人工神经网络在失去土地农民心理健康调查中的应用  

The application of artificial neural network in studying landless farmer＇s mental health problems

作　　者：张训保[1] 黄水平[1] 卓朗[1] 吴秀娟[1] 孙桂香[1] 赵华硕[1] 李磊[1] 

机构地区：[1]徐州医学院公共卫生学系,221002

出　　处：《中华流行病学杂志》2008年第10期1038-1041,共4页Chinese Journal of Epidemiology

基　　金：江苏省科技厅社会科学基金课题（BS2005018）

摘　　要：介绍人工神经网络（ANN），结合实例比较与logistic回归在解决分类问题的优缺点。以1070名失去土地农民心理健康调查资料为例建立ANN模型与logistic回归模型，比较两种模型的优劣。测试集样本BP神经网络预测精度为94．299％，logistic回归预测精度为51．028％，BP神经网络具有良好的泛化能力。结论：当传统统计分析条件不能得到满足或效果不佳时ANN能够达到良好的预测结果，在医学领域具有较好的应用前景。To introduce a method of classification with high precision - the artificial neural network （ANN）, and to compare the results using logistic regression method. Using data from 1070 landless peasants＇ mental health survey, the artificial neural network models and logistic regression model were built and compared on their advantages and disadvantages of the two models. The prediction accuracy for artificial neural network was 94. 229 % and for logistic regression it was 51. 028 %. ANN appeared to have had good ability on generalization. ANN displayed advantages when conditions of classical statistical techniques could not be met or the predictive effect appeared to be unsatisfactory. Hence, ANN would make a better facture of its application in medical researehe.

关 键 词：人工神经网络 LOGISTIC回归 失去土地农民 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]