Comparative Study of Attribute Selection for Morphological Identification of Fishes

Abstract

Taxonomy is the science of naming, describing and classifying organisms that includes all plants, animals and microorganisms of the world. Using morphological, behavioral, genetic information and biochemical observations, taxonomists identify and describe species into classification. The taxonomic identification of fishes is a time-consuming process and making errors is indispensable for those who are not specialists. This system proposes an automated species identification system to identify taxonomic characters of species based on specimen and provide statistical clues for assisting taxonomists to identify accurate species or revision of misdiagnosed species. For this system, feature selection is an essential step to effectively reduce data dimensionality. This system first selects the best relevant features by using combination and the classification performance of two classifiers, Random Forest and Attributed Selected. And then correctly classifies the fish species and compares the accuracy of these two classifiers.