Autoencoder-Based DIFAR Sonobuoy Signal Transmission and Reception Method Incorporating Residual Vector Quantization and Compensation Module: Validation Through Air Channel Modeling
Source abstract
Abstract
This paper proposes a novel autoencoder-based neural network for compressing and reconstructing underwater acoustic signals collected by Directional Frequency Analysis and Recording sonobuoys. To improve both signal compression rates and reconstruction performance, we integrate Residual Vector Quantization and a Compensation Module into the decoding process to effectively compensate for quantization errors. Additionally, an unstructured pruning technique is applied to the encoder to minimize computational load and parameters, addressing the battery limitations of sonobuoys. Experimental results demonstrate that the proposed method reduces the data transmission size by approximately 31.25% compared to the conventional autoencoder-based method. Moreover, the spectral mean square errors are reduced by 60.58% for continuous wave signals and 55.25% for linear frequency modulation signals under realistic air channel simulations.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Underwater Acoustics Research · Underwater Vehicles and Communication Systems · Speech and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information and Communication Engineering, Changwon National University, Changwon 51140, Republic of Korea
Funding
Changwon National University
References (30)
Show source-provided references
1. Urick, R.J. (1983). Principles of Underwater Sound, Peninsula Publishing. [3rd ed.].
2. Swift, M., Riley, J.L., Lourey, S., and Booth, L. (1999, January 22–25). An overview of the multistatic sonar program in Australia. Proceedings of the ISSPA ‘99—Fifth International Symposium on Signal Processing and Its Applications (IEEE Cat. No.99EX359), Brisbane, QLD, Australia.
3. Development of communication device for sound signal receiving and controlling of sonobuoy10.9766/KIMST.2021.24.3.317 ↗
4. Rayleigh fading channels in mobile digital communication systems. I. Characterization10.1109/35.601747 ↗
5. Kuzu, A., Aksit, M., Cosar, A., Guldogan, M.B., and Gunal, E. (2011, January 27–30). Calibration and test of DIFAR sonobuoys. Proceedings of the 2011 IEEE International Symposium on Industrial Electronics (ISIE), Gdansk, Poland.10.1109/ISIE.2011.5984342 ↗
6. Park, J., Seok, J., and Hong, J. (2022). Autoencoder-based signal modulation and demodulation methods for sonobuoy signal transmission and reception. Sensors, 22.10.3390/s22176510 ↗
7. Speech coding: A tutorial review10.1109/5.326413 ↗
8. Edler, B., and Purnhagen, H. (2000, January 21–25). Parametric audio coding. Proceedings of the WCC 2000—ICCT 2000. 2000 International Conference on Communication Technology, Beijing, China.10.1109/ICOSP.2000.894435 ↗
9. SoundStream: An end-to-end neural audio codec10.1109/TASLP.2021.3129994 ↗
10. Défossez, A., Copet, J., Synnaeve, G., and Adi, Y. (2022). High fidelity neural audio compression. arXiv.
11. Yang, D., Liu, S., Huang, R., Tian, J., Weng, C., and Zou, Y. (2023). HiFi-Codec: Group-residual vector quantization for high fidelity audio codec. arXiv.
12. Approximate Nearest Neighbor Search by Residual Vector Quantization10.3390/s101211259 ↗
13. Ahn, S., Woo, B.J., Han, M.H., Moon, C., and Kim, N.S. (2024). HILCodec: High-Fidelity and Lightweight Neural Audio Codec. arXiv.10.1109/JSTSP.2024.3469530 ↗
14. Xu, L., Wang, J., Zhang, J., and Xie, X. (2024, January 14–19). LightCodec: A high fidelity neural audio codec with low computation complexity. Proceedings of the ICASSP 2024—IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.10.1109/ICASSP48485.2024.10447532 ↗
15. Galand, C., and Esteban, D. (1983, January 14–16). Design and evaluation of parallel quadrature mirror filters (PQMF). Proceedings of the ICASSP ‘83—IEEE International Conference on Acoustics, Speech, and Signal Processing, Boston, MA, USA.
16. Kumar, K., Kumar, R., de Boissiere, T., Gestin, L., Teoh, W.Z., Sotelo, J., de Brebisson, A., Bengio, Y., and Courville, A. (2019). MelGAN: Generative adversarial networks for conditional waveform synthesis. arXiv.
17. Autoencoders, unsupervised learning, and deep architectures
18. Proakis, J.G., and Salehi, M. (2002). Communication Systems Engineering, Pearson. [2nd ed.].
19. Han, S., Pool, J., Tran, J., and Dally, W.J. (2015). Learning both weights and connections for efficient neural networks. arXiv.
20. ImageNet classification with deep convolutional neural networks10.1145/3065386 ↗
21. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
22. Zaman, M.A., Mamun, S.A., Gaffar, M., Alam, M.M., and Momtaz, M.I. (2010, January 11–15). Modeling VHF air-to-ground multipath propagation channel and analyzing channel characteristics and BER performance. Proceedings of the 2010 IEEE Region 8 International Conference on Computational Technologies in Electrical and Electronics Engineering (SIBIRCON), Irkutsk, Russia.10.1109/SIBIRCON.2010.5555104 ↗
23. Air–ground channel characterization for unmanned aircraft systems—Part I: Methods, measurements, and models for over-water settings10.1109/TVT.2016.2530306 ↗
24. Wireless channel models for maritime communications10.1109/ACCESS.2018.2879902 ↗
25. Parsons, J.D. (2000). The Mobile Radio Propagation Channel, Wiley.10.1002/0470841524 ↗
26. International Telecommunication Union (2024, December 20). Reflection from the Surface of the Earth. 1986–1990. Available online: http://www.itu.int/pub/R-REP-P.1008-1-1990.
27. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
28. Ultra Electronics Ltd. (2024, December 20). AN/SSQ-573 Directional Passive Multi-Mode Sonobuoy. Ultra Maritime. Available online: https://ultra.group/media/2662/anssq-573-datasheet_final.pdf.
29. Anderson, J.B., Aulin, T., and Sundberg, C.-E. (1986). Digital Phase Modulation, Plenum Press.10.1007/978-1-4899-2031-7 ↗
30. International Telecommunication Union (2024, December 20). Minimum Performance Objectives for Narrow-Band Digital Channels Using Geostationary Satellites to Serve Transportable and Vehicular Mobile Earth Stations in the 1-3 GHz Range, Not Forming Part of the ISDN. Recommendation ITU-R M.1181. Available online: https://www.itu.int/dms_pubrec/itu-r/rec/m/R-REC-M.1181-0-199510-I!!PDF-E.pdf.