Automatic Modulation Classification Using Compressive Convolutional Neural Network

Sai Huang, Lu Chai, Zening Li, Di Zhang, Yuanyuan Yao, Yifan Zhang, Zhiyong Feng

Research output: Contribution to journalArticle

Abstract

The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.

Original languageEnglish
Article number8734711
Pages (from-to)79636-79643
Number of pages8
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Modulation
Neural networks

Keywords

  • Automatic modulation classification
  • compressive loss constraint
  • deep convolutional neural network
  • multiple constellation images

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Huang, S., Chai, L., Li, Z., Zhang, D., Yao, Y., Zhang, Y., & Feng, Z. (2019). Automatic Modulation Classification Using Compressive Convolutional Neural Network. IEEE Access, 7, 79636-79643. [8734711]. https://doi.org/10.1109/ACCESS.2019.2921988

Automatic Modulation Classification Using Compressive Convolutional Neural Network. / Huang, Sai; Chai, Lu; Li, Zening; Zhang, Di; Yao, Yuanyuan; Zhang, Yifan; Feng, Zhiyong.

In: IEEE Access, Vol. 7, 8734711, 01.01.2019, p. 79636-79643.

Research output: Contribution to journalArticle

Huang, S, Chai, L, Li, Z, Zhang, D, Yao, Y, Zhang, Y & Feng, Z 2019, 'Automatic Modulation Classification Using Compressive Convolutional Neural Network', IEEE Access, vol. 7, 8734711, pp. 79636-79643. https://doi.org/10.1109/ACCESS.2019.2921988
Huang, Sai ; Chai, Lu ; Li, Zening ; Zhang, Di ; Yao, Yuanyuan ; Zhang, Yifan ; Feng, Zhiyong. / Automatic Modulation Classification Using Compressive Convolutional Neural Network. In: IEEE Access. 2019 ; Vol. 7. pp. 79636-79643.
@article{b79f82c061584b6eb580aee3081192dd,
title = "Automatic Modulation Classification Using Compressive Convolutional Neural Network",
abstract = "The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.",
keywords = "Automatic modulation classification, compressive loss constraint, deep convolutional neural network, multiple constellation images",
author = "Sai Huang and Lu Chai and Zening Li and Di Zhang and Yuanyuan Yao and Yifan Zhang and Zhiyong Feng",
year = "2019",
month = "1",
day = "1",
doi = "10.1109/ACCESS.2019.2921988",
language = "English",
volume = "7",
pages = "79636--79643",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Automatic Modulation Classification Using Compressive Convolutional Neural Network

AU - Huang, Sai

AU - Chai, Lu

AU - Li, Zening

AU - Zhang, Di

AU - Yao, Yuanyuan

AU - Zhang, Yifan

AU - Feng, Zhiyong

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.

AB - The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.

KW - Automatic modulation classification

KW - compressive loss constraint

KW - deep convolutional neural network

KW - multiple constellation images

UR - http://www.scopus.com/inward/record.url?scp=85068988165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068988165&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2921988

DO - 10.1109/ACCESS.2019.2921988

M3 - Article

AN - SCOPUS:85068988165

VL - 7

SP - 79636

EP - 79643

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8734711

ER -