location: Current position: Home >> Scientific Research >> Paper Publications

Online Chaotic Time Series Prediction Based on Square Root Kalman Filter Extreme Learning Machine

Hits:

Indexed by:会议论文

Date of Publication:2017-11-14

Included Journals:EI

Volume:10637 LNCS

Page Number:402-409

Abstract:In this paper, we proposed a novel neural network prediction model based on extreme learning machine for online chaotic time series prediction problems. The model is characterized by robustness and generalization. The initial weights are initialized by orthogonal matrix to improve the generalization performance and the output weights are updated by square root Kalman filter. The convergence of the algorithm is proved by Lyapunov stability theorem. Simulations based on artificial and real-life data sets demonstrate the effectiveness of the proposed model. © 2017, Springer International Publishing AG.

Pre One:A Secure Time Synchronization Protocol Against Fake Timestamps for Large-Scale Internet of Things

Next One:Automatic Detection of Epileptic Seizures Based on Entropies and Extreme Learning Machine