基于GA-BP神经网络的胎儿体重预测分析

胎儿体重是判断胎儿发育、保障孕产妇安全的重要指标，但是胎儿体重无法直接测得，只能根据孕妇体检数据进行预测.提出了一种基于遗传算法优化BP神经网络（GA-BPNN）的胎儿体重预测模型，首先采用回归模型和特征归一化预处理得到的历史体检数据建立孕妇连续体重变化模型，然后利用遗传算法（Genetic Algorithm，GA）优化BP神经网络的初始权值和阈值，建立胎儿体重预测模型.从我国东部某医院2016年孕产妇中随机抽取3000例样本数据，将本文的模型与基于传统BP神经网络（BPNN）的预测模型进行比较，实验结果表明，本文提出的GA-BPNN胎儿体重预测模型不仅加快了模型的收敛速度，而且将胎儿体重预测精度提高了14%.

Fetal Weight Prediction Analysis Based on GA-BP Neural Networks

Fetal weight is an important indicator of fetal development and maternal safety, but fetal weight cannot be measured directly and can only be predicted according to the examination data of pregnant women. This study proposes a model of fetal weight prediction based on the Genetic Algorithm to optimize BP Neural Network (GA-BPNN). First, the model of continuous weight change in pregnant women is established by using regression model and feature normalization preprocessing. Then, the genetic algorithm is used to optimize the initial weights and thresholds of BP neural network and establish a fetal weight prediction model. 3000 pregnant women data are randomly sampled from a hospital in the eastern part of China in 2016. The proposed model is compared with the prediction model based on the traditional BP neural network. The results show that the GA-BPNN fetal weight prediction model proposed in this paper not only accelerates the convergence of the model, but also improves the prediction accuracy of fetal weight by 14%.