Underwater target recognition is one of the most challenging tasks in underwater signal processing. Previous deep learning methods have relied on fusing more acoustic features, ignoring the rich information contained in the time-frequency features of underwater acoustics. Furthermore, fusing features that are less relevant to the target may result in redundancy and affect the recognition performance of the model. In this paper, a novel method based on Multi-Scale feature extraction, Attention mechanism for feature fusion and Convolutional Recurrent Neural Network (MACRN) is proposed to fully exploit the deep features of Mel-Frequency Cepstral Coefficients (MFCC) for underwater target recognition. In comparative experiments conducted on the open-source dataset ShipsEar, the proposed method achieves an average recognition accuracy of 98.1%


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Deep Learning Method for Ship-Radiated Noise Recognition Based on MFCC Feature


    Contributors:
    Hu, Fucai (author) / Fan, Jinyang (author) / Kong, Yiyang (author) / Zhang, Linke (author) / Guan, Xiaoxi (author) / Yu, Yongsheng (author)


    Publication date :

    2023-08-04


    Size :

    830368 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Underwater radiated noise of the NOAA ship Oscar Dyson

    Bahtiarian, Michael / Fischer, Raymond | Tema Archive | 2006


    Acoustic Target Recognition Based on MFCC and SVM

    Ding, Kai / Zheng, Shoujun / Qi, Xiaogang et al. | Springer Verlag | 2022


    Speech Emotion Recognition Based on 1D CNN and MFCC

    Li, Gaoyun / Liu, Yong / Wang, Xiong | IEEE | 2023



    Offshore dock for measuring underwater radiated noise of ship

    SHANG DAJING / LI QI / TANG RUI et al. | European Patent Office | 2020

    Free access