Forecasting interval time series using a fully complex-valued RBF neural network with DPSO and PSO algorithms

•We propose a novel interval time series (ITS) forecasting approach.•A fully complex-valued RBF neural network is extended to address ITS forecasting.•DPSO/PSO are used to jointly optimize the structure and parameters of the model.•Results on simulated and real-world ITS data confirm the efficacy of the approach.