Noise-Resistant Unsupervised Feature Selection via Multi-perspective Correlations
作者： Hao Huang , Shinjae Yoo , Dantong Yu , Hong Qin
DOI: 10.1109/ICDM.2014.88
关键词: Feature selection 、 Pattern recognition 、 Noise (video) 、 Noise measurement 、 Cluster analysis 、 Correlation 、 Feature (computer vision) 、 Artificial intelligence 、 Multi perspective 、 Mathematics 、 Matrix decomposition 、 Data mining
摘要: Unsupervised feature selection is an important issue for high dimensional dataset analysis. However popular methods are susceptible to noisy instances (observations) or features. We propose a noise-resistant algorithm by capturing multi-perspective correlations. Our proposed approach, called Noise-Resistant Feature Selection (NRFS), based on correlation that reflects the importance of with respect representative and various global trends from spectral decomposition. In this way, model concisely captures wide variety local patterns. Experimental results demonstrate effectiveness our algorithm.
osti.gov
bnl.gov 
sci-hub.se 参考文章(42)
Hanqing Lu, Xiaofang Zhou, Jing Liu, Zechao Li, Yi Yang, Unsupervised feature selection using nonnegative spectral analysis national conference on artificial intelligence. ,vol. 2, pp. 1026- 1032 ,(2012)
Ron Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection international joint conference on artificial intelligence. ,vol. 2, pp. 1137- 1143 ,(1995)
Xizhao Wang, Yadong Wang, Lijuan Wang, Improving fuzzy c -means clustering based on feature-weight learning Pattern Recognition Letters. ,vol. 25, pp. 1123- 1132 ,(2004) , 10.1016/J.PATREC.2004.03.008
J. A. Hartigan, M. A. Wong, A K-Means Clustering Algorithm Journal of The Royal Statistical Society Series C-applied Statistics. ,vol. 28, pp. 100- 108 ,(1979) , 10.2307/2346830
Xiaofeng Zhu, Zi Huang, Yang Yang, Heng Tao Shen, Changsheng Xu, Jiebo Luo, Self-taught dimensionality reduction on the high-dimensional small-sized data Pattern Recognition. ,vol. 46, pp. 215- 229 ,(2013) , 10.1016/J.PATCOG.2012.07.018
Hao Huang, Hong Qin, Shinjae Yoo, Dantong Yu, A New Anomaly Detection Algorithm Based on Quantum Mechanics 2012 IEEE 12th International Conference on Data Mining. pp. 900- 905 ,(2012) , 10.1109/ICDM.2012.127
Yuanhong Li, Ming Dong, Jing Hua, Localized feature selection for clustering Pattern Recognition Letters. ,vol. 29, pp. 10- 18 ,(2008) , 10.1016/J.PATREC.2007.08.012
Robert J Tibshirani, Bradley Efron, An introduction to the bootstrap ,(1993)
Zhigang Ma, Heng Tao Shen, Xiaofang Zhou, Zi Huang, Yi Yang, l 2,1 -norm regularized discriminative feature selection for unsupervised learning international joint conference on artificial intelligence. pp. 1589- 1594 ,(2011) , 10.5591/978-1-57735-516-8/IJCAI11-267
Wen-Liang Hung, Miin-Shen Yang, De-Hua Chen, Bootstrapping approach to feature-weight selection in fuzzy c-means algorithms with an application in color image segmentation Pattern Recognition Letters. ,vol. 29, pp. 1317- 1325 ,(2008) , 10.1016/J.PATREC.2008.02.003