Abstract
In signal analysis and processing, underwater target recognition (UTR) is one of the most important technologies. Simply and quickly identify target types using conventional methods in underwater acoustic conditions is quite a challenging task. The problem can be conveniently handled by a deep learning network (DLN), which yields better classification results than conventional methods. In this paper, a novel deep learning method with a hybrid routing network is considered, which can abstract the features of time-domain signals. The used network comprises multiple routing structures and several options for the auxiliary branch, which promotes impressive effects as a result of exchanging the learned features of different branches. The experiment shows that the used network possesses more advantages in the underwater signal classification task.
Highlights
In the complicated and volatile ocean, underwater acoustic target recognition is considered as the most challenging task, and the objective conditions of the marine environment seriously interfere with the recognition accuracy, which mainly includes transmission attenuation, multi-path effects, and ocean environmental noise
HRNet, which is 4.46% and 3.67% better than auditory perception inspired deep CNN (ADCNN) and deep neural network (DNN), respectively—this is due to the fact that the hybrid routing network structure enriches the feature extraction of signals, which gain a better performance than convolutional recurrent neural network (CRNN), ADCNN, DNN, DepthCNN, and CDBN
The used network with the multiple routing forms and the optional auxiliary exchanging branches contributes to extracting a plenty of signal features and further boost the classification performance
Summary
In the complicated and volatile ocean, underwater acoustic target recognition is considered as the most challenging task, and the objective conditions of the marine environment seriously interfere with the recognition accuracy, which mainly includes transmission attenuation, multi-path effects, and ocean environmental noise. The characteristic selecting modes more or less result in the missing details of the raw signal; this determines how effective underwater acoustic identification algorithms will be for particular sound data. The deep representation of raw signal can be separated; this method achieves satisfactory performances in underwater acoustic target classification [15]. The underwater acoustic signal classifier adopts the convolutional recurrent neural network (CRNN), and the recurrent neural network (RNN), combined with a CNN, to acquire the different natures of sound characteristics, which further enhances the recognition effects by data augmentation [18]. When the main branch remains unchanged, the auxiliary branch adopts three optional orientations, and the classification ability of the used network is furthered by exchanging advanced signal features in different branches.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
