Application of wrapper methods for feature selection in modelling ripening process of a viticulture crop

  1. Fernandez-Martinez, R. 1
  2. Fernandez-Ceniceros, J. 1
  3. Sanzgarcia, A. 1
  4. Lostado-Lorza, R. 1
  5. Martinezdepison-Ascacibar, F.J. 1
  1. 1 Universidad de La Rioja
    info

    Universidad de La Rioja

    Logroño, España

    ROR https://ror.org/0553yr311

Book:
10th WSEAS International Conference on Applied Computer and Applied Computational Science, ACACOS'11

ISBN: 978-960-474-281-3

Year of publication: 2011

Pages: 142-147

Type: Book chapter

SCOPUS: 2-s2.0-79956146789 GOOGLE SCHOLAR lock_openOpen access editor

Abstract

The importance of final quality in agricultural products is growing ever greater, and is causing many crops to be monitored. This trend and the improvement of devices that can obtain the necessary information, make that it is stored large amount of information to work with. Apply learning algorithms in this amount of variables and data stored does that it is returned high execution times and calculation errors. To solve this problem, it is used feature reduction methods to select the most relevant information in order to reduce execution times and errors generated. Specifically, in this study, wrapper methods are used to select the most influential environmental variables during viticulture crop ripening.