Multivariate chaotic time series prediction based on improved extreme learning machine

Abstract

For extreme learning machine (ELM), it is difficult to select an appropriate number of hidden layer nodes, which has a great influence on the prediction performance of ELM. Therefore, in order to overcome the influence of a large number of hidden layer nodes to prediction and enhance the prediction performance of ELM, an improved ELM is proposed based on orthogonal projections to latent structures (O-PLS) method. The improved ELM contains two steps. Firstly, the hidden layer of ELM is used to build the nonlinear mapping for input variables and get the output matrix H, where the number of bidden layer nodes can be random assigned. Then O-PLS is used to build the linear regression. Compared with least squares regression (LSR), O-PLS can effectively reduce the high dimensions, overcome the multicollinearity among H, which are caused by an improper number of hidden layer nodes. The simulation experiment results based on Lorenz time series and sunspots-runoff of Yellow river time series demonstrate that the improved ELM can effectively overcome the influence of hidden layer nodes to prediction performance and improve the stability performance and prediction performance of ELM.