Ensembles of wrappers for automated feature selection in fish age classification

• Published in: Computers and Electronics in Agriculture
• Main Author: Bermejo Sánchez, Sergi
• Other Authors: Universitat Politècnica de Catalunya. Departament d'Enginyeria Electrònica
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2017
• Subjects: Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica; Àrees temàtiques de la UPC::Enginyeria agroalimentària::Agricultura; Agriculture > Data processing; Automated fish age classification; Atlantic cod otoliths; Feature selection; Nearest neighbor classifiers; Statistical pattern recognition; Support vector machines; Agricultura > Informàtica; atlantic cod
• Online Access: http://hdl.handle.net/2117/100219; https://doi.org/10.1016/j.compag.2017.01.007

In feature selection, the most important features must be chosen so as to decrease the number thereof while retaining their discriminatory information. Within this context, a novel feature selection method based on an ensemble of wrappers is proposed and applied for automatically select features in fish age classification. The effectiveness of this procedure using an Atlantic cod database has been tested for different powerful statistical learning classifiers. The subsets based on few features selected, e.g. otolith weight and fish weight, are particularly noticeable given current biological findings and practices in fishery research and the classification results obtained with them outperforms those of previous studies in which a manual feature selection was performed. Peer Reviewed Postprint (author's final draft)