Underwater Acoustic Target Recognition with a Residual Network and the Optimized Feature Extraction Method
Source abstract
Abstract
Underwater Acoustic Target Recognition (UATR) remains one of the most challenging tasks in underwater signal processing due to the lack of labeled data acquisition, the impact of the time-space varying intrinsic characteristics, and the interference from other noise sources. Although some deep learning methods have been proven to achieve state-of-the-art accuracy, the accuracy of the recognition task can be improved by designing a Residual Network and optimizing feature extraction. To give a more comprehensive representation of the underwater acoustic signal, we first propose the three-dimensional fusion features along with the data augment strategy of SpecAugment. Afterward, an 18-layer Residual Network (ResNet18), which contains the center loss function with the embedding layer, is designed to train the aggregated features with an adaptable learning rate. The recognition experiments are conducted on the ship-radiated noise dataset from a real environment, and the accuracy results of 94.3% indicate that the proposed method is appropriate for underwater acoustic recognition problems and sufficiently surpasses other classification methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Underwater Acoustics Research · Speech and Audio Processing · Geophysical Methods and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Acoustics Laboratory, Chinese Academy of Sciences, Shanghai 201805, China
University of Chinese Academy of Sciences, Beijing 100049, China
The School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 200237, China
Funding
the National Natural Science Foundation of China for Young Scholar · National Key R&D Program of China · Youth Innovation Promotion Association CAS · the development fund for Shanghai talents · Jiading Youth Talents Program
References (22)
Show source-provided references
1. Recognition method of underwater target radiated noise based on convolutional neural network
2. Pezeshki, A., Azimi-Sadjadi, M.R., Scharf, L.L., and Robinson, M. (2003, January 22–26). Underwater target classification using canonical correlations. Proceedings of the Oceans Celebrating Past Teaming Toward Future, San Diego, CA, USA.10.1109/OCEANS.2003.178180 ↗
3. Undersea target classification using canonical correlation analysis10.1109/JOE.2007.907926 ↗
4. Ke, X., Yuan, F., and Cheng, E. (2018). Underwater Acoustic Target Recognition Based on Supervised Feature-Separation Algorithm. Sensors, 18.10.3390/s18124318 ↗
5. Li, C., Liu, Z., Ren, J., Wang, W., and Xu, J. (2020). A Feature Optimization Approach Based on Inter-Class and Intra-Class Distance for Ship Type Classification. Sensors, 20.10.3390/s20185429 ↗
6. The classification of underwater acoustic target signals based on wave structure and support vector machine10.1121/1.4900181 ↗
7. Jian, L., Yang, H., Zhong, L., and Ying, X. (2014, January 29–31). Underwater target recognition based on line spectrum and support vector machine. Proceedings of the International Conference on Mechatronics, Control and Electronic Engineering (MCE2014), Shenyang, China.
8. Feature extraction of underwater target signal using Mel frequency cepstrum coefficients based on acoustic vector sensor10.1155/2016/7864213 ↗
9. Zhang, Z., Xu, S., Cao, S., and Zhang, S. (2018). Deep Convolutional Neural Network with Mixup for Environmental Sound Classification. arXiv.10.1007/978-3-030-03335-4_31 ↗
10. Li, J., Dai, W., Metze, F., Qu, S., and Das, S. (2017, January 5–9). A comparison of deep learning methods for environmental sound detection. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.10.1109/ICASSP.2017.7952131 ↗
11. Su, Y., Zhang, K., Wang, J., and Madani, K. (2019). Environment Sound Classification Using a Two-Stream CNN Based on Decision-Level Fusion. Sensors, 19.10.3390/s19071733 ↗
12. Deep learning methods for underwater target feature extraction and recognition10.1155/2018/1214301 ↗
13. Testolin, A., and Diamant, R. (2020). Combining Denoising Autoencoders and Dynamic Programming for Acoustic Detection and Tracking of Underwater Moving Targets. Sensors, 20.10.3390/s20102945 ↗
14. Testolin, A., Kipnis, D., and Diamant, R. (2020). Detecting Submerged Objects Using Active Acoustics and Deep Neural Networks: A Test Case for Pelagic Fish. IEEE Trans. Mob. Comput.
15. Shen, S., Yang, H., Li, J., Xu, G., and Sheng, M. (2018). Auditory Inspired Convolutional Neural Networks for Ship Type Classification with Raw Hydrophone Data. Entropy, 20.10.3390/e20120990 ↗
16. ShipsEar: An underwater vessel noise database10.1016/j.apacoust.2016.06.008 ↗
17. Yang, H., Shen, S., Yao, X., Sheng, M., and Wang, C. (2018). Competitive deep-belief networks for underwater acoustic target recognition. Sensors, 18.10.3390/s18040952 ↗
18. Luo, X., and Feng, Y. (2020). An Underwater Acoustic Target Recognition Method Based on Restricted Boltzmann Machine. Sensors, 20.10.3390/s20185399 ↗
19. End-to-end environmental sound classification using a 1D convolutional neural network10.1016/j.eswa.2019.06.040 ↗
20. Park, D.S., Chan, W., Zhang, Y., Chiu, C.C., Zoph, B., Cubuk, E.D., and Le, Q.V. (2019). SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition. arXiv.10.21437/Interspeech.2019-2680 ↗
21. He, K., Zhang, X., and Ren, S. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision & Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
22. Wen, Y., Zhang, K., Li, Z., and Qiao, Y. (2016). A discriminative feature learning approach for deep face recognition. ECCV, Springer.10.1007/978-3-319-46478-7_31 ↗