Memorias de investigación
Conferences:
Classification of MEG data using a combined machine learning approach
Year:2010

Research Areas
  • Artificial intelligence

Information
Abstract
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.
International
Si
978-3-642-12196-8
Entity
17th International Conference on Biomagnetism
Entity Nationality
Sin nacionalidad
Place
Dubrovnik, Croacia
Participants

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: COMPUTATIONAL INTELLIGENCE GROUP
  • Centro o Instituto I+D+i: Centro de tecnología Biomédica CTB