基于径向基神经网络用于中医舌诊诊断的研究

Research of RBF Neural Networks Based on Clustering Analysis in TCM Inspection of Tongue Diagnosis

研究基于聚类分析的径向基神经网络用于中医舌诊诊断,构建一个中医舌诊智能诊断的神经网络模型。先对输入样本集进行数据归一化处理,采用K-means聚类算法对样本集进行聚类分析,得到聚类中心的位置和数量,再构建RBF神经网络进行学习、训练。以肝病病证诊断进行仿真。实验结果表明:该中医舌诊智能诊断模型具有诊断能力强、收敛速度快、泛化能力强等特点。因此,基于聚类分析的径向基神经网络用于中医舌诊诊断的研究是可行的、有效的。

Presents the RBF neural networks based on clustering analysis is applied in TCM inspection of tongue diagnosis, to construct a neural networks model of TCM inspection of tongue intelligent diagnosis. Put the input sample data set into normalization treatment. It uses K-means clustering algorithm to analyze the input sample data set and gains the clustering center＇s position and number and constructs the RBF networks to learn and train. It uses the hepatic disease symptom as simulation. The experimental result demonstrates that TCM inspection of the tongue diagnosis model has good diagnostic ability, fast convergence rate and good generalization ability. So the research of RBF neural networks based on clustering analysis in TCM inspection of tongue diagnosis is feasible and valid.