A novel sea clutter suppression method based on neural network

Yifei Fan, Chenxiang Li, Dongtao Li, Jieshuang Li, Jia Su, Mingliang Tao

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

4 Scopus citations

Abstract

In order to suppress sea clutter effectively, it is necessary to estimate the center and width of the power spectrum of sea clutter accurately. Since the complex property of sea clutter, traditional methods cannot estimate the accurate parameters of power spectrum of sea clutter, which leads to the decrease of the clutter suppression performance. In this paper, a sea clutter suppression method based on neural network is proposed, where the real sea clutter datasets are taken to train the neural network. Finally, real sea clutter data is input into neural network to estimate the center and width of the power spectrum. The results show that the neural network is more accurate in estimating the spectral center and width than the traditional method.

Original languageEnglish
Title of host publication2021 IEEE 4th International Conference on Electronic Information and Communication Technology, ICEICT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages437-440
Number of pages4
ISBN (Electronic)9781665432030
DOIs
StatePublished - 18 Aug 2021
Event4th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2021 - Xi'an, China
Duration: 18 Aug 202120 Aug 2021

Publication series

Name2021 IEEE 4th International Conference on Electronic Information and Communication Technology, ICEICT 2021

Conference

Conference4th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2021
Country/TerritoryChina
CityXi'an
Period18/08/2120/08/21

Keywords

  • Clutter suppression
  • Eigenvector
  • Neural network
  • Sea clutter

Fingerprint

Dive into the research topics of 'A novel sea clutter suppression method based on neural network'. Together they form a unique fingerprint.

Cite this