Jump to ContentJump to Main Navigation
Show Summary Details

Biomedical Engineering / Biomedizinische Technik

Editor-in-Chief: Dössel, Olaf

Editorial Board Member: Augat, Peter / Haueisen, Jens / Jockenhoevel, Stefan / Lenarz, Thomas / Leonhardt, Steffen / Plank, Gernot / Radermacher, Klaus M. / Schkommodau, Erik / Schmitz, Georg / Stieglitz, Thomas / Witte, Herbert / Boenick, Ulrich / Jaramaz, Branislav / Kraft, Marc / Lenthe, Harry / Lo, Benny / Mainardi, Luca / Micera, Silvestro / Penzel, Thomas / Robitzki, Andrea A. / Schaeffter, Tobias / Snedeker, Jess G. / Sörnmo, Leif / Sugano, Nobuhiko / Werner, Jürgen / Wintermantel, Erich /

6 Issues per year

IMPACT FACTOR increased in 2015: 1.650

See all formats and pricing


Select Volume and Issue


Volume 57 (2012)

30,00 € / $42.00 / £23.00

Get Access to Full Text

Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear classifier

David Steyrl
  • Institute for Knowledge Discovery, BCI Lab, Graz University of Technology, Graz, Austria
/ Reinhold Scherer
  • Institute for Knowledge Discovery, BCI Lab, Graz University of Technology, Graz, Austria
  • :
/ Josef Faller
  • Biological Psychology and Neuroergonomics, Berlin Institute of Technology, Berlin, Germany
/ Gernot R. Müller-Putz
  • Institute for Knowledge Discovery, BCI Lab, Graz University of Technology, Graz, Austria
Published Online: 2015-04-01 | DOI: https://doi.org/10.1515/bmt-2014-0117


There is general agreement in the brain-computer interface (BCI) community that although non-linear classifiers can provide better results in some cases, linear classifiers are preferable. Particularly, as non-linear classifiers often involve a number of parameters that must be carefully chosen. However, new non-linear classifiers were developed over the last decade. One of them is the random forest (RF) classifier. Although popular in other fields of science, RFs are not common in BCI research. In this work, we address three open questions regarding RFs in sensorimotor rhythm (SMR) BCIs: parametrization, online applicability, and performance compared to regularized linear discriminant analysis (LDA). We found that the performance of RF is constant over a large range of parameter values. We demonstrate – for the first time – that RFs are applicable online in SMR-BCIs. Further, we show in an offline BCI simulation that RFs statistically significantly outperform regularized LDA by about 3%. These results confirm that RFs are practical and convenient non-linear classifiers for SMR-BCIs. Taking into account further properties of RFs, such as independence from feature distributions, maximum margin behavior, multiclass and advanced data mining capabilities, we argue that RFs should be taken into consideration for future BCIs.

Keywords: brain-computer interfaces; machine learning; random forests; regularized linear discriminant analysis; sensorimotor rhythms

Corresponding author: Reinhold Scherer, Institute for Knowledge Discovery, Laboratory of Brain-Computer Interfaces, Graz University of Technology, Inffeldgasse 13/IV, 8010 Graz, Austria, Phone: +43 316 873 30713, Fax: +43 316 873 30702, E-mail:

Received: 2014-10-03

Accepted: 2015-03-02

Published Online: 2015-04-01

Published in Print: 2016-02-01

Citation Information: Biomedical Engineering / Biomedizinische Technik. Volume 61, Issue 1, Pages 77–86, ISSN (Online) 1862-278X, ISSN (Print) 0013-5585, DOI: https://doi.org/10.1515/bmt-2014-0117, April 2015

Comments (0)

Please log in or register to comment.