Abstract
The loudness and timbre of propeller are remarkable features of ship-radiated noise. The information of loudness and timbre is indicated in the wave structure of time series, and the feature of wave structure can be applied to classify various marine acoustic targets. In this paper, the feature extracting method of time series wave structure is studied. A nine-dimensional feature vector is constructed through statistical characteristics, containing zero-crossing wavelength, peek-to-peek amplitude, zero-crossing-wavelength difference and wave train areas. The feature vectors are inputted into SVM classifier to identify marine acoustic targets. The kernel function is set radial basis function (RBF).The penalty factor and kernel width of RBF are selected by the method of grid search. Finally, the recognition rate of test data reaches over 89.5%, with the help of cross validation. The sea-test data show the validity of target recognition ability of the method above.
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.
