Learning from more than one data source: Data fusion techniques for sensorimotor rhythm-based brain - Computer interfaces

Siamac Fazli, Sven Dähne, Wojciech Samek, Felix Bießmann, Klaus Muller

Research output: Contribution to journalArticle

48 Citations (Scopus)

Abstract

Brain-computer interfaces (BCIs) are successfully used in scientific, therapeutic and other applications. Remaining challenges are among others a low signal-to-noise ratio of neural signals, lack of robustness for decoders in the presence of inter-trial and inter-subject variability, time constraints on the calibration phase and the use of BCIs outside a controlled lab environment. Recent advances in BCI research addressed these issues by novel combinations of complementary analysis as well as recording techniques, so called hybrid BCIs. In this paper, we review a number of data fusion techniques for BCI along with hybrid methods for BCI that have recently emerged. Our focus will be on sensorimotor rhythm-based BCIs. We will give an overview of the three main lines of research in this area, integration of complementary features of neural activation, integration of multiple previous sessions and of multiple subjects, and show how these techniques can be used to enhance modern BCI systems.

Original languageEnglish
Article number7110317
Pages (from-to)891-906
Number of pages16
JournalProceedings of the IEEE
Volume103
Issue number6
DOIs
Publication statusPublished - 2015 Jun 1

Fingerprint

Brain computer interface
Data fusion
Signal to noise ratio
Chemical activation
Calibration

Keywords

  • Brain-computer interface (BCI)
  • data fusion
  • electroencephalography (EEG)
  • hybrid BCI
  • multi-modal
  • mutual information
  • near-infrared spectroscopy (NIRS)
  • zero-training

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Learning from more than one data source : Data fusion techniques for sensorimotor rhythm-based brain - Computer interfaces. / Fazli, Siamac; Dähne, Sven; Samek, Wojciech; Bießmann, Felix; Muller, Klaus.

In: Proceedings of the IEEE, Vol. 103, No. 6, 7110317, 01.06.2015, p. 891-906.

Research output: Contribution to journalArticle

Fazli, Siamac ; Dähne, Sven ; Samek, Wojciech ; Bießmann, Felix ; Muller, Klaus. / Learning from more than one data source : Data fusion techniques for sensorimotor rhythm-based brain - Computer interfaces. In: Proceedings of the IEEE. 2015 ; Vol. 103, No. 6. pp. 891-906.
@article{78a9d0c725ef43f9a63c839c226659a9,
title = "Learning from more than one data source: Data fusion techniques for sensorimotor rhythm-based brain - Computer interfaces",
abstract = "Brain-computer interfaces (BCIs) are successfully used in scientific, therapeutic and other applications. Remaining challenges are among others a low signal-to-noise ratio of neural signals, lack of robustness for decoders in the presence of inter-trial and inter-subject variability, time constraints on the calibration phase and the use of BCIs outside a controlled lab environment. Recent advances in BCI research addressed these issues by novel combinations of complementary analysis as well as recording techniques, so called hybrid BCIs. In this paper, we review a number of data fusion techniques for BCI along with hybrid methods for BCI that have recently emerged. Our focus will be on sensorimotor rhythm-based BCIs. We will give an overview of the three main lines of research in this area, integration of complementary features of neural activation, integration of multiple previous sessions and of multiple subjects, and show how these techniques can be used to enhance modern BCI systems.",
keywords = "Brain-computer interface (BCI), data fusion, electroencephalography (EEG), hybrid BCI, multi-modal, mutual information, near-infrared spectroscopy (NIRS), zero-training",
author = "Siamac Fazli and Sven D{\"a}hne and Wojciech Samek and Felix Bie{\ss}mann and Klaus Muller",
year = "2015",
month = "6",
day = "1",
doi = "10.1109/JPROC.2015.2413993",
language = "English",
volume = "103",
pages = "891--906",
journal = "Proceedings of the IEEE",
issn = "0018-9219",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Learning from more than one data source

T2 - Data fusion techniques for sensorimotor rhythm-based brain - Computer interfaces

AU - Fazli, Siamac

AU - Dähne, Sven

AU - Samek, Wojciech

AU - Bießmann, Felix

AU - Muller, Klaus

PY - 2015/6/1

Y1 - 2015/6/1

N2 - Brain-computer interfaces (BCIs) are successfully used in scientific, therapeutic and other applications. Remaining challenges are among others a low signal-to-noise ratio of neural signals, lack of robustness for decoders in the presence of inter-trial and inter-subject variability, time constraints on the calibration phase and the use of BCIs outside a controlled lab environment. Recent advances in BCI research addressed these issues by novel combinations of complementary analysis as well as recording techniques, so called hybrid BCIs. In this paper, we review a number of data fusion techniques for BCI along with hybrid methods for BCI that have recently emerged. Our focus will be on sensorimotor rhythm-based BCIs. We will give an overview of the three main lines of research in this area, integration of complementary features of neural activation, integration of multiple previous sessions and of multiple subjects, and show how these techniques can be used to enhance modern BCI systems.

AB - Brain-computer interfaces (BCIs) are successfully used in scientific, therapeutic and other applications. Remaining challenges are among others a low signal-to-noise ratio of neural signals, lack of robustness for decoders in the presence of inter-trial and inter-subject variability, time constraints on the calibration phase and the use of BCIs outside a controlled lab environment. Recent advances in BCI research addressed these issues by novel combinations of complementary analysis as well as recording techniques, so called hybrid BCIs. In this paper, we review a number of data fusion techniques for BCI along with hybrid methods for BCI that have recently emerged. Our focus will be on sensorimotor rhythm-based BCIs. We will give an overview of the three main lines of research in this area, integration of complementary features of neural activation, integration of multiple previous sessions and of multiple subjects, and show how these techniques can be used to enhance modern BCI systems.

KW - Brain-computer interface (BCI)

KW - data fusion

KW - electroencephalography (EEG)

KW - hybrid BCI

KW - multi-modal

KW - mutual information

KW - near-infrared spectroscopy (NIRS)

KW - zero-training

UR - http://www.scopus.com/inward/record.url?scp=85027956954&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027956954&partnerID=8YFLogxK

U2 - 10.1109/JPROC.2015.2413993

DO - 10.1109/JPROC.2015.2413993

M3 - Article

AN - SCOPUS:85027956954

VL - 103

SP - 891

EP - 906

JO - Proceedings of the IEEE

JF - Proceedings of the IEEE

SN - 0018-9219

IS - 6

M1 - 7110317

ER -