Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.347
Fuzzy relational classifier (FRC) is the recently proposed two-step nonlinear classifiers, which effectively integrates the formed clusters and the given classes. However, FRC can not copy with the influence ofÂ Â those irrelevant or redundant features. To effectively filter out those irrelevant features andÂ Â preserve the internal structure hidden in the given data, in this paper, a simultaneous clustering and feature selection framework called FCM_FS is introduced, which incorporates margin based feature selectionÂ Â criterion into the unsupervised fuzzy c-means(FCM) clustering. Based onÂ Â FCM_FSÂ Â and FRC framework, we introduce an enhanced FRC (EFRC). The experimental results on 8 real-life benchmark datasets show that: EFRC can consistently outperform FRC in classification performance.
FCM, Classification, Feature Selection, Enhanced Fuzzy Relational Classifier (EFRC)
Jing Song, Ming Yang, Gen-lin Ji, "FCM_FS: A Simultaneous Clustering and Feature Selection Model for Classification", Computer Science and Information Engineering, World Congress on, vol. 04, no. , pp. 250-255, 2009, doi:10.1109/CSIE.2009.347