Underwater Acoustic Signal LOFAR Spectrogram Denoising Based on Enhanced Simulation
Source abstract
Abstract
In complex marine environments, extracting target features from acoustic signal is very difficult, making the targets hard to be recognized. Therefore, it is necessary to perform denoising method on the acoustic signal to highlight the target features. However, training deep learning denoising models requires a large mount of acoustic data with labels and obtaining labels with real measured data is also extremely difficult. In this paper, an enhanced simulation algorithm, which considers integrating features of target line spectrum and ocean environmental noise, is proposed to construct a large-scale training sample set. Additionally, a deep convolutional denoising model is presented, which is first train on simulated data and directly applied to real measured data for denoising, enabling line spectrum to be significantly displayed in the time-frequency spectrogram. The results on simulation experiments and sea trials demonstrate that the proposed method can significantly reduce ocean noise while preserving the characteristics of target line spectrum. Furthermore, the experiments demonstrate that the proposed convolutional denoising model has transferability and generalization, making it suitable for denoising underwater acoustic signal in different marine areas.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Underwater Acoustics Research · Underwater Vehicles and Communication Systems · Blind Source Separation Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Chengdu Union Big Data Technology Incorporation, Chengdu 610000, China
Sichuan Jiuzhou Electric Co., Ltd., Mianyang 621000, China
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610000, China
Funding
Innovation Research Group Project of the Natural Science Foundation of Sichuan
References (21)
Show source-provided references
1. Recent advances and future directions on underwater wireless communications10.1007/s11831-019-09354-8 ↗
2. Wang, P., and Peng, Y. (2020, January 19–20). Research on underwater acoustic target recognition based on LOFAR spectrogram and deep learning method. Proceedings of the 2020 5th International Conference on Automation, Control and Robotics Engineering (CACRE), Dalian, China.10.1109/CACRE50138.2020.9230002 ↗
3. Chen, J., Han, B., Ma, X., and Zhang, J. (2021). Underwater target recognition based on multi-decision LOFAR spectrogram enhancement: A deep-learning approach. Future Internet, 13.10.3390/fi13100265 ↗
4. Lu, H., Shang, J., Chen, Y., and Ma, Q. (2022, January 20–22). A LOFAR spectrogram multi-sub-band matching method for passive target recognition. Proceedings of the 2nd International Conference on Signal Image Processing and Communication (ICSIPC 2022), Qingdao, China.10.1117/12.2643457 ↗
5. Yao, H., Gao, T., Wang, Y., Wang, H., and Chen, X. (2024). Mobile_ViT: Underwater Acoustic Target Recognition Method Based on Local–Global Feature Fusion. J. Mar. Sci. Eng., 12.10.3390/jmse12040589 ↗
6. Yao, Q., Wang, Y., and Yang, Y. (2023). Underwater Acoustic Target Recognition Based on Data Augmentation and Residual CNN. Electronics, 12.10.3390/electronics12051206 ↗
7. Raj, K.M., Murugan, S.S., Natarajan, V., and Radha, S. (2011, January 3–5). Denoising algorithm using wavelet for underwater signal affected by wind driven ambient noise. Proceedings of the 2011 International Conference on Recent Trends in Information Technology (ICRTIT), Chennai, India.10.1109/ICRTIT.2011.5972413 ↗
8. A novel noise reduction technique for underwater acoustic signals based on complete ensemble empirical mode decomposition with adaptive noise, minimum mean square variance criterion and least mean square adaptive filter10.1016/j.dt.2019.07.020 ↗
9. Denoising and baseline drift removal method of MEMS hydrophone signal based on VMD and wavelet threshold processing10.1109/ACCESS.2019.2915612 ↗
10. A novel signal feature extraction technology based on empirical wavelet transform and reverse dispersion entropy10.1016/j.dt.2020.09.001 ↗
11. A line spectrum Enhancement Algorithm Based on Unsupervised Deep Learning
12. Research on LOFAR spectrogram Enhancement of Passive Sonar Target signal Based on Long Short-Term Memory Networks
13. Denoising and Reconstruction of Pulsed signal in Non-Gaussian Environments Based on Deep Learning
14. Enhancement of Underwater Acoustic Signal Based on Denoising Autoencoder
15. A Water Sound Signal Recognition Method Based on Deep Convolutional Networks and Convolutional Denoising Autoencoders
16. Luo, W. (2020). Research on Sonar Signal Feature Enhancement Technology Based on Deep Learning. [Master’s Thesis, Harbin Engineering University].
17. Jiang, Y. (2021). Research on Recognition and Separation of Underwater Acoustic signal Based on Generative Adversarial Networks. [Master’s Thesis, Harbin Engineering University].
18. Study on spectrogram Line Enhancement of Underwater Targets Based on Time-Frequency Attention Mechanism Network
19. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
20. Ma, T., Yan, S., and Wang, W. (2023, January 14–17). An underwater acoustic signal denoising algorithm based on U-Net. Proceedings of the 2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Zhengzhou, China.10.1109/ICSPCC59353.2023.10400249 ↗
21. A novel noise reduction technique for underwater acoustic signals based on dual-path recurrent neural network10.1049/cmu2.12518 ↗