摘要
目的:探讨矽肺纤维化同生物活性介质之间的关系。方法:利用Delphi语言编制了BP人工神经网络模型计算机程序,建立并分析了矽肺胶原纤维预测的数学模型。结果:选定网络隐含层节点为9,初始权值阈值约为(-0.2,0.2),最大相对误差为4%,最小相对误差为0.2%。结论:应用神经网络具有较好的预测效果,可为临床医学研究提供一个很好的研究思路。
Objective： To study the relation of pulmonary fibrosis and bioactivity mediums. Method： To apply BP neutral network based on Delphi computer language to construct and analyze math model of pulmonary fibrosis prediction. Result： Max relative error and rain relative error are respective 4 percent and 0. 2 percent when the number of network hidden nodes is 9 and threshold of initial weight is between --0. 2 and 0. 2. Conclusion. The result shows that there is a better prediction result and the method can provide a better research direction for the clinical medicine.
出处
《数理医药学杂志》
2009年第1期19-23,共5页
Journal of Mathematical Medicine
基金
全军"十五"基金课题(NA086)
关键词
BP神经网络
生物活性介质
矽肺
胶原纤维
预测
BP neutral network
bioactivity mediums
pulmonary fibrosis
collagen fibre
prediction
