doi: 10.18178/ijfcc.2017.6.3.504
The Forecast of PM10 Pollutant by Using a Hybrid Model
Ronnachai Chuentawat
1
,
Nittaya Kerdprasop
2
,
Kittisak Kerdprasop
2
- 1 Nakhonratchasima Rajabhat University, Thailand.
- 2 Suranaree University of Technology, Thailand.
Abstract
This research aims to study the forecasting modelto predict the 24-hour average PM10 concentration in theNorthern region of Thailand. This research presents a hybridmodel that combines the autoregressive part of theAutoregressive Integrated Moving Average (ARIMA) modelwith the support vector regression technique. The data used inthis study are the 24-hour average PM10 concentration from 3locations. Each of the data sets is the daily univariate time seriesduring 1st January to 31th May 2016. We evaluate predictiveperformance of our hybrid model using the two measurements:Root Mean Squared Error (RMSE) and Mean AbsolutePercentage Error (MAPE). The performance of our hybridmodel has been compared against the ARIMA model. From theexperimental results, we found that a hybrid model has lowerRMSE and MAPE than the ARIMA model for all three datasets. Therefore, we concluded that our hybrid model can beused to forecast the 24-hour average PM10 concentration in theNorthern region of Thailand.
Keywords
- PM10
- ARIMA model
- support vectorregression
- hybrid model
How to Cite
Ronnachai Chuentawat, Nittaya Kerdprasop, and Kittisak Kerdprasop, "The Forecast of PM10 Pollutant by Using a Hybrid Model," International Journal of Future Computer and Communication, vol. 6, no. 3, pp. 128-132, 2017. https://doi.org/ 10.18178/ijfcc.2017.6.3.504
Copyright & License
Copyright © 2017 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).