Modeling Research on Hospitalization Cost in Patients with Cerebral Infarction Based on BP Neural Network

Abstract:

Article Preview

To establish the model of hospitalization cost in patients with cerebral infarction based on neural network using artificial network mathematical model, and setting the appropriate parameters. LM, BR, OSS, SCG four algorithms were used respectively to model 3, 5,10,15, 20 neuron number in different hidden layers and comparisons between model fitting ability and its generalization ability were made. The model which involves a hidden layer, 8 input neurons, 15 neurons in output layer network is the optimal model by using OSS system.

Info:

Periodical:

Edited by:

Shaobo Zhong, Yimin Cheng and Xilong Qu

Pages:

944-948

DOI:

10.4028/www.scientific.net/AMM.50-51.944

Citation:

L. Zhou et al., "Modeling Research on Hospitalization Cost in Patients with Cerebral Infarction Based on BP Neural Network", Applied Mechanics and Materials, Vols. 50-51, pp. 944-948, 2011

Online since:

February 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.