Paper Bagging ensemble based on fuzzy c-means

Based on fuzzy clustering, a new ensemble method of Bagging F-Bagging is proposed in this paper. Firstly the training data are clustered using fuzzy clustering, and then according to the matrix, dividing the training samples into subset intersect, at last each subset of the data are trained, and proper weighted method is used to base learners. As each subset contains different categories and different training data, thus the members of the classifier are diverse. The number of subsets determines the number of the base learners. Experimental results show that this approach can achieve good results.