Abstract | ||
---|---|---|
This paper proposes a new clustering method that combines the k Near Neighbor (k NN) method and the local Principal Component Analysis (PCA) to consider the global and local information of data points for clustering. Specifically, we propose firstly preserving the local information of samples using the k NN method to obtain a neighborhood subset and a covariance matrix for each data point, and then preserving the global information of the data by conducting the local PCA on each covariance matrix to obtain a binary affinity matrix of the data. Furthermore, our method conducts clustering on the resulting affinity matrix without the assignment of clustering number. Experimental analysis on 8 UCI benchmark datasets showed that our proposed method outperformed the state-of-the-art clustering methods in terms of clustering performance. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/s11042-018-6488-1 | Multimedia Tools Appl. |
Keywords | Field | DocType |
k nearest neighbor, Local PCA, Spectral clustering | Data point,k-nearest neighbors algorithm,Spectral clustering,Pattern recognition,Computer science,Global information,Artificial intelligence,Covariance matrix,Cluster analysis,Principal component analysis,Binary number | Journal |
Volume | Issue | ISSN |
77 | 22 | 1380-7501 |
Citations | PageRank | References |
0 | 0.34 | 34 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Wu | 1 | 3 | 1.39 |
Xiaofeng Zhu | 2 | 1960 | 81.85 |
Tao Tong | 3 | 0 | 0.68 |