WOA based Selection and Parameter Optimization of SVM Kernel Function for Underwater Target Classification

Sherin B. M., Dr. Supriya M. H.


The identification and classification of noise sources in the ocean is a challenging task due to a myriad of impediments introduced by the complicated oceanic environment. The underwater target recognition system essentially has to identify underwater targets of interest that are heavily masked by the oceanic noise. The characteristic acoustic signatures of the underwater targets of interest, are patterned by feature recognition algorithms operating on data captured by hydrophone. In this paper, an SVM based classifier is used to distinguish between 4 classes of acoustic targets and attempt is made towards improving the performance of the classifier by automating the selection of kernel and algorithmic parameters of the underlying classifier through Whale Optimization Algorithm (WOA).

Keywords: Underwater target classifier, Support Vector machines, Kernel Function, Whale Optimization Algorithm.

Full Text:


DOI: https://doi.org/10.26483/ijarcs.v8i3.2982


  • There are currently no refbacks.

Copyright (c) 2017 International Journal of Advanced Research in Computer Science