Spectrum prediction for high-frequency radar based on Extreme Learning Machine

摘要

In this paper, a new predictive method based on Extreme Learning Machine is proposed to predict the spectrum data obtained from by frequency monitoring system of high-frequency radar. In order to improve the forecasting accuracy and real-time of spectrum prediction of high-frequency radar, Empirical Mode Decomposition method is used for the preprocessing of spectrum data. Based on the simulation environment of MATLAB, compared with the predictive method based on support vector regression, the results show that the proposed method performs better both at forecasting accuracy and speed.