Artificial neural networks as a tool for species identification of fish schools

Abstract

Fish schools of sardine, anchovy, and horse mackerel can be discriminated from each other, under given conditions, using a set of parameters extracted from echointegration data. Trawl sampling and hydroacoustic data were collected in 1992 and 1993 in the Thermaikos Gulf by using a towed dual-beam 120 kHz transducer. The parameters extracted from the available schools were used to train multi-layered feed-forward artificial neural networks. Various applied networks easily generated associations between school descriptors and species identity, providing a powerful tool for classification. The expertise of the trained network was tested with data from identified schools not used in training. The use of neural networks cannot replace classical statistical procedures, but offers an alternative when there are significant overlaps in the school characteristics and the parametric assumptions are not satisfied.1996 International Council for the Exploration of the Sea

The Use of Artificial Neural Networks (ANNs) in Aquatic Ecology

“…When ANNs were not found to perform better than linear methods it was most probably due to non-optimal training strategies, ANN architectures or data-limited situations. Haralabous & Georgakarakos (1996) reported that comparing ANNs and DA is not straightforward, because an ANN can only be tested on a subset of training-free cases, while DA can be acceptably tested on the whole dataset. However, this is not exactly correct because the performance of DA cannot be tested without an independent test set.…”

“…Ozesmi & Ozesmi (1999) predicted the nesting probability of two riverine bird species using 6 environmental variables. The MLP has also been used to identify three different fish species from 25 variables corresponding to the main school descriptors (Haralabous & Georgakarakos, 1996). Power et al (2005) made use of MLP to classify a marine fish species according to the three different fisheries from which it was harvested using as predictors the abundance of different sets of parasites (3-6).…”

Clasificacion acustica de anchoveta (Engraulis ringens) y sardina comun (Strangomera bentincki) mediante maquinas de vectores soporte en la zona centro sur de Chile: efecto de la calibracion de los parametros en la matriz de confusion

“…La menor exactitud indicada se debe a que el método multiclase utilizó en el proceso de clasificación una tercera especie (jurel), lo que genera funciones de decisión más complejas, adicionalmente la muestra utilizada en el proceso de calibración se encontraba desbalanceada, factores que sin duda podrían incidir en la menor clasificación. Estudios similares sobre estas especies en el área no han sido reportados, sin embargo, otros estudios con otros métodos y especies reportan tasas de clasificación entre 77 y 96% (Haralabous & Georgakarakos, 1996;Simmonds et al, 1996;Lawson et al, 2001;Cabreira et al, 2009;Korneliussen et al, 2009;Fernandes, 2009).…”

“…La clasificación de cardúmenes monoespecíficos con información de una única frecuencia acústica se ha realizado mediante un amplio rango de técnicas estadísticas, destacándose los métodos multivariados como análisis de componentes principales y de funciones discriminantes (Nero & Magnuson, 1989;Vray et al, 1990;Scalabrin et al, 1996;Lawson et al, 2001). También se han aplicado métodos de clasificación como redes neuronales artificiales (Haralabous & Georgakarakos, 1996;Simmonds et al, 1996;Cabreira et al, 2009); análisis del vecino más cercano (Richards et al, 1991); conglomerados k-medias (Tegowski et al, 2003); modelos mixtos (Fleischman & Burwen, 2003), método de Kernel (Buelens et al, 2009); métodos árboles de clasificación (Fernandes, 2009). Demer et al (2009) utilizan el análisis estadístico espectral.…”

Fish School Identification in the Bali Strait Using Acoustic Descriptor and Artificial Neural Networks Techniques

“…The ANN has been used in fish school identification (Haralabous and Georgakarakos, 1996) and then combined with discriminant analysis (Simmonds et al, 1996). The usage of ANN technique is expected to overcome the difficulty of identifying fish school as mentioned early.…”