Abstract
We consider using sparse representations to identify underwater targets, since underwater acoustic signal have sparse characteristics. We consider the identification problem as one of the identifying among multiple linear regression models and believe that the new theory from sparse signal representation provides the key to solving this problem. Based on a sparse representation computed by l 1 -minimization, we propose a general classification algorithm for (hydroacoustic signal-based) targets identification. This new framework provides new insights into identifying two key issues in underwater targets: feature extraction and robustness of signal loss and noise interference. For feature extraction, we point out that feature extraction is no longer critical if the sparseness of the underwater acoustic signal is properly utilized. The critical is whether the number of features is large enough and whether the sparse representation is correctly computed. This framework can handle errors due to signal loss and noise interference uniformly by exploiting the fact that these errors are often sparse with respect to the standard (hydroacoustic signal) basis. Extensive experiments have been conducted based on a public underwater acoustic signal sampling set to verify the efficacy of the proposed algorithm and corroborate the above claims.
Highlights
Progress of underwater sensors and other equipment enable intelligent identification technology of underwater targets to be widely applied in many fields, primarily involving military invasion monitoring [1], exploitation of seabed resources [2], positioning and protection of fish [3] and so on
The main research method for underwater targets identification is the statistical identification method based on the theory of hydroacoustic signal and information processing [5].The low-dimensional observations of sparse representation must contain most of the useful information of the original
If the sparse basis of the hydroacoustic signal can be constructed, the compressed sensing can be applied to underwater signal processing, which can reduce the cost of signal processing, improve the compression efficiency, enhance the anti-noise performance of the identification system as well as the robustness
Summary
Progress of underwater sensors and other equipment enable intelligent identification technology of underwater targets to be widely applied in many fields, primarily involving military invasion monitoring [1], exploitation of seabed resources [2], positioning and protection of fish [3] and so on. 2) Our classification algorithm based on sparse representation differs significantly from the traditional classification method based on feature extraction (e.g., SVM and Random Forest(RF)).In this paper, instead of using sparsity to identify a related model or related features and using these features to classify all test samples, the sparse representation of each individual test sample is used directly for classification, and the training sample that gives the most concise representation (See Section IV-A) is adaptively selected. In experiments with sparse representations of test samples based on extended dictionary for signal loss and noise interference(See Section IV-B), the theories of sparse representations and compressed sensing characterize when such source-and-error separation is possible, the identification algorithm that determines how much signal loss and noise interference can tolerate these errors. The experimental results of SRC, SVM and Random Forest(RF) are compared and discussed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
