Forecasting of Kelantan’s air pollution index [AP] PM2.5 using support vector machine [SVM] / Nur Fithrinnisaa Zamani

Forecasting the air pollution index has become a popular topic in recent years due to the impact of air pollution on environmental and human health. The Support Vector Machine (SVM) is not only appropriate for object classification, regression analysis and pattern recognition, it can also be used in time series forecasting. The work presented here aims to compare the accuracy of different types of the kernel function in Support Vector Machine (SVM) and to build a forecasting system for Kelantan’s air pollution index for PM2.5 using Support Vector Machine (SVM). The data used was provided by the Department of Environment (DOE) and was recorded from two Continuous Air Quality Monitoring Stations (CAQM) located at Tanah Merah and Kota Bharu. The results of the model were analyzed by using mean absolute error (MAE) and root mean squared error (RMSE). It is found that the proposed model using Radial Basis Function (RBF) kernel function with its parameters of cost and gamma equal to 100 can effectively and accurately forecast the air pollution index based on the model testing with 0.03868583 (MAE) and 0.06251793 (RMSE) for API in Kota Bharu and 0.03857308 (MAE) and 0.05895648 (RMSE) for API in Tanah Merah.