Deep Learning Based Underwater Acoustic Target Recognition: Introduce a Recent Temporal 2D Modeling Method

Author:

Tang Jun1ORCID,Gao Wenbo1ORCID,Ma Enxue1,Sun Xinmiao2,Ma Jinying3

Affiliation:

1. School of Civil Engineering, Tianjin University, Tianjin 300072, China

2. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China

3. School of Electronic Engineering, Tianjin University of Technology and Education, Tianjin 300222, China

Abstract

In recent years, the application of deep learning models for underwater target recognition has become a popular trend. Most of these are pure 1D models used for processing time-domain signals or pure 2D models used for processing time-frequency spectra. In this paper, a recent temporal 2D modeling method is introduced into the construction of ship radiation noise classification models, combining 1D and 2D. This method is based on the periodic characteristics of time-domain signals, shaping them into 2D signals and discovering long-term correlations between sampling points through 2D convolution to compensate for the limitations of 1D convolution. Integrating this method with the current state-of-the-art model structure and using samples from the Deepship database for network training and testing, it was found that this method could further improve the accuracy (0.9%) and reduce the parameter count (30%), providing a new option for model construction and optimization. Meanwhile, the effectiveness of training models using time-domain signals or time-frequency representations has been compared, finding that the model based on time-domain signals is more sensitive and has a smaller storage footprint (reduced to 30%), whereas the model based on time-frequency representation can achieve higher accuracy (1–2%).

Funder

National Key R&D Program of China

Publisher

MDPI AG

Reference38 articles.

1. Urick, R.J. (1983). Principles of Underwater Sound, McGraw-Hill Book, Co.

2. Subsea Broadband Reverberation Modeling and Simulation of High-speed Motion Sonar;Yang;J. Unmanned Undersea Syst.,2023

3. Multipath Effect of Sonar Pulse Waveforms in Shallow Water;Sun;J. Sichuan Ordnance,2013

4. Ranjani, G., and Sadashivappa, G. (2019). Analysis of Doppler Effects in Underwater Acoustic Channels using Parabolic Expansion Modeling. Int. J. Adv. Comput. Sci. Appl., 10.

5. IA-PNCC: Noise processing method for underwater target recognition convolutional neural network;Wang;Comput. Mater. Contin.,2019

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3