AUTHOR=Wang Yan , Xiao Jing , Cheng Xiao , Wei Qiang , Tang Ning 

TITLE=Underwater acoustic signal classification based on a spatial–temporal fusion neural network

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2024.1331717

DOI=10.3389/fmars.2024.1331717

ISSN=2296-7745

ABSTRACT=In the paper, a novel fusion network for automatic modulation classification (AMC) is proposed in underwater acoustic communication, which consists of Transformer and depth wise convolution (DWC) network. Transformer breaks the limitation of sequential signal input and establishes the connection between different modulations in the parallel manner. Its attention mechanism can improve the modulation recognition ability by focusing on the key information. DWC is regularly inserted in the Transformer network to constitute spatial-temporal structure, which can enhance the classification results at lower signal-to-noise ratios (SNRs). The proposed method can obtain more deep features of underwater acoustic signals. The experiment results achieve average 92.1% at -4dB ≤ SNR ≤ 0dB, which exceed other state-of-the-art neural networks.