【摘要】 提出了一种粗糙模糊神经网络分类器的模型。其过程为:利用粗糙集理论获取分类知识,根据训练样本建立决策表,进行决策表属性值离散化、属性约简和分类规则的提取;依据约简后决策表的属性、经模糊化处理的属性值及分类规则构造粗糙模糊神经网络分类器。该分类器可以有效地克服粗糙集规则匹配方法抗噪声能力和规则泛化能力差的缺点;同时可简化神经网络的结构,加快网络的训练速度。并详细介绍了该分类器用于汽车车牌字符识别的步骤和实验结果。更多还原

【Abstract】 A model of rough fuzzy neural network classifiers is proposed.The rough set theory is used to acquire the knowledge of classification,which includes decision table construction,attribute discretization,attribute reduction and rule abstract.The rough fuzzy neural network classifier is established according to the reduced attributes,the fuzzilized attribute values and the classification rules.The proposed classifier has better abilities of anti-disturbance and generalization and can simplify the structure of the neural network and speed up the training rate of the network.The steps of applying this classifier to recognition of the car’s plate characters and the results are described in detail.更多还原