Feature Based Modulation Classification for Overlapped Signals

Yizhou JIANG; Sai HUANG; Yixin ZHANG; Zhiyong FENG; Di ZHANG; Celimuge WU

doi:10.1587/transfun.E101.A.1123

Regular Section

Feature Based Modulation Classification for Overlapped Signals

Yizhou JIANG, Sai HUANG, Yixin ZHANG, Zhiyong FENG, Di ZHANG, Celimuge WU

Author information

Keywords: modulation classification, overlapped sources, cumulant, multinomial logistic regression, multi-gene genetic programming

JOURNAL RESTRICTED ACCESS

2018 Volume E101.A Issue 7 Pages 1123-1126

DOI https://doi.org/10.1587/transfun.E101.A.1123

Details

Abstract

This letter proposes a novel modulation classification method for overlapped sources named LRGP involving multinomial logistic regression (MLR) and multi-gene genetic programming (MGGP). MGGP based feature engineering is conducted to transform the cumulants of the received signals into highly discriminative features and a MLR based classifier is trained to identify the combination of the modulation formats of the overlapped sources instead of signal separation. Extensive simulations demonstrate that LRGP yields superior performance compared with existing methods.

Corresponding author

Register with J-STAGE for free!