within-class coefficients and over-density for between-class coefficients in SSC and LSR, this paper proposes a new subspace clustering based on Euclidean distance using A2 norm. Using the weighted method based on Euclidean distance, the coefficient representation obtained by this algorithm maintains the connections of the data points from the same subspace. Meanwhile, the algorithm can eliminate the connections between clusters. The clusters can be produced by using the spectral clustering with the similarity matrix which is constructed by this coefficient representation. The results of experiments indicate the presented method improves the accuracy of clustering. |
| Key words: low rank subspace clustering grouping effect A2 norm weighted method spectral clustering |
