The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Este artigo apresenta um detector de detecção de símbolos e classificação de modulação (SDMCD) baseado em rede neural profunda (DNN) para detecção de sinais cegos mistos. Ao contrário dos métodos convencionais que empregam detecção de símbolos após classificação de modulação, o SDMCD proposto pode realizar recuperação de símbolos e identificação de modulação simultaneamente. Um vetor de características cumulantes e de momento é apresentado em conjunto com uma arquitetura de autoencoder esparso de baixa complexidade para completar a detecção de sinais mistos. Os resultados numéricos mostram que o esquema SDMCD possui notável desempenho de taxa de erro de símbolo e precisão de classificação de modulação para vários formatos de modulação em canais de desvanecimento AWGN e Rayleigh. Além disso, o detector proposto possui desempenho robusto sob o impacto de deslocamentos de frequência e fase.
Chongzheng HAO
Nanjing University of Aeronautics and Astronautics
Xiaoyu DANG
Nanjing University of Aeronautics and Astronautics
Sai LI
Nanjing University of Aeronautics and Astronautics
Chenghua WANG
Nanjing University of Aeronautics and Astronautics
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.
Copiar
Chongzheng HAO, Xiaoyu DANG, Sai LI, Chenghua WANG, "Deep Learning Based Low Complexity Symbol Detection and Modulation Classification Detector" in IEICE TRANSACTIONS on Communications,
vol. E105-B, no. 8, pp. 923-930, August 2022, doi: 10.1587/transcom.2021EBP3148.
Abstract: This paper presents a deep neural network (DNN) based symbol detection and modulation classification detector (SDMCD) for mixed blind signals detection. Unlike conventional methods that employ symbol detection after modulation classification, the proposed SDMCD can perform symbol recovery and modulation identification simultaneously. A cumulant and moment feature vector is presented in conjunction with a low complexity sparse autoencoder architecture to complete mixed signals detection. Numerical results show that SDMCD scheme has remarkable symbol error rate performance and modulation classification accuracy for various modulation formats in AWGN and Rayleigh fading channels. Furthermore, the proposed detector has robust performance under the impact of frequency and phase offsets.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2021EBP3148/_p
Copiar
@ARTICLE{e105-b_8_923,
author={Chongzheng HAO, Xiaoyu DANG, Sai LI, Chenghua WANG, },
journal={IEICE TRANSACTIONS on Communications},
title={Deep Learning Based Low Complexity Symbol Detection and Modulation Classification Detector},
year={2022},
volume={E105-B},
number={8},
pages={923-930},
abstract={This paper presents a deep neural network (DNN) based symbol detection and modulation classification detector (SDMCD) for mixed blind signals detection. Unlike conventional methods that employ symbol detection after modulation classification, the proposed SDMCD can perform symbol recovery and modulation identification simultaneously. A cumulant and moment feature vector is presented in conjunction with a low complexity sparse autoencoder architecture to complete mixed signals detection. Numerical results show that SDMCD scheme has remarkable symbol error rate performance and modulation classification accuracy for various modulation formats in AWGN and Rayleigh fading channels. Furthermore, the proposed detector has robust performance under the impact of frequency and phase offsets.},
keywords={},
doi={10.1587/transcom.2021EBP3148},
ISSN={1745-1345},
month={August},}
Copiar
TY - JOUR
TI - Deep Learning Based Low Complexity Symbol Detection and Modulation Classification Detector
T2 - IEICE TRANSACTIONS on Communications
SP - 923
EP - 930
AU - Chongzheng HAO
AU - Xiaoyu DANG
AU - Sai LI
AU - Chenghua WANG
PY - 2022
DO - 10.1587/transcom.2021EBP3148
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E105-B
IS - 8
JA - IEICE TRANSACTIONS on Communications
Y1 - August 2022
AB - This paper presents a deep neural network (DNN) based symbol detection and modulation classification detector (SDMCD) for mixed blind signals detection. Unlike conventional methods that employ symbol detection after modulation classification, the proposed SDMCD can perform symbol recovery and modulation identification simultaneously. A cumulant and moment feature vector is presented in conjunction with a low complexity sparse autoencoder architecture to complete mixed signals detection. Numerical results show that SDMCD scheme has remarkable symbol error rate performance and modulation classification accuracy for various modulation formats in AWGN and Rayleigh fading channels. Furthermore, the proposed detector has robust performance under the impact of frequency and phase offsets.
ER -