For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Feature Based Modulation Classification for Overlapped Signals
Yizhou JIANG Sai HUANG Yixin ZHANG Zhiyong FENG Di ZHANG Celimuge WU
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2018/07/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
Category: Digital Signal Processing
modulation classification, overlapped sources, cumulant, multinomial logistic regression, multi-gene genetic programming,
Full Text: PDF(277.6KB)
>>Buy this Article
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.