Line Spectrum Enhancement of Underwater Acoustic Targets Based on a Time-Frequency Attention Network

GU Tianlong; ZHANG Qingzhi; LI Jingjing

doi:10.11999/JEIT230217

Volume 46 Issue 1

Jan. 2024

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2024 > 46(1): 92-100

GU Tianlong, ZHANG Qingzhi, LI Jingjing. Line Spectrum Enhancement of Underwater Acoustic Targets Based on a Time-Frequency Attention Network[J]. Journal of Electronics & Information Technology, 2024, 46(1): 92-100. doi: 10.11999/JEIT230217

Citation:

GU Tianlong, ZHANG Qingzhi, LI Jingjing. Line Spectrum Enhancement of Underwater Acoustic Targets Based on a Time-Frequency Attention Network[J]. Journal of Electronics & Information Technology, 2024, 46(1): 92-100. doi: 10.11999/JEIT230217

Citation:

PDF( 10984 KB)

Line Spectrum Enhancement of Underwater Acoustic Targets Based on a Time-Frequency Attention Network

doi: 10.11999/JEIT230217

1.
Engineering Research Center of Trustworthy AI, Ministry of Education, Jinan University, Guangzhou 510632, China
2.
Guangxi Key Laboratory of Trusted Software, Guilin University of Electronic Technology, Guilin 541004, China

Funds: The National Natural Science Foundation of China (U22A2099, 62172350), Fundamental Research Foundation for the Central Universities (21621028), Science and Technology Projects in Guangzhou (202201011128)

Received Date: 2023-04-03
Rev Recd Date: 2023-08-28

Available Online: 2023-08-30

Publish Date: 2024-01-17

Abstract

Abstract

Deep learning-based line spectrum enhancement methods have received increasing attention for improving the detection performance of underwater low-noise targets using passive sonar. Among them, Long Short-Term Memory (LSTM)-based line spectrum enhancement networks have high flexibility due to their nonlinear processing capabilities in time and frequency domains. However, their performance requires further improvement. Therefore, a Time-Frequency Attention Network (TFA-Net) is proposed herein. The line spectrum enhancement effect of the LOw-Frequency Analysis Record (LOFAR) spectrum can be improved by incorporating the time and frequency-domain attention mechanisms into LSTM networks, In TFA-Net, the time-domain attention mechanism utilizes the correlation between the hidden states of LSTM to increase the model’s attention in the time domain, while the frequency-domain attention mechanism increases the model’s attention in the frequency domain by designing the full link layer of the shrinkage sub-network in deep residual shrinkage networks as a one-dimensional convolutional layer. Compared to LSTM, TFA-Net has a higher system signal-to-noise ratio gain: when the input signal-to-noise ratio is –3 dB and –11 dB, the system signal-to-noise ratio gain is increased from 2.17 to 12.56 dB and from 0.71 to 10.6 dB, respectively. Experimental results based on simulated and real data show that TFA-Net could effectively improve the line spectrum enhancement effect of the LOFAR spectrum and address the problem of detecting underwater low-noise targets.
- Underwater target detection,
- LOFAR,
- Line spectrum enhancement,
- LSTM,
- Attention mechanism

FullText(HTML)

References(21)

References

[1]	ALI M F, JAYAKODY D N K, CHURSIN Y A, et al. Recent advances and future directions on underwater wireless communications[J]. Archives of Computational Methods in Engineering, 2020, 27(5): 1379–1412. doi: 10.1007/s11831-019-09354-8
[2]	ISLAM K Y, AHMAD I, HABIBI D, et al. A survey on energy efficiency in underwater wireless communications[J]. Journal of Network and Computer Applications, 2022, 198: 103295. doi: 10.1016/j.jnca.2021.103295
[3]	LI Sichun, JIN Xin, YAO Sibing, et al. Underwater small target recognition based on convolutional neural network[C]. Global Oceans 2020: Singapore – U. S. Gulf Coast, Biloxi, USA, 2020: 1–7.
[4]	JIN Guanghao, LIU Fan, WU Hao, et al. Deep learning-based framework for expansion, recognition and classification of underwater acoustic signal[J]. Journal of Experimental & Theoretical Artificial Intelligence, 2020, 32(2): 205–218. doi: 10.1080/0952813X.2019.1647560
[5]	BIANCO M J, GERSTOFT P, TRAER J, et al. Machine learning in acoustics: Theory and applications[J]. The Journal of the Acoustical Society of America, 2019, 146(5): 3590–3628. doi: 10.1121/1.5133944
[6]	VIVEK V S, VIDHYA S, and MADHANMOHAN P. Acoustic scene classification in hearing aid using deep learning[C]. 2020 International Conference on Communication and Signal Processing, Chennai, India, 2020: 695–699.
[7]	WANG Peibing and PENG Yuan. Research on feature extraction and recognition method of underwater acoustic target based on deep convolutional network[C]. 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications, Dalian, China, 2020: 863–868.
[8]	RAO S K and JAGAN B O L. Passive target tracking in underwater environment using bearing and frequency measurements[C]. OCEANS 2022-Chennai, Chennai, India, 2022: 1–4.
[9]	KOGEKAR A P, NAYAK R, and PATI U C. A CNN-BiLSTM-SVR based deep hybrid model for water quality forecasting of the river Ganga[C]. 2021 IEEE 18th India Council International Conference, Guwahati, India, 2021: 1–6.
[10]	朱雨男, 解方彤, 张明亮, 等. 基于多层双向长短时记忆网络的水声多载波通信索引检测方法[J]. 电子与信息学报, 2022, 44(6): 1984–1990. doi: 10.11999/JEIT210949 ZHU Yunan, XIE Fangtong, ZHANG Mingliang, et al. Index detection for underwater acoustic multi-carrier communication based on deep bidirectional long short-term memory network[J]. Journal of Electronics &Information Technology, 2022, 44(6): 1984–1990. doi: 10.11999/JEIT210949
[11]	鞠东豪, 迟骋, 李宇, 等. 基于无监督深度学习的线谱增强算法[J]. 舰船科学技术, 2020, 42(23): 117–120. doi: 10.3404/j.issn.1672-7649.2020.12.023 JU Donghao, CHI Cheng, LI Yu, et al. Line enhancement algorithm based on unsupervised deep learning for passive sonars[J]. Ship Science and Technology, 2020, 42(23): 117–120. doi: 10.3404/j.issn.1672-7649.2020.12.023
[12]	JU Donghao, CHI Cheng, LI Zigao, et al. Deep-learning-based line enhancer for passive sonar systems[J]. IET Radar, Sonar & Navigation, 2022, 16(3): 589–601. doi: 10.1049/rsn2.12205
[13]	WIDROW B, GLOVER J R, MCCOOL J M, et al. Adaptive noise cancelling: Principles and applications[J]. Proceedings of the IEEE, 1975, 63(12): 1692–1716. doi: 10.1109/PROC.1975.10036
[14]	杨路飞, 章新华, 吴秉坤. 基于长短时记忆网络的被动声纳目标信号LOFAR谱增强研究[J]. 电声技术, 2020, 44(6): 101–103. doi: 10.16311/j.audioe.2020.06.024 YANG Lufei, ZHANG Xinhua, and WU Bingkun. A study on signal LOFAR spectrum enhancement of passive sonar target based on short and short time memory network[J]. Audio Engineering, 2020, 44(6): 101–103. doi: 10.16311/j.audioe.2020.06.024
[15]	YANGZHOU Jianyun, MA Zhengyu, and HUANG Xun. A deep neural network approach to acoustic source localization in a shallow water tank experiment[J]. The Journal of the Acoustical Society of America, 2019, 146(6): 4802–4811. doi: 10.1121/1.5138596
[16]	SAMEK W, MONTAVON G, LAPUSCHKIN S, et al. Explaining deep neural networks and beyond: A review of methods and applications[J]. Proceedings of the IEEE, 2021, 109(3): 247–278. doi: 10.1109/JPROC.2021.3060483
[17]	SIAMI-NAMINI S, TAVAKOLI N, and NAMIN A S. The performance of LSTM and BiLSTM in forecasting time series[C]. 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, USA, 2019: 3285–3292.
[18]	王同, 苏林, 任群言, 等. 基于注意力机制的全海深声速剖面预测方法[J]. 电子与信息学报, 2022, 44(3): 726–736. doi: 10.11999/JEIT210078 WANG Tong, SU Lin, REN Qunyan et al. Full-sea depth sound speed profiles prediction using RNN and attention mechanism[J]. Journal of Electronics &Information Technology, 2022, 44(3): 726–736. doi: 10.11999/JEIT210078
[19]	李文洁, 葛凤培, 张鹏远, 等. 双向长短时记忆模型训练中的空间平滑正则化方法研究[J]. 电子与信息学报, 2019, 41(3): 544–550. doi: 10.11999/JEIT180314 LI Wenjie, GE Fengpei, ZHANG Pengyuan, et al. Spatial smoothing regularization for bi-direction long short-term memory model[J]. Journal of Electronics &Information Technology, 2019, 41(3): 544–550. doi: 10.11999/JEIT180314
[20]	RICKARD J and ZEIDLER J. Second-order output statistics of the adaptive line enhancer[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1979, 27(1): 31–39. doi: 10.1109/TASSP.1979.1163203
[21]	NEHORAI A and MALAH D. On the stability and performance of the adaptive line enhancer[C]. ICASSP'80. IEEE International Conference on Acoustics, Speech, and Signal Processing, Denver, USA, 1980: 478–481.