Input Data Balancing in a Neural Network PM-10 Forecasting System
Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.
Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1314469Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 601
 Hee-Yong Kwon, S.H. Yu, Y.S. Koo, and E.Y. Ha, ‘PM-10 Forecasting using Neural Networks Model’, CIMCA'2008 Proc., pp.60~60, 2008
 https://nepis.epa.gov/Exe/ZyPURL.cgi?Dockey=2000F0ZT.TXT, Sep, 2017.
 Ian G. McKendry: ‘Evaluation of Artificial Neural Networks for Fine Particulate Pollution (PM10 and PM2.5) Forecasting’, Journal. of Air & Waste Management Association, Sep, 2002.
 T. S. Dye, D. S. Miller, C. B. Anderson, C. P. MacDonald, C. A. and Knoderer, B. S. Thompson: ‘PM2.5 Forecasting Method Development and Operations for Salt Lake City, Utah’, 2003 National Air Quality Conference, U.S. EPA, pp 1-18, 2003.
 M. Benjamin and J. Rousseau: ‘Winter INFO-SMOG Program Forecast for the Greater Montreal Area’, 2003 National Air Quality Conference, U.S. EPA, pp 19-23, 2003.
 Use of Time-Series Analysis to Examine the Link Between Photochemistry and PM Concentrations in Chicago, http://capita.wustl.edu/NEARDAT/WebLinks /pmupdate.htm.
 Air Pollution Forecasting in the UK, http: //www.airquality.co.uk/ archive/reports/ list.php.
 Ana Russo, Pedro G. Lin, Frank Raischel, Ricardo Trigo, and Manuel Mendes, ‘Neural network forecast of daily pollution concentration using optimal meteorological data at synoptic and local scales’, Atmospheric Pollution Research, pp.540~549, 6, 2015.
 Madhavi Anushka Elangasinghe, Naresh Singhal, Kim N. Dirks, Jennifer A. Salmond, ‘Development of an ANN–based air pollution forecasting system with explicit knowledge through sensitivity analysis’, Atmospheric Pollution Research, pp.696~708, 5, 2014.