Prediction of Fine Dust (PM2.5) Concentration Based on RBF Kernel SVM  
Author Deukwoo Lee


Co-Author(s) Soowon Lee


Abstract Fine dust in the air causes respiratory problems. Particularly PM2.5 causes more serious health problems because it infiltrates deep blood vessels in the body, even the brain. Thus, it is important to predict days with ‘Bad’ level of PM2.5. In this paper, we propose a model to predict PM2.5 of Seoul city from air information. The prediction model uses RBF Kernel SVM with the adjusted gamma parameter. To evaluate the performance of the prediction model, we conducted comparative experiments using various models. As a result, the proposed model showed the best performance against the others in all labels.


Keywords Fine Dust, Particulate Matter, PM2.5, Machine Learning, RBF Kernel SVM
    Article #:  DSBFI19-114
Proceedings of ISSAT International Conference on Data Science in Business, Finance and Industry
July 3-5, 2019 - Da Nang, Vietnam