基于小波函数的模糊大脑情感学习分类器

将小波函数和模糊推理相结合，提出一种基于小波函数的模糊大脑情感学习分类器（WFBELC）。采用小波函数的时频局部化特性反应输入信号的突变信息，快速精确地逼近信号，并去除噪声；利用参数自学习规则更新WFBELC结构参数。将该分类器应用于3个公开数据集，并与BP算法模型、模糊小脑模型(FCMAC)和模糊大脑情感学习模型（FBEL）进行对比。仿真结果显示，分类器在3个数据集上的分类准确率平均值均为最高，其中，在Wine数据集上的准确率最大值达到100%，平均值为9756%，表明WFBELC对数据集的学习能力更强，能获得更好的分类效果。

A Fuzzy Brain Emotional Learning Classifier Based on Wavelet Function

Combining the wavelet function and fuzzy reasoning,a fuzzy brain emotional learning classifier (WFBELC) based on the wavelet function is proposed.It inputs the mutation information of the signal using the time frequency localized reactions of the wavelet function so that the brain emotional learning algorithm approaches the signal speedily and accurately and noise is removed,and uses parameter self learning rules to update parameters in the structure.The classifier is applied to three public datasets and compared with the BP algorithm model,the fuzzy cerebellum model (FCMAC),and the fuzzy brain emotional learning model (FBEL) respectively.The simulation results show that the average classification accuracy of the three datasets proposed in this paper is the highest,the maximum classification accuracy on the Wine dataset reaches 100%,and the average value is 97.56%,indicating that WFBELC has strong learning ability on the dataset and can obtain good classification effect.