Artículo de publicación ISIIn this work we apply multi-class support vector machines (SVMs) and a multi-class stochastic SVM formulation
to the classification of fish schools of three species: anchovy, common sardine, and Jack Mackerel,
and we compare their performance. The data used come from acoustic measurements in southerncentral
Chile. These classifications were carried out by using a diver set of descriptors including morphology,
bathymetry, energy, and space positions. In both type of formulations, the deterministic and the stochastic
one, the strategy used to classify multi-class SVM consists in employing the criterion one-speciesagainst-
the-Rest. We thus provide an empirical way to adjust the parameters involved in the stochastic
classifiers with the aim of improving its performance. When this procedure is applied to the classification
of fish schools we obtain a classifier with a better performance than the deterministic classifier
Castillo, J., and Robotham, H. 2004. Spatial structure and geometry of schools of sardine (Sardinops sagax) in relation to abundance, fishing effort, and catch in northern Chile. e ICES Journal of Marine Science, 61: 1113e1119.We analysed the interrelationships of morphological, energetic, and relational descriptors of schools of sardines in the winter seasons of 1984e1990. A surface occupation index was used to measure the space covered by sardine. These descriptors were then related to catch, fishing effort, and catch per unit effort (cpue). We found that the greater the distance between the schools and the smaller the surface occupation index for schools, the smaller their size, biomass, and density. However, these descriptors were weakly related to the number of schools. The annual catch, fishing effort, and cpue were significantly and directly related to surface occupation index and inversely with the distance between schools. These fishery indices were weakly related to school area, school density, and school biomass. The change in the space occupied by sardine affected their catchability, as shown by the logarithmic relationship between the cpue and acoustic biomass. The lack of linearity can be corrected by taking into consideration the index of surface occupation of the stock so as to produce a corrected cpue (cpue*) value, which is directly proportional to stock biomass.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.