Pelagic species identification by using a PNN neural network and echo-sounder data
- Autori: Fontana, I.; Giacalone, G.; Bonanno, A.; Mazzola, S.; Basilone, G.; Genovese, S.; Aronica, S.; Pissis, S.; Iliopoulos, C.; Kundu, R.; Fiannaca, A.; Langiu, A.; Lo Bosco, G.; La Rosa, M.; Rizzo, R.
- Anno di pubblicazione: 2017
- Tipologia: Abstract in atti di convegno pubblicato in volume (Breve introduzione)
- OA Link: http://hdl.handle.net/10447/248857
Abstract
For several years, a group of CNR researchers conducted acoustic surveys in the Sicily Channel to estimate the biomass of small pelagic species, their geographical distribution and their variations over time. The instrument used to carry out these surveys is the scientific echo-sounder, set for different frequencies. The processing of the back scattered signals in the volume of water under investigation determines the abundance of the species. These data are then correlated with the biological data of experimental catches, to attribute the composition of the various fish schools investigated. Of course, the recognition of the fish schools helps to produce very good results, that is very close to the truth about the abundances associated with the various species. In this work, only the acoustic traces of biological monospecific catches, exclusively of two species of pelagic fish. The ecograms where pre-processed using various software tools [1, 2]. For this work, the potential fish schools are detected and isolated using the SHAPES algorithm in Echoview. At the end of the pre-processing phase, the signals are labelled using the two species of pelagic fish: Engraulis encrasicolus and Sardina pilchardus. These labelled signals were used to train a Probabilistic Neural Network (PNN) [3].