Design of Siamese Network for Underwater Target Recognition with Small Sample Size
Abstract
:1. Introduction
2. Model of Ship-Radiated Noise and Sample Generation
2.1. Ship-Radiated Noise and DEMON Processing
2.2. Design of Samples and Datasets
2.2.1. Sample Design
- 1.
- Generation of the dataset with different Doppler shifts (dataset B)
- 2.
- Generation of the dataset with different SNRs (dataset C)
- 3.
- Generation of the dataset with different interference (dataset D)
2.2.2. Generation of Positive and Negative Sample Pairs
3. Design of the Siamese Network
4. Experiments and Results
4.1. Network Training
4.2. Network Performance Test
- Performance evaluation of Doppler shifts.
- Performance evaluation of SNRs.
- Performance evaluation of interference.
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Hemminger, T.L.; Pao, Y.-H. Detection and classification of underwater acoustic transients using neural networks. IEEE Trans. Neural Netw. 1994, 5, 712–718. [Google Scholar] [CrossRef]
- Yang, H.; Shen, S.; Yao, X.; Sheng, M.; Wang, C. Competitive Deep-Belief Networks for Underwater Acoustic Target Recognition. Sensors 2018, 18, 952. [Google Scholar] [CrossRef] [Green Version]
- Zhu, J.; Christensen, J.; Jung, J.; Martin-Moreno, L.; Yin, X.; Fok, L.; Zhang, X.; Garcia-Vidal, F.J. A holey-structured metamaterial for acoustic deep-subwavelength imaging. Nat. Phys. 2011, 7, 52–55. [Google Scholar] [CrossRef] [Green Version]
- Henclik, S. Underwater acoustic target tracking with fixed passive sonar system. In Proceedings of the 6th European Conference on Underwater Acoustics (ECUA 2002), Gdansk, Poland, 24–27 June 2002. [Google Scholar]
- Zhang, Y.; Sun, J.; Zhang, Y. Research on acoustic signal detection simulation for passive sonar. In Proceedings of the 2010 International Conference on Computational and Information Sciences (ICCIS 2010), Chengdu, China, 17–19 December 2010. [Google Scholar]
- Feng, S.; Zhu, X. A Transformer-Based Deep Learning Network for Underwater Acoustic Target Recognition. IEEE Geosci. Remote Sens. Lett. 2022, 19, 1–5. [Google Scholar] [CrossRef]
- Yao, j.; Wang, D.; Hu, H.; Xing, W.; Wang, L. ADCNN: Towards learning adaptive dilation for convolutional neural networks. Pattern Recognit. 2022, 123, 108369. [Google Scholar] [CrossRef]
- Chen, Z.; Li, Y.; Liang, H.; Yu, J. Hierarchical Cosine Similarity Entropy for Feature Extraction of Ship-Radiated Noise. Entropy 2018, 20, 425. [Google Scholar] [CrossRef] [Green Version]
- Zeng, D.; Peng, R.; Jiang, C.; Li, Y.; Dai, J. CSDM: A context-sensitive deep matching model for medical dialogue information extraction. Inf. Sci. 2022, 607, 727–738. [Google Scholar] [CrossRef]
- Dubey, S.R.; Chakraborty, S. Average biased ReLU based CNN descriptor for improved face retrieval. Multimed. Tools Appl. 2021, 80, 23181–23206. [Google Scholar] [CrossRef]
- Zhu, J.; Hu, T.; Jiang, B.; Yang, X. Intelligent bearing fault diagnosis using PCA-DBN framework. Neural Comput. Appl. 2020, 32, 10773–10781. [Google Scholar] [CrossRef]
- Yang, H.; Li, L.-L.; Li, G.-H.; Guan, Q. A novel feature extraction method for ship-radiated noise. Def. Technol. 2022, 18, 604–617. [Google Scholar] [CrossRef]
- Safi, M.E.; Abbas, E.I. Isolated word recognition based on PNCC with different classifiers in a noisy environment. Appl. Acoust. 2022, 195, 108848. [Google Scholar] [CrossRef]
- Patil, A.A.; Patil, C.B.; Mahulikar, P.P. Effect of coactive influence of LDHs and PNCC on thermal and mechanical properties of epoxy resin. Plast. Rubber Compos. 2021, 50, 209–218. [Google Scholar] [CrossRef]
- Patil, A.A.; Patil, C.B.; Mahulikar, P.P. Impact of synergism of LDH with PNCC on the thermal and mechanical properties of polyester nanocomposites. Polym. Plast. Technol. Mater. 2020, 59, 864–873. [Google Scholar] [CrossRef]
- Zhang, Q.; Bai, J.; Xu, F. A retrieval method for encrypted speech based on improved power normalized cepstrum coefficients and perceptual hashing. Multimed. Tools Appl. 2022, 81, 15127–15151. [Google Scholar] [CrossRef]
- Takacs, B.; Doczi, R.; Suto, B.; Kallo, J.; Varkonyi, T.A.; Haidegger, T.; Kozlovszky, M. Extending AUV Response Robot Capabilities to. Solve Standardized Test Methods. Acta Polytech. Hung. 2016, 13, 157–170. [Google Scholar]
- Bereketli, A.; Tumcakir, M.; Yeni, B. P-AUV: Position aware routing and medium access for ad hoc AUV networks. J. Netw. Comput. Appl. 2019, 125, 146–154. [Google Scholar] [CrossRef]
- Ssegey, Z.; Nikos, K. Learning to Compare Image Patches via Convolutional Neural Networks. In Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 7–12 June 2015. [Google Scholar]
- Yuan, J.; Guo, H.; Jin, Z.; Jin, H.; Zhang, X.; Luo, J. One-shot Learning for Fine-grained Relation Extraction via Convolutional Siamese Neural Network. In Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA, 11–14 December 2017. [Google Scholar]
- Lee, D.-H. One-Shot Scale and Angle Estimation for Fast Visual Object Tracking. IEEE Access 2019, 7, 55477–55484. [Google Scholar] [CrossRef]
- Salberg, A.-B.; Swami, A. Doppler and frequency-offset synchronization in wideband OFDM. IEEE Trans. Wirel. Commun. 2005, 4, 2870–2881. [Google Scholar] [CrossRef]
- Yang, T.; Yang, W. Performance analysis of direct-sequence spread-spectrum underwater acoustic communications with low signal-to-noise-ratio input signals. J. Acoust. Soc. Am. 2008, 123, 842–855. [Google Scholar] [CrossRef]
- Tian, P.; Kang, R.; Yu, H.; Wu, Y. Analysis of quantisation noise within signal band for sinusoidal signal. IET Commun. 2013, 7, 335–339. [Google Scholar] [CrossRef]
- Wu, Y.; Yang, Y.; Yang, L.; Wang, Y. Underwater target recognition based on constant-beamwidth waveform fidelity and interference-suppression. J. Northwestern Polytech. Univ. 2015, 33, 843–848. [Google Scholar]
- Tanveer, M.; Tan, H.K.; Ng, H.F.; Leung, M.K.; Chuah, J.H. Regularization of Deep Neural Network with Batch Contrastive Loss. IEEE Access 2021, 9, 124409–124418. [Google Scholar] [CrossRef]
- Akritas, P.; Antoniou, I.; Ivanov, V.V. I dentification and prediction of discrete chaotic maps applying a Chebyshev neural network. Chaos Solitons Fractals 2000, 11, 337–344. [Google Scholar] [CrossRef]
- Ma, X.; Zhang, S.; Sun, J.; Han, Y.; Du, J.; Fu, X.; Yang, Y.; Sa, Y.; Li, Q.; Yang, C. A TFA-CNN method for quantitative analysis in infrared spectroscopy. Infrared Phys. Technol. 2022, 126, 104329. [Google Scholar] [CrossRef]
- Deng, M.; Zhang, Q.; Zhang, K.; Li, H.; Zhang, Y.; Cao, W. A Novel Defect Inspection System Using Convolutional Neural Network for MEMS Pressure Sensors. J. Imaging 2022, 8, 268. [Google Scholar] [CrossRef]
- Yang, L.; Yang, L.; Ho, K.C. Moving Target Localization in Multistatic Sonar by Differential Delays and Doppler Shifts. IEEE Signal Process. Lett. 2016, 23, 1160–1164. [Google Scholar] [CrossRef]
- Hammad, I.; Li, L.; El-Sankary, K.; Snelgrove, W.M. CNN Inference Using a Preprocessing Precision Controller and Approximate Multipliers with Various Precisions. IEEE Access 2021, 9, 7220–7232. [Google Scholar] [CrossRef]
- Li, M.T.; Lee, S.H. A Study on Small Pest Detection Based on a CascadeR-CNN-Swin Model. CMC Comput. Mater. Contin. 2022, 72, 6155–6165. [Google Scholar] [CrossRef]
- Goncalves, C.B.; Souza, J.R.; Fernandes, H. CNN architecture optimization using bio-inspired algorithms for breast cancer detection in infrared images. Comput. Biol. Med. 2022, 142, 105205. [Google Scholar] [CrossRef]
- DeVries, Z.; Locke, E.; Hoda, M.; Moravek, D.; Phan, K.; Stratton, A.; Phan, P. Using a national surgical database to predict complications following posterior lumbar surgery and comparing the area under the curve and F1-score for the assessment of prognostic capability. Spine J. 2021, 21, 1135–1142. [Google Scholar] [CrossRef]
Datasets | Ship Status | No. Ships | Sample Dimension | Total No. Samples | |
---|---|---|---|---|---|
Training | A | 1 | 7 | 1 × 2048 | 1 × 7 × 3000 |
Verification | B | 41 | 7 | 1 × 2048 | 41 × 7 × 500 |
C | 16 | 7 | 1 × 2048 | 16 × 7 × 500 | |
D | 7 | 7 | 1 × 2048 | 7 × 7 × 500 | |
Test | E | 41 | 10 | 1 × 2048 | 41 × 10 × 500 |
F | 16 | 10 | 1 × 2048 | 16 × 10 × 500 | |
G | 7 | 10 | 1 × 2048 | 7 × 10 × 500 |
Datasets | Sub-Dataset | Ship Status | No. Ships | No. Pairs | |
---|---|---|---|---|---|
Training | AA | AA+ | 1 | 7 | 1 × 7 × 1000 |
AA− | 1 | 7 | 1 × 7 × 1000 | ||
Validation | BB | BB+ | 41 | 7 | 41 × 7 × 500 |
BB− | 41 | 7 | 41 × 7 × 500 | ||
CC | CC+ | 16 | 7 | 16 × 7 × 500 | |
CC− | 16 | 7 | 16 × 7 × 500 | ||
DD | DD+ | 7 | 7 | 7 × 7 × 500 | |
DD− | 7 | 7 | 7 × 7 × 500 | ||
Test | EE | EE+ | 41 | 10 | 41 × 10 × 1000 |
EE− | 41 | 10 | 41 × 10 × 1000 | ||
FF | FF+ | 16 | 10 | 16 × 10 × 1000 | |
FF− | 16 | 10 | 16 × 10 × 1000 | ||
GG | GG+ | 7 | 10 | 7 × 10 × 1000 | |
GG− | 7 | 10 | 7 × 10 × 1000 |
Layer Type | Output Shape | No. Kernels | Kernel Size | Activation Function |
---|---|---|---|---|
Input | 2048 × 1 | |||
Conv_1D | 2048 × 4 | 4 | 1 × 5 | ReLU |
MaxPooling1D | 512 × 4 | 1 | ||
Conv_1D | 512 × 4 | 4 | 1 × 5 | ReLU |
MaxPooling1D | 128 × 4 | 1 | ||
Conv_1D | 128 × 4 | 4 | 1 × 5 | ReLU |
MaxPooling1D | 32 × 4 | 1 | ||
Flatten | 128 × 1 | |||
Dense | 64 × 1 | ReLU |
Layer Type | Neuron Size | Output Shape |
---|---|---|
Input | 2048 × 1 | |
Dense_1 | 1024 | 1024 × 1 |
Dense_2 | 256 | 256 × 1 |
Dropout_1 | 256 × 1 | |
Dense_3 | 128 | 128 × 1 |
Dropout_2 | 128 × 1 | |
Dense_4 | 64 | 64 × 1 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Liu, D.; Shen, W.; Cao, W.; Hou, W.; Wang, B. Design of Siamese Network for Underwater Target Recognition with Small Sample Size. Appl. Sci. 2022, 12, 10659. https://doi.org/10.3390/app122010659
Liu D, Shen W, Cao W, Hou W, Wang B. Design of Siamese Network for Underwater Target Recognition with Small Sample Size. Applied Sciences. 2022; 12(20):10659. https://doi.org/10.3390/app122010659
Chicago/Turabian StyleLiu, Dali, Wenhao Shen, Wenjing Cao, Weimin Hou, and Baozhu Wang. 2022. "Design of Siamese Network for Underwater Target Recognition with Small Sample Size" Applied Sciences 12, no. 20: 10659. https://doi.org/10.3390/app122010659
APA StyleLiu, D., Shen, W., Cao, W., Hou, W., & Wang, B. (2022). Design of Siamese Network for Underwater Target Recognition with Small Sample Size. Applied Sciences, 12(20), 10659. https://doi.org/10.3390/app122010659