Feature Based Modulation Classification for Overlapped Signals

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

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E101-A   No.7   pp.1123-1126
Publication Date: 2018/07/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E101.A.1123
Type of Manuscript: LETTER
Category: Digital Signal Processing
Keyword: 
modulation classification,  overlapped sources,  cumulant,  multinomial logistic regression,  multi-gene genetic programming,  

Full Text: PDF(277.6KB)
>>Buy this Article


Summary: 
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.