Vessel classification is an extremely important task for coastal areas security and surveillance. Currently, this task relies on Synthetic Aperture Radar (SAR) images but gathering these images is expensive and often prohibitive. In this paper, we propose using spectrograms containing characteristic sound noise records of each vessel acquired from a single passive sonar device as an input to a convolutional neural network, which performs the classification. The main advantage of our method is its simplicity and low cost development due to the nature of this kind of data. Furthermore, our proposal can be used alongside other SAR-image-based method, potentially improving results of the overall classifier.
Adaptive filters exploiting sparsity have been a very active research field, among which the algorithms that follow the "proportional updates" principle, the so-called proportionatetype algorithms, are very popular. Indeed, there are hundreds of works on proportionate-type algorithms and, therefore, their advantages are widely known. This paper addresses the unexplored drawbacks and limitations of using proportional updates and their practical impacts. Our findings include the theoretical justification for the poor performance of these algorithms in several sparse scenarios, and also when dealing with non-stationary and compressible systems. Simulation results corroborating the theory are presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.