Multihydrophone Fusion Network for Modulation Recognition
Abstract
:1. Introduction
- This study proposes a new network framework, including a feature extraction module and a fusion module, which successfully realizes effective identification in the multihydrophone reception scenarios of 2FSK, 4FSK, 8FSK, BPSK, LFM, and OFDM and other commonly used underwater acoustic communication signals.
- To extract the characteristics of the signals received by multiple hydrophones, this study uses a CNN to extract the characteristics of the signal time-domain sequence.
- To fully utilize different locations to obtain signals of different reception qualities, this study uses a neural network to construct a fusion module that can automatically evaluate the signal quality and assign the optimal weights to different hydrophones.
- Experimental results show that the proposed method is better than DV and DA in multiple hydrophone scenarios, showing an improvement of approximately 16% when the symbol signal-to-noise ratio is 10 dB.
2. System Model
3. Proposed Recognition Approach
3.1. Feature Extraction Module
3.2. Fusion Module
3.3. Loss Function
4. Review of the Other Fusion Method
5. Performance Analysis
5.1. Generation of Underwater Acoustic Communication Signals
5.2. Experiment Setting
5.3. Result Analysis
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Zhang, Y.; Ansari, N.; Su, W. Multi-Sensor Signal Fusion Based Modulation Classification by Using Wireless Sensor Networks. In Proceedings of the 2011 IEEE International Conference on Communications (ICC), Kyoto, Japan, 5–9 June 2011; pp. 1–5. [Google Scholar]
- Forero, P.; Cano, A.; Giannakis, G. Distributed feature-based modulation classification using wireless sensor networks. In Proceedings of the 2008 IEEE Military Communications Conference, San Diego, CA, USA, 16–19 November 2008; pp. 1–7. [Google Scholar]
- Wimalajeewa, T.; Jagannath, J.; Varshney, P.; Drozd, A.; Su, W. Distributed Automatic Modulation Classification with Multiple Sensors. IEEE Sens. J. 2010, 10, 1779–1785. [Google Scholar]
- Wimalajeewa, T.; Jagannath, J.; Varshney, P.; Drozd, A.; Su, W. Distributed asynchronous modulation classification based on hybrid maximum likelihood approach. In Proceedings of the 2015 IEEE Military Communications Conference, Tampa, FL, USA, 26–28 October 2015; pp. 1519–1523. [Google Scholar]
- Yin, J.; Luo, W.; Li, L.; Han, X.; Guo, L.; Wang, J. Enhancement of underwater acoustic signal based on denoising automatic-encoder. J. Commun. 2019, 40, 119–126. [Google Scholar]
- Wang, B.; Wang, H.; Li, Y. A Method of Modulation Recognition Technology for Underwater Acoustic Communication Signal in Impulsive Noise Environment. J. Signal Processing 2020, 36, 2107–2115. [Google Scholar]
- Li, L.; Huang, J.; Cheng, Q.; Meng, H.; Han, Z. Automatic Modulation Recognition: A Few-Shot Learning Method Based on the Capsule Network. IEEE Wirel. Commun. Lett. 2020, 10, 474–477. [Google Scholar] [CrossRef]
- Yao, X.; Yang, H.; Li, Y. Modulation Identification of Underwater Acoustic Communications Signals Based on Generative Adversarial Networks. In Proceedings of the 2019 OCEANS, Seattle, WA, USA, 27–31 October 2019; pp. 1–6. [Google Scholar]
- Wang, T.; Hou, Y.; Zhang, H.; Guo, Z. Deep Learning Based Modulation Recognition With Multi-Cue Fusion. IEEE Wirel. Commun. Lett. 2021, 10, 1757–1760. [Google Scholar] [CrossRef]
- Ding, L.; Wang, S.; Zhang, W. Modulation Classification of Underwater Acoustic Communication Signals Based on Deep Learning. In Proceedings of the 2018 OCEANS—MTS/IEEE Kobe Techno-Ocean (OTO), Kobe, Japan, 28–31 May 2018; pp. 1–4. [Google Scholar]
- Wang, Y.; Jin, Y.; Zhang, H.; Lu, Q.; Cao, C.; Sang, Z.; Sun, M. Underwater Communication Signal Recognition Using Sequence Convolutional Network. IEEE Access 2021, 9, 46886–46899. [Google Scholar] [CrossRef]
- Yang, H.; Shen, S.; Xiong, J. Modulation Recognition of Underwater Acoustic Communication Signals Based on Denoting & Deep Sparse Autoencoder. In Proceedings of the INTER-NOISE and NOISE-CON Congress and Conference Proceedings, Hamburg, Germany, 21–24 August 2016; pp. 5144–5149. [Google Scholar]
- Liang, Z.; Tao, M.; Wang, L.; Su, J.; Yang, X. Automatic Modulation Recognition Based on Adaptive Attention Mechanism and ResNeXt WSL Model. IEEE Commun. Lett. 2021, 25, 2953–2957. [Google Scholar] [CrossRef]
- Wang, Y.; Wang, J.; Zhang, W.; Yang, J.; Gui, G. Deep Learning-Based Cooperative Automatic Modulation Classification Method for MIMO Systems. IEEE Trans. Veh. Technol. 2020, 69, 4575–4579. [Google Scholar] [CrossRef]
- An, Z.; Zhang, T.; Ma, B.; Deng, P.; Xu, Y. Cooperative modulation recognition based on one-dimensional. J. Commun. 2021, 42, 84–94. [Google Scholar]
- Li, Y.; Wang, B.; Shao, G.; Shao, S. Automatic Modulation Classification for Short Burst Underwater Acoustic Communication Signals Based on Hybrid Neural Networks. IEEE Access 2020, 8, 227793–227809. [Google Scholar] [CrossRef]
Signal Types | Symbol Rate (Baud) | Modulation Index | Roll-Off Factor | Carrier/Center Frequency (kHz) | No. of Subcarriers | Frequency Modulation Slope (Hz/ms) |
---|---|---|---|---|---|---|
2FSK | {500, 800} | {1, 1.2, 1.3} | / | [15, 16] | / | / |
4FSK | {500, 1000} | {1, 1.2, 1.3} | / | [15, 16] | / | / |
8FSK | {500, 1000} | {1, 1.2, 1.3} | / | [15, 16] | / | / |
BPSK | {1000, 2000} | / | {0.2, 0.25, 0.3} | [15, 16] | / | / |
LFM | / | / | / | [15, 16] | / | {60, 100} |
OFDM | {31, 56} | / | / | [15, 16] | {64, 128, 256} | / |
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
Wang, H.; Wang, B.; Wu, L.; Tang, Q. Multihydrophone Fusion Network for Modulation Recognition. Sensors 2022, 22, 3214. https://doi.org/10.3390/s22093214
Wang H, Wang B, Wu L, Tang Q. Multihydrophone Fusion Network for Modulation Recognition. Sensors. 2022; 22(9):3214. https://doi.org/10.3390/s22093214
Chicago/Turabian StyleWang, Haiwang, Bin Wang, Lulu Wu, and Qiang Tang. 2022. "Multihydrophone Fusion Network for Modulation Recognition" Sensors 22, no. 9: 3214. https://doi.org/10.3390/s22093214
APA StyleWang, H., Wang, B., Wu, L., & Tang, Q. (2022). Multihydrophone Fusion Network for Modulation Recognition. Sensors, 22(9), 3214. https://doi.org/10.3390/s22093214