Forecasting of ARIMA air pollution with improved fuzzy data preparation.

An important way to protect public health is to forecast air quality by giving early warnings about air pollution. Management of air quality is highly dependent on data from time series collected at air monitoring stations. However, data input must be processed first in time series observations for several reasons, such as measurement errors, to prevent misleading results during forecast analysis. Data obtained from different measurements brings a degree of uncertainty that contributes to uncertainty in the data. Therefore, by constructing the Fuzzy Symmetry Triangular Fuzzy number data using the standard deviation and percentage error methods, the procedure for preparing data containing uncertain information is presented in this paper. ARIMA then uses the pre-processed data to create a predictive model. The findings of this study suggest that smaller prediction errors have resulted in the use of the proposed method to create fuzzy numbers for ARIMA. This implies that, with fewer prediction errors, the accuracy of the prediction model is higher. [ABSTRACT FROM AUTHOR]