Observatorio de I+D+i UPM

Memorias de investigación
Classification of MEG data using a combined machine learning approach
Research Areas
  • Artificial intelligence
In this study subjects were asked to covertly attend left, right, up or down. Apply a classifier to predict in which direction the subjects were covertly attending. Apply a multi-variable channel information representation. Use and combine different type of information (raw data, channels correlation, interaction graphs). Apply an efficient classification method (deals with up to 53841 variables and 254 cases). Search for a subset of informative channels (out of 274) using a multi-objective evolutionary-based optimization algorithm over the four subjects. Use classification accuracy estimation to reduce the cost of the accuracy evaluation step. Apply leave-one-out cross-validation to the Pareto set of optimal solutions.
17th International Conference on Biomagnetism
Entity Nationality
Sin nacionalidad
Dubrovnik, Croacia
  • Autor: Roberto Santana Hermida (UPM)
  • Autor: Maria Concepcion Bielza Lozoya (UPM)
  • Autor: Pedro Maria Larrañaga Mugica (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: COMPUTATIONAL INTELLIGENCE GROUP
  • Centro o Instituto I+D+i: Centro de tecnología Biomédica CTB
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)