Underwater acoustic target recognition based on u-shaped network

Xue Lingzhi, Zeng Xiangyang

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

Abstract

Underwater target recognition is an essential but difficult technique in acoustic signal processing. The most serious challenge of the underwater recognition is the scarcity of underwater acoustic samples. To solve this problem, this paper proposed a local skip connection U-shaped architecture network (U-Net), which is based on the convolutional neural network (CNN). The network architecture is designed ingeniously with generating a contracting path and an expansive path to achieve the extraction of different scale features, so as to improve the classification rate. The experimental results based on the measured data demonstrate that the recognition accuracy of our proposed scheme performs better than that of the deep belief network (DBN), deep auto-encoder (DAE) model and UATC-Densenet (underwater acoustic target classification Densenet) model. Meanwhile, the visualization of these four networks shows that the proposed network can learn more effective feature information with limited samples.

Original languageEnglish
Title of host publicationProceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering
EditorsTyler Dare, Stuart Bolton, Patricia Davies, Yutong Xue, Gordon Ebbitt
PublisherThe Institute of Noise Control Engineering of the USA, Inc.
ISBN (Electronic)9781732598652
DOIs
StatePublished - 2021
Event50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021 - Washington, United States
Duration: 1 Aug 20215 Aug 2021

Publication series

NameProceedings of INTER-NOISE 2021 - 2021 International Congress and Exposition of Noise Control Engineering

Conference

Conference50th International Congress and Exposition of Noise Control Engineering, INTER-NOISE 2021
Country/TerritoryUnited States
CityWashington
Period1/08/215/08/21

Fingerprint

Dive into the research topics of 'Underwater acoustic target recognition based on u-shaped network'. Together they form a unique fingerprint.

Cite this