Zhang Yonglin, Wang Haibin, Li Chao, Meriaudeau Fabrice
State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing, 100190, China.
Laboratory ImViA, Université Bourgogne Franche-Comté, 21078 Dijon, France.
J Acoust Soc Am. 2022 Jun;151(6):4150. doi: 10.1121/10.0011674.
In this paper, a data augmentation aided complex-valued network is proposed for underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) channel estimations, wherein empirical mode decomposition based data augmentation is proposed to solve the current dilemma in the deep learning embedded UWA-OFDM communications: data scarcity and data-sampling difficulties in real-world applications. In addition, the significance of high-frequency component augmentation for the UWA channel and how it positively influences the following model training are discussed in detail and demonstrated experimentally in this paper. In addition, the complex-valued network is specially designed for the complex-formatted UWA-OFDM signal, which can fully utilize the relationship between its real and imaginary parts with half of the spatial resources of its real-valued counterparts. The experiments with the at-sea-measured WATERMARK dataset indicate that the proposed method can perform a near-optimal channel estimation, and its low resource requirements (on dataset and model) make it more adaptable to real-world UWA applications.
本文提出了一种用于水声（UWA）正交频分复用（OFDM）信道估计的数据增强辅助复值网络，其中提出了基于经验模态分解的数据增强方法，以解决深度学习嵌入UWA-OFDM通信中的当前困境：实际应用中的数据稀缺和数据采样困难。此外，本文详细讨论了UWA信道高频分量增强的重要性及其对后续模型训练的积极影响，并通过实验进行了验证。此外，复值网络是专门为复格式UWA-OFDM信号设计的，它可以利用其实部和虚部之间的关系，占用实值对应网络一半的空间资源。对海上实测的WATERMARK数据集进行的实验表明，该方法能够实现接近最优的信道估计，并且其对数据集和模型的低资源需求使其更适用于实际的UWA应用。
