Comparison of support vector regression (SVR) kernel functions for predicting PM10 time series data in Malaysia.

In this study, the Support Vector Regression (SVR) model was used to forecast air quality time series data which is the particulate matter 10 micrometers or less in diameter (PM₁₀) in Malaysia. Several SVR kernel functions, which are the Linear, Polynomial and Radial Basis Function (RBF) kernels, were considered in this study to determine the most suitable kernel function for forecasting the PM₁₀ time series. The period of the data is from 5th July 2017 to 31st January 2019 consists of five air quality monitoring stations which are Kangar station in Perlis, Tasek Ipoh station in Perak, Shah Alam station in Selangor, Pasir Gudang station in Johor and Kuala Terengganu station in Terengganu. Model performance was compared based on the testing dataset's mean squared error (MSE) values. The results show that the SVR model with Radial Basis Function kernel is more suitable for forecasting the PM₁₀ time series compared to the Linear and Polynomial kernels. [ABSTRACT FROM AUTHOR]