Forecasting Incidence Seniority of Coal Workers’ Pneumoconiosis Based on BP Neural Network

  • Jianhui Wu
  • Xiaohong Wang
  • Xinlei Guo
  • Guoli Wang
  • Yu Su
  • Lei Zhou
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 226)

Abstract

Applying the value of BP neural network model is discussed in the occupational prediction in order to provide evidence for pneumoconiosis prevention of dust operators. The data of patients who have been diagnosed as coal workers’ pneumoconiosis were collected, and then the selected cases samples were randomly divided into three parts by the ratio of 3:1:1 to establish the BP neural network model, the fitting results of test and the forecast accuracy of the model, respectively. There was no significant difference between the model predictions and true value (P = 0.785 > 0.05), and the coefficient of determination between the true value and predictive value of validation sample and stimulation sample were 0.875 and 0.859, respectively. The predicted relative error of validation sample and stimulation sample was 12.8 % and 14.8 %, respectively, both less than 20 %. The model is good to be used in analysis that predicts incidence seniority of the health of coal workers, and the predictions were reliable and were worth to be widely applied.

Keywords

Coal workers’ pneumoconiosis Incidence seniority BP neural network Prediction 

Notes

Acknowledgments

This work is supported by Hebei Science and Technology Funds (11276911D) and program of Tangshan Science and Technology Research and Development (11150205A-3).

References

  1. 1.
    Xin G, Wang T (2005) China’s current of incidence and countermeasures. China Coal 31(2):62MathSciNetGoogle Scholar
  2. 2.
    Tian J, Liu H, Yang Y et al (2009) Prediction of a coal mine workers pneumoconiosis trend. Chin J Ind Med 22(2):127–128Google Scholar
  3. 3.
    Chen Y, Min F, Yuan J et al (2009) Incidence investigation of coal worker’s pneumoconiosis in a coal mine. Chin J Public Health 25(5):623–624Google Scholar
  4. 4.
    Zhang F, Yuan J, Han X (1998) Comparison of prevalence trend prediction methods of coal workers’ pneumoconiosis. Chin J Ind Med 1(3):267–268Google Scholar
  5. 5.
    Ru DJ (2008) The application of BP neural network in disease prediction. J Pharm Pharmacol 21(3):259–260Google Scholar
  6. 6.
    Zhu D, Shi H (2006) Principle of artificial neural network and its application, vol 33. Beijing Publishing House, Beijing, pp 12–14Google Scholar
  7. 7.
    Mamuya SHD, Bratveit M, Mashalla Y et al (2007) High prevalence of respiratory symptoms among workers in the development section of a manually operated coal mine in a developing country. A cross sectional study. BMC Public Health 7:17–24Google Scholar
  8. 8.
    Liu H, Duan Z, Sun G et al (2009) Risk research of coal workers’ pneumoconiosis based on artificial neural network. Chin J Public Health 26(6):617–619MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Jianhui Wu
    • 1
  • Xiaohong Wang
    • 2
  • Xinlei Guo
    • 1
  • Guoli Wang
    • 1
  • Yu Su
    • 1
  • Lei Zhou
    • 1
  1. 1.Department of Epidemiology and Health Statistics School of Public HealthHebei United UniversityTangshanChina
  2. 2.Tangshan Centers for Disease Control and PreventionTangshanChina

Personalised recommendations