Physical Fields of Ship, Ocean and Atmosphere         
Original article
http://doi.org/10.24866/2227-6858/2022-2/62-68

Kuzin D., Statsenko L.

DENIS А. KUZIN, Senior Lecturer, kuzindeal@gmail.com^*
LUBOV G. STATSENKO, Doctor of Physico-Mathematical Sciences, Professor, lu-sta@mail.ru
Department of Electronics and Communications
Polytechnic Institute
Far Eastern Federal University
Vladivostok, Russia

Comparative analysis of machine learning models in classifying hydroacoustic noises of sea vessels

Abstract. The automated identification and classification of marine objects by hydroacoustic noise is an important task in water areas monitoring and World Ocean exploration. The important stages in the development of an automated object recognition system are the choice of a classifier and choice of features. The article provides a comparative analysis of the accuracy of determining the ship class based on its hydroacoustic noise by three different models of machine learning and an artificial neural network.

Keywords: machine learning, hydroacoustic noise features, marine objects classification, audio signal processing

See the reference in English at the end of the article

For citation: Kuzin D., Statsenko L. Comparative analysis of machine learning models in classifying hydroacoustic noises of sea vessels. FEFU: School of Engineering Bulletin. 2022;(2):62-68. (In Russ.).