Malaysian Journal of Mathematical Sciences, December 2019, Vol. 13(S)
Special Issue: Conference on Mathematics, Informatics and Statistics (CMIS2018)
Multi-Layer Perceptron Model for Air Quality Prediction
Abdullah, S., Ismail, M., and Ahmed, A. N.
Corresponding Email: [email protected]
Received date: -
Accepted date: -
Abstract:
This study trained two MLP models with different activation functions in assessing the capability of the model for the prediction of air quality. The daily air quality data and meteorological variables from the year 2010-2014 were assembled in training and testing the models. The MLP model with the combination of tansig and purelin activation function revealed 69.0% of the variance in data with 5.58 \(\eta\)g/m3 (RMSE) and 80.0% of the variance in data with 8.14 \(\eta\)g/m3 (RMSE), during training and testing phase, respectively. This model is appropriate for operational use by respected authorities in managing air quality and as an early warning during the unhealthy level of air quality.
Keywords: Air quality, Meteorological, Prediction
