Loading...
Multiple steps time series prediction by a novel Recurrent Kernel Extreme Learning Machine approach
Author(s)
Date Issued
July 1, 2017
Type
Conference Paper
Abstract
This paper proposes a novel recurrent multi-steps- prediction model called Recurrent Kernel Extreme Learning Machine (RKELM). This model combines the strengths of recurrent multi-steps-prediction and Extreme Learning Machine (ELM) to unleash the limitation of prediction horizon. The kernel matrix is applied to replace the hidden layer mapping of ELM in order to solve the lack of predicting deterministic and parameter dependency. In the experiment, we apply two synthetic benchmark datasets and two real-world time series datasets including Malaysia palm oil price, ozone concentration of Toronto to evaluate RKELM and compare its performance against Recurrent Support Vector Regression (RSVR) and Recurrent Extreme Learning Machine (RELM). The experimental results show that RKELM has superior abilities in the different predicting horizons and stronger predicting deterministic than others.
Citation
2017 9th International Conference on Information Technology and Electrical Engineering Icitee 2017, 2018-January, 1-4, 2017