An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder

Tianyi Yao; Chenhong Yan; Yang Yu; Jiawei Tu; Guang Pan

doi:10.1145/3631726.3631779

An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder

Tianyi Yao
, Chenhong Yan
, Yang Yu
, Jiawei Tu
, Guang Pan

School of Marine Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The noise radiated from marines consists of line spectra and continuous spectra, within which the line spectra contain high energy and propagate over long distances. Traditional methods for line spectrum detection exhibit poor performance in underwater target detection for weak noise signals. Hence, this paper proposes an algorithm enhancing the frequency domain line spectrum based on stacked sparse autoencoders to exploit the sparsity of the frequency and spatial domain line spectrum signals. This algorithm shows stronger line spectrum detection capability than the Conventional Adaptive Line Enhancer algorithm (C-ALE). Ceteris paribus, this algorithm yields an increase of 3.2 dB in the output Signal-to-Noise Ratio (oSNR).

Original language	English
Title of host publication	WUWNet 2023 - 17th ACM International Conference on Underwater Networks and Systems
Publisher	Association for Computing Machinery
ISBN (Electronic)	9798400716744
DOIs	https://doi.org/10.1145/3631726.3631779
State	Published - 24 Nov 2023
Event	17th ACM International Conference on Underwater Networks and Systems, WUWNet 2023 - Shenzhen, China Duration: 23 Nov 2023 → 26 Nov 2023

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	17th ACM International Conference on Underwater Networks and Systems, WUWNet 2023
Country/Territory	China
City	Shenzhen
Period	23/11/23 → 26/11/23

Keywords

Array signal processing
line spectrum enhancement
sparse autoencoders
underwater target detection

Access to Document

10.1145/3631726.3631779

Cite this

@inproceedings{6371cd4e590145bea19ee5c6b99b6d89,

title = "An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder",

abstract = "The noise radiated from marines consists of line spectra and continuous spectra, within which the line spectra contain high energy and propagate over long distances. Traditional methods for line spectrum detection exhibit poor performance in underwater target detection for weak noise signals. Hence, this paper proposes an algorithm enhancing the frequency domain line spectrum based on stacked sparse autoencoders to exploit the sparsity of the frequency and spatial domain line spectrum signals. This algorithm shows stronger line spectrum detection capability than the Conventional Adaptive Line Enhancer algorithm (C-ALE). Ceteris paribus, this algorithm yields an increase of 3.2 dB in the output Signal-to-Noise Ratio (oSNR).",

keywords = "Array signal processing, line spectrum enhancement, sparse autoencoders, underwater target detection",

author = "Tianyi Yao and Chenhong Yan and Yang Yu and Jiawei Tu and Guang Pan",

note = "Publisher Copyright: {\textcopyright} 2023 Owner/Author.; 17th ACM International Conference on Underwater Networks and Systems, WUWNet 2023 ; Conference date: 23-11-2023 Through 26-11-2023",

year = "2023",

month = nov,

day = "24",

doi = "10.1145/3631726.3631779",

language = "英语",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

booktitle = "WUWNet 2023 - 17th ACM International Conference on Underwater Networks and Systems",

}

Yao, T, Yan, C, Yu, Y, Tu, J & Pan, G 2023, An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder. in WUWNet 2023 - 17th ACM International Conference on Underwater Networks and Systems., 48, ACM International Conference Proceeding Series, Association for Computing Machinery, 17th ACM International Conference on Underwater Networks and Systems, WUWNet 2023, Shenzhen, China, 23/11/23. https://doi.org/10.1145/3631726.3631779

An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder. / Yao, Tianyi; Yan, Chenhong; Yu, Yang et al.
WUWNet 2023 - 17th ACM International Conference on Underwater Networks and Systems. Association for Computing Machinery, 2023. 48 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder

AU - Yao, Tianyi

AU - Yan, Chenhong

AU - Yu, Yang

AU - Tu, Jiawei

AU - Pan, Guang

PY - 2023/11/24

Y1 - 2023/11/24

N2 - The noise radiated from marines consists of line spectra and continuous spectra, within which the line spectra contain high energy and propagate over long distances. Traditional methods for line spectrum detection exhibit poor performance in underwater target detection for weak noise signals. Hence, this paper proposes an algorithm enhancing the frequency domain line spectrum based on stacked sparse autoencoders to exploit the sparsity of the frequency and spatial domain line spectrum signals. This algorithm shows stronger line spectrum detection capability than the Conventional Adaptive Line Enhancer algorithm (C-ALE). Ceteris paribus, this algorithm yields an increase of 3.2 dB in the output Signal-to-Noise Ratio (oSNR).

AB - The noise radiated from marines consists of line spectra and continuous spectra, within which the line spectra contain high energy and propagate over long distances. Traditional methods for line spectrum detection exhibit poor performance in underwater target detection for weak noise signals. Hence, this paper proposes an algorithm enhancing the frequency domain line spectrum based on stacked sparse autoencoders to exploit the sparsity of the frequency and spatial domain line spectrum signals. This algorithm shows stronger line spectrum detection capability than the Conventional Adaptive Line Enhancer algorithm (C-ALE). Ceteris paribus, this algorithm yields an increase of 3.2 dB in the output Signal-to-Noise Ratio (oSNR).

KW - Array signal processing

KW - line spectrum enhancement

KW - sparse autoencoders

KW - underwater target detection

UR - https://www.scopus.com/pages/publications/85197231576

U2 - 10.1145/3631726.3631779

DO - 10.1145/3631726.3631779

M3 - 会议稿件

AN - SCOPUS:85197231576

T3 - ACM International Conference Proceeding Series

BT - WUWNet 2023 - 17th ACM International Conference on Underwater Networks and Systems

PB - Association for Computing Machinery

T2 - 17th ACM International Conference on Underwater Networks and Systems, WUWNet 2023

Y2 - 23 November 2023 through 26 November 2023

ER -

An Algorithm Enhancing Line Spectrum in Frequency Domain Based on Stacked Sparse Autoencoder

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this