摘要
本文采用反向传播神经网络算法，根据孕妇身高、体重、宫高及腹围预测胎儿体重。建立了一个预测胎儿体重的网络模型，讨论了确定网络拓扑结构的方法。采用该方法预测了１４０例胎儿体重，预测符合率高达８５％，相对误差１０％者占预测总数的９４２８％。采用神经网络分析输入对于输出的贡献的结果表明孕妇宫高对于胎儿体重影响最大。
Artificial Neural Network (ANN) was applied to estimate fetal weight based on height, weight, height of uterine fundus and abdominal perimeter of pregnant women. An ANN model for estimating fetal weight was established, and method for determining topological structure of the model was discussed. Furthermore, by this ANN model, weights of 140 fetus were estimated. The result of the estimation was that the correspondence rate was as high as 85%, and the cases with relative error10% made up 94.28 of the estimated cases. The ANN analysis on the contribution of the input to the output showed that the height of uterine fundus had the largest effect on the fetal weight.
出处
《中国生物医学工程学报》
EI
CAS
CSCD
北大核心
1999年第2期155-158,193,共5页
Chinese Journal of Biomedical Engineering
关键词
胎儿体重
预测
神经网络
Fetal weight
Estimation
Artificial Neural Network
