Main Article Content
Prediction model of missing data: a case study of PM10 across Malaysia Region
Abstract
PM10 is one of the major concerns that have high potential for harmful effects on human health. Thus, prediction of PM10 was performed with the objectives to model suitable PM10 prediction formula to predict the concentration of PM10. Imputation methods of EMB-algorithm and nearest neighbor were applied to treat missing data before analyzed by Fit model, MLR and ANN. R2 obtained for Fit-model, MLR and ANN using imputation method of EMB-algorithm and nearest neighbor are (0.9975, 0.3858), (0.9623, 0.3857) and (0.9975, 0.4025) respectively. Sensitivity analysis (SA) shows humidity, temperature, CO, UVB and O3 out of fifteen parameters contribute the most to the present of PM10 concentration. In conclusion, formula for the best PM10 prediction can be modeled by using ANN or Fit model together with the imputation method of EMB-algorithm.
Keywords: PM10 prediction; fit-model; MLR, ANN; imputation method