Effective air pollution prediction by combining time series decomposition with stacking and bagging ensembles of evolving spiking neural networks

Piotr S. Maciag, Robert Bembenik, Aleksandra Piekarzewicz, Javier Del Ser, Jesus L. Lobo, Nikola K. Kasabov

Abstract: Highlights•Stacking and bagging ensembles of evolving spiking neural networks.•Computational and space complexity of (bagging) evolving spiking neural nets.•A new encoding method based on Gaussian Receptive Fields.•Air pollution and weather time series data for Warsaw tested.