Title :
A New Model of Estimating Fetal Macrosomia Based on Neural Network
Author :
Zhipeng, Xu ; Aifang, Shen
Author_Institution :
Sch. of Phys. Sci. & Inf. Eng., Liaocheng Univ., Liaocheng, China
Abstract :
Fetal macrosomia not only produces a great risk in delivery both to the mother and the fetus, but also has a bad influence to the future of the child. Prediction of fetal macrosomia has an important clinical meaning. In this paper, a new model of estimating fetal macrosomia is proposed. The aim of the model is to predict the fetal macrosomia, not the fetal weight. An artificial neural network is established to estimate the fetal macrosomia, the original data are trained and tested with the Bayesian Regularization method. The model gets an accuracy of 75% with estimating fetal macrosomia.
Keywords :
medical computing; neural nets; Bayesian regularization method; artificial neural network; fetal macrosomia; fetus; mother; neural network; Artificial neural networks; Equations; Fetus; Mathematical model; Neurons; Pediatrics; Training; Bayesian Regularization; artificial neural network; fetal macrosomia;
Conference_Titel :
Distributed Computing and Applications to Business Engineering and Science (DCABES), 2010 Ninth International Symposium on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7539-1
DOI :
10.1109/DCABES.2010.142
