Deep convolution stack for waveform in underwater acoustic target recognition

Abstract In underwater acoustic target recognition, deep learning methods have been proved to be effective on recognizing original signal waveform. Previous methods often utilize large convolutional kernels to extract features at the beginning of neural networks. It leads to a lack of depth and stru...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shengzhao Tian, Duanbing Chen, Hang Wang, Jingfa Liu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/0a2e8f2785584d68a2ccc8d0c380e1cc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0a2e8f2785584d68a2ccc8d0c380e1cc
record_format	dspace
spelling	oai:doaj.org-article:0a2e8f2785584d68a2ccc8d0c380e1cc2021-12-02T14:29:15ZDeep convolution stack for waveform in underwater acoustic target recognition10.1038/s41598-021-88799-z2045-2322https://doaj.org/article/0a2e8f2785584d68a2ccc8d0c380e1cc2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88799-zhttps://doaj.org/toc/2045-2322Abstract In underwater acoustic target recognition, deep learning methods have been proved to be effective on recognizing original signal waveform. Previous methods often utilize large convolutional kernels to extract features at the beginning of neural networks. It leads to a lack of depth and structural imbalance of networks. The power of nonlinear transformation brought by deep network has not been fully utilized. Deep convolution stack is a kind of network frame with flexible and balanced structure and it has not been explored well in underwater acoustic target recognition, even though such frame has been proven to be effective in other deep learning fields. In this paper, a multiscale residual unit (MSRU) is proposed to construct deep convolution stack network. Based on MSRU, a multiscale residual deep neural network (MSRDN) is presented to classify underwater acoustic target. Dataset acquired in a real-world scenario is used to verify the proposed unit and model. By adding MSRU into Generative Adversarial Networks, the validity of MSRU is proved. Finally, MSRDN achieves the best recognition accuracy of 83.15%, improved by 6.99% from the structure related networks which take the original signal waveform as input and 4.48% from the networks which take the time-frequency representation as input.Shengzhao TianDuanbing ChenHang WangJingfa LiuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Shengzhao Tian Duanbing Chen Hang Wang Jingfa Liu Deep convolution stack for waveform in underwater acoustic target recognition
description	Abstract In underwater acoustic target recognition, deep learning methods have been proved to be effective on recognizing original signal waveform. Previous methods often utilize large convolutional kernels to extract features at the beginning of neural networks. It leads to a lack of depth and structural imbalance of networks. The power of nonlinear transformation brought by deep network has not been fully utilized. Deep convolution stack is a kind of network frame with flexible and balanced structure and it has not been explored well in underwater acoustic target recognition, even though such frame has been proven to be effective in other deep learning fields. In this paper, a multiscale residual unit (MSRU) is proposed to construct deep convolution stack network. Based on MSRU, a multiscale residual deep neural network (MSRDN) is presented to classify underwater acoustic target. Dataset acquired in a real-world scenario is used to verify the proposed unit and model. By adding MSRU into Generative Adversarial Networks, the validity of MSRU is proved. Finally, MSRDN achieves the best recognition accuracy of 83.15%, improved by 6.99% from the structure related networks which take the original signal waveform as input and 4.48% from the networks which take the time-frequency representation as input.
format	article
author	Shengzhao Tian Duanbing Chen Hang Wang Jingfa Liu
author_facet	Shengzhao Tian Duanbing Chen Hang Wang Jingfa Liu
author_sort	Shengzhao Tian
title	Deep convolution stack for waveform in underwater acoustic target recognition
title_short	Deep convolution stack for waveform in underwater acoustic target recognition
title_full	Deep convolution stack for waveform in underwater acoustic target recognition
title_fullStr	Deep convolution stack for waveform in underwater acoustic target recognition
title_full_unstemmed	Deep convolution stack for waveform in underwater acoustic target recognition
title_sort	deep convolution stack for waveform in underwater acoustic target recognition
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/0a2e8f2785584d68a2ccc8d0c380e1cc
work_keys_str_mv	AT shengzhaotian deepconvolutionstackforwaveforminunderwateracoustictargetrecognition AT duanbingchen deepconvolutionstackforwaveforminunderwateracoustictargetrecognition AT hangwang deepconvolutionstackforwaveforminunderwateracoustictargetrecognition AT jingfaliu deepconvolutionstackforwaveforminunderwateracoustictargetrecognition
_version_	1718391173008064512

Deep convolution stack for waveform in underwater acoustic target recognition

Ejemplares similares