基于SVM的老年痴呆症智能诊断研究

A Study on Intelligent Diagnosis of Senile Dementia Based on SVM

为了验证支持向量机(SVM)更适用于基于血常规数据的老年痴呆症的预测诊断,通过仿真实验,将BP神经网络、RBF神经网络、SVM支持向量机分别应用于老年痴呆症的预测诊断,建立3种算法对应的诊断模型,并对3种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,与BP、RBF神经网络方法相比,SVM模型预测准确度高,建模时间短,整体性能好,更适用于基于血常规数据的老年痴呆症预测诊断,实际应用时可以此结论作为理论指导.

In order to verify that the support vector machine（SVM）is more suitable for predicting diagnosis based on thedata of blood routine examination of Alzheimer＇s disease,through the simulation experiment,BP neural network,RBFneural network,SVM support vector machine（SVM）are applied to predict the diagnosis of Alzheimer＇s disease. Threediagnostic models are established,and the prediction results of the three models are analyzed and compared. The simula-tion experiments are carried out on the platform of Matlab software,the results show that compared with BP,RBF neuralnetwork method,SVM model with high predictive accuracy,short modeling time,good overall performance is more suit-able for prediction diagnosis based on the data of blood routine examination of Alzheimer＇s disease. This conclusion canbe used as a theoretical guide in the practical application.