Abstract
This article focuses on an underwater acoustic target recognition method based on target radiated noise. The difficulty of underwater acoustic target recognition is mainly the extraction of effective classification features and pattern classification. Traditional feature extraction methods based on Low Frequency Analysis Recording (LOFAR), Mel-Frequency Cepstral Coefficients (MFCC), Gammatone-Frequency Cepstral Coefficients (GFCC), etc. essentially compress data according to a certain pre-set model, artificially discarding part of the information in the data, and often losing information helpful for classification. This paper presents a target recognition method based on feature auto-encoding. This method takes the normalized frequency spectrum of the signal as input, uses a restricted Boltzmann machine to perform unsupervised automatic encoding of the data, extracts the deep data structure layer by layer, and classifies the acquired features through the BP neural network. This method was tested using actual ship radiated noise database, and the results show that proposed classification system has better recognition accuracy and adaptability than the hand-crafted feature extraction based method.
Highlights
Underwater acoustic target recognition is the technique of identifying the type of target through the analysis of underwater acoustic signal
Feature extraction and pattern recognition are the key steps of an underwater acoustic target recognition algorithm
This kind of network has the characteristics of self-supervised training, which is suitable for the scene of underwater acoustic target recognition which lacks labeled data and can supplement the generalization ability of unknown signals for traditional feature extraction methods [30]
Summary
Underwater acoustic target recognition is the technique of identifying the type of target through the analysis of underwater acoustic signal. Feature extraction based on various neural network methods can adaptively extract the key information of the acoustic signal according to the probabilistic characteristics of the data, and it will have a better effect in the problem of multi-class division. DBM is composed of multi-layer RBM stack This kind of network has the characteristics of self-supervised training, which is suitable for the scene of underwater acoustic target recognition which lacks labeled data and can supplement the generalization ability of unknown signals for traditional feature extraction methods [30]. The result of feature extraction can be used to classify and recognize signals through neural network after dimensionality reduction It can obtain recognition performance better than hand-crafted features for ordinary noise signals.
Sign-in/Register to view highlights & summary 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.
