The Common Fisheries Policy of the European Union aims to exploit fish stocks at a level of Maximum Sustainable Yield by 2020 at the latest. At the Mediterranean level, the General Fisheries Commission for the Mediterranean (GFCM) has highlighted the importance of reversing the observed declining trend of fish stocks. In this complex context, it is important to obtain reliable biomass estimates to support scientifically sound advice for sustainable management of marine resources. This paper presents a machine learning methodology for the classification of pelagic species schools from acoustic and environmental data. In particular, the methodology was tuned for the recognition of anchovy, sardine and horse mackerel. These species have a central role in the fishing industry of Mediterranean countries and they are also of considerable importance in the trophic web because they occupy the so-called middle trophic level. The proposed methodology consists of a classifier based on an optimized two layer feed-forward neural network. Morphological, bathymetric, energetic and positional features, extracted from acoustic data, are used as input, together with other environmental data features. The classifier uses an optimal number of neurons in the hidden layer, and a feature selection strategy based on a genetic algorithm. Working on a dataset of 2565 fish schools, the proposed methodology permitted us to identify the these three fish species with an accuracy of around 95%.
|Numero di pagine||13|
|Stato di pubblicazione||Published - 2019|
All Science Journal Classification (ASJC) codes
- Ecology, Evolution, Behavior and Systematics
- Modelling and Simulation
- Ecological Modelling
- Computer Science Applications
- Computational Theory and Mathematics
- Applied Mathematics
Lo Bosco, G., Genovese, S., Aronica, S., Giacalone, G., Ferreri, R., Barra, M., Fontana, I., Mazzola, S., Basilone, G., Mazzola, S., Bonanno, A., & Rizzo, R. (2019). Identifying small pelagic Mediterranean fish schools from acoustic and environmental data using optimized artificial neural networks. Ecological Informatics, 50, 149-161.