Forecasting Incidence Age of Coal Workers’ Pneumoconiosis Based on BP Neural Networks

  • Xiaohong Wang
  • Jianhui Wu
  • Sufeng Yin
  • Guoli Wang
  • Zhengjun Guo
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 223)


Retrospective analysis of the data of hospitalized coal worker patients suffering from pneumoconiosis in the Tangshan money home since 2005. Using these data which provide seniority of exposure to dust, time of exposure to dust, age and the dust class as the influence factors of length of service, which build the model of the BP neural network, and forecast the length of service of coal worker’s pneumoconiosis. Making use of SPSS statistical software package, using matching t test comparison before and after the length of service of the forecast, prediction the D-value of the length of service before and after is 0.095 ± 2.399, t = 1.225, P = 0.221. The importance of each variable distribution result shows that the importance of the biggest is seniority of exposure in dust to forecast coal worker’s pneumoconiosis (0.632), followed is the dust class (0.247), time of exposure in dust (0.061), and age (0.060). BP neural network model has high forecasting accuracy to forecast the length of service of coal worker’s pneumoconiosis.


Coal workers’ pneumoconiosis BP neural network Incidence seniority Prediction 



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


  1. 1.
    Tian L-j, Liu H-b, Yang Y-l et al (2009) Prediction on the morbidity tendency of coal worker’s pneumoconiosis in a certain coal mine. Chinese J Ind Med 22(2):127–128Google Scholar
  2. 2.
    Li B-p (1995) The progress for the research of the popular trend forecast method of Pneumoconiosis. J Occup Health Damage 04:51Google Scholar
  3. 3.
    Simon HDM, Magne B, Yohana M 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 Pub Health 7:17–24Google Scholar
  4. 4.
    Erkinjuntti T, Lee DH, Gao FQ et al (1993) Temporal lobe at rophy on magnetic resonance imaging in the diagnosis of early Alzheimer s disease. Arch Neurol 50:305–310CrossRefGoogle Scholar
  5. 5.
    Wang W (ed) (1995) The principle of artificial neural network-introduction and application. Chapter four More class neural network and error back propagation algorithm, vol 1, Beijing University of Aeronautics and Astronautics Press, Beijing, pp 52–76Google Scholar
  6. 6.
    Wang X-j (2002) Research and application on prediction method based on gray theory and neural network. Master Degree Thesis of South-central University for nationalities 1:675–683Google Scholar
  7. 7.
    Jiao L-c (1993) Neural network system theory, vol 1, Xidian University Publishing House, Xi’an, pp 56–67Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Xiaohong Wang
    • 1
  • Jianhui Wu
    • 2
  • Sufeng Yin
    • 2
  • Guoli Wang
    • 2
  • Zhengjun Guo
    • 2
  1. 1.Tangshan Centers for Disease Control and PreventionTangshanChina
  2. 2.Hebei United UniversityTang ShanChina

Personalised recommendations