Machine learning methods of the Berlin brain-computer interface

Carmen Vidaurre, Claudia Sannelli, Wojciech Samek, Sven Dähne, Klaus Muller

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper is a compilation of the most recent machine learning methods used in the Berlin Brain-Computer Interface. In the field of Brain-Computer Interfacing, machine learning has been mainly used to extract meaningful features from noisy signals of large dimensionality and to classify them to transform them into computer commands. Recently, our group developed different methods to deal with noisy, non-stationary and high dimensional signals. These approaches can be seen as variants of the algorithm Common Spatial Patterns (CSP). All of them outperform CSP in the different conditions for which they were developed.

Original languageEnglish
Pages (from-to)447-452
Number of pages6
JournalIFAC-PapersOnLine
Volume28
Issue number20
DOIs
Publication statusPublished - 2015 Sep 1

Fingerprint

Brain computer interface
Learning systems
Brain

Keywords

  • Adaptive systems
  • Brain-computer interfacing
  • Electroencephalogram
  • Motor imagery
  • Multimodal analysis
  • Non-stationary analysis

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Vidaurre, C., Sannelli, C., Samek, W., Dähne, S., & Muller, K. (2015). Machine learning methods of the Berlin brain-computer interface. IFAC-PapersOnLine, 28(20), 447-452. https://doi.org/10.1016/j.ifacol.2015.10.181

Machine learning methods of the Berlin brain-computer interface. / Vidaurre, Carmen; Sannelli, Claudia; Samek, Wojciech; Dähne, Sven; Muller, Klaus.

In: IFAC-PapersOnLine, Vol. 28, No. 20, 01.09.2015, p. 447-452.

Research output: Contribution to journalArticle

Vidaurre, C, Sannelli, C, Samek, W, Dähne, S & Muller, K 2015, 'Machine learning methods of the Berlin brain-computer interface', IFAC-PapersOnLine, vol. 28, no. 20, pp. 447-452. https://doi.org/10.1016/j.ifacol.2015.10.181
Vidaurre C, Sannelli C, Samek W, Dähne S, Muller K. Machine learning methods of the Berlin brain-computer interface. IFAC-PapersOnLine. 2015 Sep 1;28(20):447-452. https://doi.org/10.1016/j.ifacol.2015.10.181
Vidaurre, Carmen ; Sannelli, Claudia ; Samek, Wojciech ; Dähne, Sven ; Muller, Klaus. / Machine learning methods of the Berlin brain-computer interface. In: IFAC-PapersOnLine. 2015 ; Vol. 28, No. 20. pp. 447-452.
@article{fb3a042ff22d4bea886894a09506875a,
title = "Machine learning methods of the Berlin brain-computer interface",
abstract = "This paper is a compilation of the most recent machine learning methods used in the Berlin Brain-Computer Interface. In the field of Brain-Computer Interfacing, machine learning has been mainly used to extract meaningful features from noisy signals of large dimensionality and to classify them to transform them into computer commands. Recently, our group developed different methods to deal with noisy, non-stationary and high dimensional signals. These approaches can be seen as variants of the algorithm Common Spatial Patterns (CSP). All of them outperform CSP in the different conditions for which they were developed.",
keywords = "Adaptive systems, Brain-computer interfacing, Electroencephalogram, Motor imagery, Multimodal analysis, Non-stationary analysis",
author = "Carmen Vidaurre and Claudia Sannelli and Wojciech Samek and Sven D{\"a}hne and Klaus Muller",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.ifacol.2015.10.181",
language = "English",
volume = "28",
pages = "447--452",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "20",

}

TY - JOUR

T1 - Machine learning methods of the Berlin brain-computer interface

AU - Vidaurre, Carmen

AU - Sannelli, Claudia

AU - Samek, Wojciech

AU - Dähne, Sven

AU - Muller, Klaus

PY - 2015/9/1

Y1 - 2015/9/1

N2 - This paper is a compilation of the most recent machine learning methods used in the Berlin Brain-Computer Interface. In the field of Brain-Computer Interfacing, machine learning has been mainly used to extract meaningful features from noisy signals of large dimensionality and to classify them to transform them into computer commands. Recently, our group developed different methods to deal with noisy, non-stationary and high dimensional signals. These approaches can be seen as variants of the algorithm Common Spatial Patterns (CSP). All of them outperform CSP in the different conditions for which they were developed.

AB - This paper is a compilation of the most recent machine learning methods used in the Berlin Brain-Computer Interface. In the field of Brain-Computer Interfacing, machine learning has been mainly used to extract meaningful features from noisy signals of large dimensionality and to classify them to transform them into computer commands. Recently, our group developed different methods to deal with noisy, non-stationary and high dimensional signals. These approaches can be seen as variants of the algorithm Common Spatial Patterns (CSP). All of them outperform CSP in the different conditions for which they were developed.

KW - Adaptive systems

KW - Brain-computer interfacing

KW - Electroencephalogram

KW - Motor imagery

KW - Multimodal analysis

KW - Non-stationary analysis

UR - http://www.scopus.com/inward/record.url?scp=84992478782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992478782&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2015.10.181

DO - 10.1016/j.ifacol.2015.10.181

M3 - Article

AN - SCOPUS:84992478782

VL - 28

SP - 447

EP - 452

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 20

ER -