Observatorio de I+D+i UPM

Memorias de investigación
Book chapters:
Applied Advanced Classifiers for Brain Computer Interface.
Research Areas
  • Electric engineers, electronic and automatic (eil),
  • Medical images,
  • Recognition of patterns,
  • Characteristic extraction
Brain Computer Interface is an emerging technology that allows new output paths to communicate the user?s intentions without the use of normal output paths, such as muscles or nerves. In order to obtain their objective, BCI devices make use of classifiers which translate inputs from the user?s brain signals into commands for external devices. This paper describes and compares the results of three types of classifiers based on three different types of neural networks: Radial Basis Functions (RBF), Probabilistic Neural Networks (PNN), and Multi-Layer Perceptrons (MLP). Before classifying the electroencephalographic signal into one of the different mental tasks used during the training phase, the signal is windowed with seven different types of preprocessing windows; so as to increase its discrimination capability. Tests carried out on five healthy volunteers resulted in the attainment of an estimation of the success rate of each classifier. This allows for the selection of the best type and architecture of neural network, as well as usage of the preprocessing window in the classifier.
Book Edition
Book Publishing
Book title
Recent Advances in Brain-Computer Interface Systems
From page
To page
  • Autor: Jose Luis Martínez Perez
  • Autor: Antonio Barrientos Cruz (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Robótica y Cibernética
  • Centro o Instituto I+D+i: Centro de Automática y Robótica (CAR). Centro Mixto UPM-CSIC
  • Departamento: Automática, Ingeniería Electrónica e Informática Industrial
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)