基于RBF神经网络的老年痴呆症智能诊断研究  

Study on Intelligent Diagnosis of Senile Dementia Based on RBF Neural Network

作　　者：张会敏[1] 叶明全[2] 罗永钱 孟婷玮 陈玥珠 

机构地区：[1]皖南医学院 [2]皖南医学院计算机教研室

出　　处：《中国数字医学》2015年第6期38-41,共4页China Digital Medicine

基　　金：国家级大学生创新训练项目(编号:201310368027);省级大学生创新训练项目(编号:AH201310368027;AH201410368072);安徽省高校省级自然科学研究重点项目(编号:KJ2014A266)~~

摘　　要：为验证单RBF神经网络更适用于老年痴呆症的预测诊断,通过仿真实验将单BP神经网络、单RBF神经网络、遗传算法优化BP神经网络及遗传算法优化RBF神经网络分别应用于老年痴呆症的预测诊断,建立这四种网络模型,并对四种网络模型的预测结果进行分析比较。仿真实验在Matlab软件平台上进行。结果表明:在老年痴呆症的预测诊断中,单RBF神经网络比单BP神经网络预测结果更好,建模时间更短。此外,单RBF神经网络与遗传算法优化的BP神经网络预测结果相同,但单RBF神经网络建模较为简单,预测结果更为稳定。而遗传算法对RBF神经网络优化作用不明显。因此,单RBF神经网络更适用于老年痴呆症的预测诊断,实际应用时可以此结论作为理论指导。In order to verify single RBF neural network is more suitable for the predictive diagnosis of senile dementia, through the simulation experiment, a single BP neural network, a single RBF neural network, a genetic algorithm to optimize BP neural network and a genetic algorithm to optimize RBF neural network are used to predict senile dementia, establishing of these four kinds of network model, then analyzing and comparing the forecasted results of these four kinds of network model. The simulation experiments were carried out on the platform of Matlab software, the results show that： in the predictive diagnosis of senile dementia, the single RBF neural network predictive results is higher than the single BP neural network, and the modeling time is shorter. Furthermore, the prediction results of the single IKBF neural network is as the same as the genetic algorithm to optimize BP neural network, but the single P, BF neural network model is relatively simple, and the prediction results are more stable. Therefore, diagnosis and prediction of the single RBF neural network is more suitable for senile dementia, and this conclusion can be used as a theoretical guide to the actual application.

关 键 词：遗传算法 BP神经网络 RBF神经网络 老年痴呆症预测 数据挖掘 

分 类 号：R741[医药卫生—神经病学与精神病学] TP391[医药卫生—临床医学]