IEICE TRANSACTIONS on Fundamentals
Feature Based Modulation Classification for Overlapped Signals
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.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E101-A No.7 pp.1123-1126
- Publication Date
- 2018/07/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E101.A.1123
- Type of Manuscript
- LETTER
- Category
- Digital Signal Processing
Authors
Yizhou JIANG
Beijing University of Posts and telecommunications
Sai HUANG
Beijing University of Posts and telecommunications
Yixin ZHANG
Beijing University of Posts and telecommunications
Zhiyong FENG
Beijing University of Posts and telecommunications
Di ZHANG
Zhengzhou University
Celimuge WU
The University of Electro-Communications
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Yizhou JIANG, Sai HUANG, Yixin ZHANG, Zhiyong FENG, Di ZHANG, Celimuge WU, "Feature Based Modulation Classification for Overlapped Signals" in IEICE TRANSACTIONS on Fundamentals,
vol. E101-A, no. 7, pp. 1123-1126, July 2018, doi: 10.1587/transfun.E101.A.1123.
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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E101.A.1123/_p
Copy
@ARTICLE{e101-a_7_1123,
author={Yizhou JIANG, Sai HUANG, Yixin ZHANG, Zhiyong FENG, Di ZHANG, Celimuge WU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Feature Based Modulation Classification for Overlapped Signals},
year={2018},
volume={E101-A},
number={7},
pages={1123-1126},
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.},
keywords={},
doi={10.1587/transfun.E101.A.1123},
ISSN={1745-1337},
month={July},}
Copy
TY - JOUR
TI - Feature Based Modulation Classification for Overlapped Signals
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1123
EP - 1126
AU - Yizhou JIANG
AU - Sai HUANG
AU - Yixin ZHANG
AU - Zhiyong FENG
AU - Di ZHANG
AU - Celimuge WU
PY - 2018
DO - 10.1587/transfun.E101.A.1123
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E101-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2018
AB - 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.
ER -
English
