A prediction model of occupational manganese exposure based on artificial neural network

Abstract

Application of two statistical models to reconstruct occupational exposure to manganese (Mn) is discussed. Air monitoring of 635 samples were analyzed by a back-propagation artificial neural network (back-propagation ANN) in comparison with a multiple linear regression (MLR). The stepwise MLR yielded significant results with five selected variables for predicting airborne manganese dioxide (MnO₂). However, a 6-12-1 back-propagation ANN was superior to the data from MLR. Statistical parameters and non-parametric paired tests indicated that back-propagation ANN represents the more useful and accurate tool. ANN was used to predict missing MnO₂ concentrations in the present study. The median of MnO₂ was 0.445 mg/m³ (IQR 0.131–1.342). The MnO₂ characteristics of time, distance, and exposure site were defined. Airborne MnO₂ for three previous periods (1978–1988, 1989–1998, and 1998–2007) were 1.228 mg/m³, 0.664 mg/m³, and 0.501 mg/m³, respectively. The medians were 0.350 mg/m³, 0.281mg/m³, and 0.190  mg/m³ at distances of 5, 10, and 25 m away from the site of exposure. Compared with levels encountered in other studies, mine concentrator sites were more seriously polluted, due to the practices of direct ore processing.

Keywords::

• Artificial neural network
• prediction model
• manganese

Acknowledgements

We would like to acknowledge the following people, who kindly give help for our research: Professor Nong Dongxiao, who offered many suggestions for the design of the research; Professor Glenn Bulmer, Professor Michael Aschner, and two anonymous reviewers for article proof reading.

This study was partly supported by the China Guangxi Commission of Science and Technology Grant #0640044 (Yan-Ning Li) and the Chinese Ministry of Science and Technology Grant #2006BAI06B02 (Yue-Ming Jiang).

Declaration of interest: The authors report no conflicts of interest. The authors alone are responsible for the content and writing of the paper.