Discriminating fish species by an Echo sounder in a set-net using a CNN

Abstract

Currently, the prediction of fish species and catches is based on the experience of fishermen. Echo sounders can support fisheries; however, they cannot identify fish species. A system for the identification of fish species with machines has not been established. The purpose of this research is to propose a new method for the identification of fish species using echo sounders attached to a set-net. From the results of an experiment, five fish species (yellowtail, salmon, sardine, squid, and juvenile tuna) were identified with an accuracy of 95%.