In this section, we will use MLPs to develop time series forecasting models. The dataset used for these examples is on air pollution measured by concentration of particulate matter (PM) of diameter less than or equal to 2.5 micrometers. There are other variables such as air pressure, air temperature, dew point, and so on. A couple of time series models have been developed-one on air pressure and the other on pm 2.5. The dataset has been downloaded from the UCI Machine Learning Repository. The link to the problem's description and datasets is https://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data.
The code for the time series model of air pressure is in the Jupyter notebook code/Chapter_5_Air Pressure_Time_Series_Forecasting_by_MLP.ipynb ...
