[1]武建辉)△,薛玲),郭正军),等.基于径向基函数神经网络的组合模型在煤工尘肺发病工龄预测中的应用*[J].郑州大学学报(医学版),2014,(06):818.
 WU Jianhui,XUE Ling,GUO Zhengjun,et al.Application of combination model in forecasting work year of coal workers′ pneumoconiosis based on radical basis function neural network[J].JOURNAL OF ZHENGZHOU UNIVERSITY(MEDICAL SCIENCES),2014,(06):818.
点击复制

基于径向基函数神经网络的组合模型在煤工尘肺发病工龄预测中的应用*
分享到:

《郑州大学学报(医学版)》[ISSN:1671-6825/CN:41-1340/R]

卷:
期数:
2014年06期
页码:
818
栏目:
应用研究
出版日期:
2014-11-20

文章信息/Info

Title:
Application of combination model in forecasting work year of coal workers′ pneumoconiosis based on radical basis function neural network
作者:
武建辉1)△薛玲2)郭正军1)尹素凤1)王国立1)
1)河北省煤矿卫生与安全实验室;河北联合大学公共卫生学院流行病与卫生统计学学科 唐山 0630002)河北联合大学公共卫生学院儿少卫生与妇幼保健学学科 唐山 063000
Author(s):
WU Jianhui1)XUE Ling2)GUO Zhengjun1)YIN Sufeng1)WANG Guoli1)
1)Hebei Province Key Laboratory of Occupational Health and Safety for Coal Industry; Division of Epidemiology and Health Statistics, School of Public Health, Hebei United University, Tangshan 0630002)Division of Maternal, Child and Adolescent Health, School of Public Health, Hebei United University, Tangshan 063000
关键词:
径向基函数神经网络多重线性回归模型组合模型煤工尘肺发病工龄
Keywords:
radical basis function neural network multiple linear regression model combined model coal workers' pneumoconiosis onset length of service
分类号:
R181.3
摘要:
目的:研究径向基函数(RBF)神经网络与多重线性回归的组合模型在煤工尘肺发病工龄预测中的性能优劣。方法:采用RBF神经网络模型与多重线性回归模型对研究数据进行分析,对2模型进行加权拟合,采用均方根误差、均方误差、平均相对误差对模型的预测性能进行评价。结果:多重线性回归模型、RBF神经网络模型和组合模型真实值与预测值比较,差异均无统计学意义(t配对=1.552、0.231、0.155,P均>0.05)。多重线性回归模型、RBF神经网络模型和组合模型的均方根误差分别为(1.63±0.11)、(2.45±0.19)和(0.59±0.07)(F=26.141,P<0.001),均方误差分别为(2.656 9±0.241 2)、(5.986 7±0.380 4)和(0.348 3±0.065 3)(F=49.678,P<0.001),平均相对误差分别为(7.15±0.82)%、(15.39±1.25)%和(3.68±0.59)%(F=35.282,P<0.001)。结论:在煤工尘肺发病工龄的预测中,组合模型预测性能优于单一模型。
Abstract:
Aim: To study the pros and cons of prediction performance of multiple linear regression model and radical basis function neural network combined model to forecast the work year of coal workers′ pneumoconiosis.Methods: Root of mean square error, mean square predict error, and mean percent error were applied to analyze the predicting outcomes of the three models in order to achieve the aim of comparing the prediction performance. Results: For multiple linear regression model,radical basis function neural network and the combination model, the difference between true and predicted values were significant(tpaired=1.552,0.231, and 0.155, P>0.05).The root of mean square error of the multiple linear regression model,radical basis function neural network and the combination model was respectively (1.63±0.11),(2.45±0.19),and (0.59±0.07)(F=26.141,P<0.001). The mean square predict error was respectively (2.656 9±0.241 2),(5.986 7±0.380 4),and(0.348 3±0.065 3)(F=49.678,P<0.001). The mean percent error was respectively (7.15±0.82)%,(15.39±1.25)%,and (3.68±0.59)%(F=35.282,P<0.001).Conclusion: In the prediction of coal workers′ pneumoconiosis incidence seniority, combined forecasting model is superior to a single model.

参考文献/References:

[1]李翠兰,钱庆增,沈福海,等.某煤矿掘砌工人肺通气功能分析[J].环境与职业医学,2012,29(6):371 [2]刘红波,杨永利,段志文,等.基于神经网络模型预测未来煤工尘肺发病危险性的研究[J].中国卫生统计,2009,26(6):617 [3]王晓红,武建辉,郭正军,等.基于BP神经网络的煤工尘肺发病工龄预测组合模型的研究[J].中国煤炭工业医学杂志,2013,16(2):263 [4]Lee WL, Choi BS. Reliability and validity of soft copy images based on flatpanel detector in pneumoconiosis classification[J].Acad Radiol, 2013, 20(6):746 [5]Mukhopadhyay S,Gujral M,Abraham JL,et al.A case of hut lung: scanning electron microscopy with energy dispersive xray spectroscopy analysis of a domestically acquired form of pneumoconiosis[J].Chest,2013,144(1):323 [6]王丹,张敏,郑迎东.中国煤工尘肺发病水平的估算[J].中华劳动卫生职业病杂志,2013,31(1):24 [7]张国良,后永春,舒文,等.三种模型在肺结核发病预测中的应用[J].中国卫生统计,2013,30(4):480 [8]张辉,柴毅.一种改进的RBF神经网络参数优化方法[J].计算机工程与应用,2012,48(20):146 [9]Rabe F. A logical framework combining model and proof theory[J].Mathemat Struct Comput Sci, 2013, 23(5):945 [10]陈银苹,吴爱萍,余亮科.组合模型对乙肝发病趋势的预测研究[J].解放军医学杂志,2014,39(1):52

备注/Memo

备注/Memo:
*河北省科技支撑项目11276911D;河北省卫生厅医学重点项目20120146;唐山市科技支撑项目11150205A3;△男,1981年12月生,硕士,讲师,研究方向:疾病监测、数据挖掘,Email:wujianhui555@163.com
更新日期/Last Update: 2014-11-26