AUTOMATIC MODULATION CLASSIFICATION THROUGH CORRELATION ANALYSIS BETWEEN THE FEATURES

摘要

An automatic modulation classification method through correlation analysis between features according to the present invention includes: (a) the automatic modulation classification system defining feature values to classify a plurality of signals; (b) the automatic modulation classification system calculating a correlation coefficient between feature values for each signal; (c) the automatic modulation classification system calculating a representative value for each signal; And (d) the automatic modulation classification system using a DNN structure to measure the classification rate while excluding one for each feature in the SNR environment, including removing the meaningless features having little effect on classification and correlating coefficients. By analyzing, only the effective features with high impact are used, which has the effect of reducing the complexity of the Automatic Modulation Classification (AMC) system.