FPGA Deployment of Deep Neural Network for Modulation Recognition

  • Zhuang Xu
  • , Yunxiang Luo
  • , Wei Yao
  • , Xi Yang
  • , Shengliang Peng*
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

Modulation recognition is an important task in intelligent communications, and modulation recognition using deep neural network has gained considerable attention due to the rapid advancement of deep learning technology. However, implementing modulation recognition using deep neural network on a general-purpose platform is time-consuming, which makes it difficult to meet the high-speed and real-time requirements of practical applications. To address the issue, this paper proposes a field-programmable gate array (FPGA) deployment system for modulation recognition network. The proposed system leverages parallel computing and pipeline methods to significantly enhance the inference speed of the modulation network, Experiment results show that FPGA as a hardware accelerator can run parallel calculations up to 139 times faster than the ARM Cortex-A9 processor.

Original languageEnglish
Title of host publicationProceedings of 13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1397-1402
Number of pages6
ISBN (Electronic)9798350315196
DOIs
StatePublished - 2023
Externally publishedYes
Event13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023 - Qinhuangdao, China
Duration: 11 Jul 202314 Jul 2023

Publication series

NameProceedings of 13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

Conference

Conference13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023
Country/TerritoryChina
CityQinhuangdao
Period11/07/2314/07/23

Fingerprint

Dive into the research topics of 'FPGA Deployment of Deep Neural Network for Modulation Recognition'. Together they form a unique fingerprint.

Cite this