为了解决传统分类方法对不平衡数据集中少数类的识别率较低的问题,提出一种基于模糊c-均值与核Fisher判别分析相结合的分类方法.该方法首先采用模糊c-均值算法对样本数据进行聚类,将聚类后的样本数据映射到特征空间中,再对映射后的样本数据采用核Fisher判别分析算法对数据进行分类.在UCI上选取8个不平衡数据进行仿真实验,就分类性能上与其他5种算法作了比较和分析.实验结果表明采用模糊c-均值与核Fisher判别相结合的方法可以获得较高的识别率,能有效地处理不平衡数据集的分类. In order to solve the problem that the traditional classification method has a low recognition rate for minority numbers in unbalanced datasets, a classification method based on fuzzy c-means and kernel Fisher discriminant analysis is proposed.This method first uses fuzzy c-means algorithm to sample Data are clustered, the clustered sample data is mapped into the feature space, and then the data is classified by using the kernel Fisher discriminant analysis algorithm on the mapped sample data.On the UCI, 8 unbalanced data are selected for simulation experiment, The classification performance is compared with the other five algorithms.Experimental results show that the combination of fuzzy c-means and kernel Fisher discriminant can obtain a higher recognition rate and can effectively deal with the classification of unbalanced data sets.