粗糙集模糊神经网络味觉信号识别系统

针对C-means聚类算法和减法聚类算法的不足,提出了一种模糊神经网络味觉信号识别系统模型,该模型利用粗糙集的离散化算法和规则提取算法获得数量较少的分类规则,将这些分类规则转化为模糊IF-THEN规则,进而通过这些模糊IF-THEN规则确定网络结构.网络输出采用投票机制,使用粒子群优化方法精炼网络参数,与常用的提取模糊if-then规则的算法相比,该方法只有一个参数且易于实现.实验结果表明:该方法可获得更简洁的系统表示,并且通过选择合适的系统参数可使系统对加噪声训练样本的错误识别率降低5%左右.

Rough-set-based fuzzy-neural-network system for taste signal identification

Comparing with general methods to acquire fuzzy if-then rules,such as C-means and the subtractive clustering algorithm, a fuzzy neural network model for identifying 11 kinds of mineral waters by its taste signals is proposed.In the model,a classification rule extracting algorithm based on discretization methods in rough sets is developed to extract fewer but robust classification rules,which are ease to be translated to fuzzy if-then rules to construct a fuzzy neural network system.This method is easy to implement and it requires only one parameter.Finally,the voting mechanism is used to decide the network output and the particle swarm optimization is adopted to refine the network parameters.Experimental results show that the system can acquire more compact representation,and by choosing the system parameter properly,the misclassification rates for the training samples polluted by the noise can be improved about 5%.