DSpace Repository

An experimental features selection approach in a multiclass classifier

An experimental features selection approach in a multiclass classifier
 
Reig Bolaño, Ramon ; Martí i Puig, Pere
2013

Files in this item

Icon
Name: artconlli_a2013_reig_ramon_experimental_features.pdf
Size: 265.0Kb
Format: PDF
Description: Només accés administradors
Enllaç permanent: http://hdl.handle.net/10854/2801
 
Versió de l'editor: https://doi.org/10.3233/978-1-61499-320-9-137
 

Abstract

This paper focuses on an experimental feature selection for the images of otoliths in order to validate their effectiveness in a multiclass classifier used to resolve an automatic otolith identification process. Otoliths are calcareus structures found in the inner ear of fishes and are used to identifie species, populations, ...»»»»
This paper focuses on an experimental feature selection for the images of otoliths in order to validate their effectiveness in a multiclass classifier used to resolve an automatic otolith identification process. Otoliths are calcareus structures found in the inner ear of fishes and are used to identifie species, populations, age and can be used in other ecological studies. The most relevant result confirms the importance of high order EFD coefficients to discriminate close shape specimens or populations.^^^^

Type:

Book part

Rights:

 
(c) 2013 IOP Press
 
Tots els drets reservats
 

Citation:

Reig Bolaño, R., & Martí-Puig, P. (2013). In Gibert K., Botti V. & Reig Bolaño R.(Eds.), An experimental features selection approach in a multiclass classifier. A: Frontiers in Artificial Intelligence and Applications, vol. 256, IOS Press, 2013, pp. 137-140 doi:10.3233/978-1-61499-320-9-137