Li Wei
ABSTRACT
An underwater acoustic (UWA) channel model with high validity and re-usability is widely demanded. In this paper, we propose a variational auto-encoder (VAE)-based deep generative model which learns an abstract representation of the UWA channel impulse responses (CIRs) and can generate CIR samples with similar features. A customized training process is proposed to avoid the model collapse and being trapped in a gradient pit. The proposed deep generative model is validated using field experimental data sets.
- Paul C Etter. 2018. Underwater acoustic modeling and simulation. CRC press.Google Scholar
- David Foster. 2019. Generative deep learning: Teaching machines to paint, write, compose, and play. O’Reilly Media.Google Scholar
- Jiajia Guo, Chao-Kai Wen, Shi Jin, and Geoffrey Ye Li. 2020. Convolutional neural network-based multiple-rate compressive sensing for massive MIMO CSI feedback: Design, simulation, and analysis. IEEE Transactions on Wireless Communications 19, 4(2020), 2827–2840.Google ScholarCross Ref
- Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q Weinberger. 2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. 4700–4708.Google Scholar
- Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114(2013).Google Scholar
- Zhilin Lu, Jintao Wang, and Jian Song. 2020. Multi-resolution CSI feedback with deep learning in massive MIMO system. In ICC 2020-2020 IEEE International Conference on Communications (ICC). IEEE, 1–6.Google ScholarCross Ref
- Roald Otnes, Paul A van Walree, and Trond Jenserud. 2013. Validation of replay-based underwater acoustic communication channel simulation. IEEE Journal of Oceanic Engineering 38, 4 (2013), 689–700.Google ScholarCross Ref
- Parastoo Qarabaqi and Milica Stojanovic. 2013. Statistical characterization and computationally efficient modeling of a class of underwater acoustic communication channels. IEEE Journal of Oceanic Engineering 38, 4 (2013), 701–717.Google ScholarCross Ref
- Zhijin Qin, Hao Ye, Geoffrey Ye Li, and Biing-Hwang Fred Juang. 2019. Deep learning in physical layer communications. IEEE Wireless Communications 26, 2 (2019), 93–99.Google ScholarCross Ref
- Aijun Song, Milica Stojanovic, and Mandar Chitre. 2019. Editorial Underwater Acoustic Communications: Where We Stand and What Is Next?IEEE Journal of Oceanic Engineering 44, 1 (2019), 1–6.Google Scholar
- Wensheng Sun and Zhaohui Wang. 2018. Online modeling and prediction of the large-scale temporal variation in underwater acoustic communication channels. IEEE Access 6(2018), 73984–74002.Google ScholarCross Ref
- Li Wei, Zheng Peng, Hao Zhou, Jun-Hong Cui, Shengli Zhou, Zhijie Shi, and James O’Donnell. 2013. Long island sound testbed and experiments. In 2013 OCEANS-San Diego. IEEE, 1–6.Google Scholar
- Chao-Kai Wen, Wan-Ting Shih, and Shi Jin. 2018. Deep learning for massive MIMO CSI feedback. IEEE Wireless Communications Letters 7, 5 (2018), 748–751.Google ScholarCross Ref
- T. C. Yang and S. H. Huang. 2016. Building a database of ocean channel impulse responses for underwater acoustic communication performance evaluation: issues, requirements, methods and results. In Proceedings of the 11th ACM International Conference on Underwater Networks & Systems. 1–8.Google ScholarDigital Library
- Hao Ye, Le Liang, and Geoffrey Ye Li. 2019. Circular convolutional auto-encoder for channel coding. In 2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). IEEE, 1–5.Google ScholarCross Ref
Recommendations
Underwater Acoustic Communication Channel Modeling using Deep Learning
With the recent increase in the number of underwater activities, having effective underwater communication systems has become increasingly important. Underwater acoustic communication has been widely used but greatly impaired due to the complicated ...
Experimental Studies of Underwater Acoustic Communications over Multipath Channels
Underwater acoustic experiments were conducted in the Trondheim fjord between fixed transmitters and receivers separated by 2.3 km, 4.3km and 8.0 km. Direct-sequence spread spectrum signals were used and binary information was modulated between two ...
Asynchronous cooperative transmission for three‐dimensional underwater acoustic networks
Although the techniques of cooperative transmission have been developed for terrestrial sensor networks in recent years to improve the bit‐error‐rate (BER) performance, the unique characteristics of the underwater acoustic communication channel, such as ...
Comments