一种基于加权核Fisher准则的朴素贝叶斯分类器

Naive Bayesian Classifier Based on the Weight Kernel Fisher Discriminant Analysis

利用加权核Fisher准则,给出一种朴素贝叶斯分类器的改进算法。该算法通过寻找使类与类最大分离的最优投影矩阵,将样本数据进行投影变换,再利用朴素贝叶斯分类器对新样本进行分类。将该方法应用于双酚A生产过程在线监测数据集的分类中,仿真结果表明,相比于单纯朴素贝叶斯分类器,该分类算法具有更好的分类性能。

Based on the weight kernel fisher discriminant analysis,an improved algorithm of the naive Bayesian classifier is proposed.This algorithm is the key to search the optimal projection matrix of the maximum separation between classes,and then the original samples are projected to obtain new samples.These new samples are classified by the naive Bayesian classifier.An on-line monitoring data set from an industrial Bisphenol-A （BPA） device is classified by the proposed method.Simulation results show that the improved classifier has better performances of classification compared with the naive Bayesian classifier.